Article(id=1327017418712527812, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327017337032651028, articleNumber=null, orderNo=null, doi=10.7544/issn1000-1239.202440315, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1714924800000, receivedDateStr=2024-05-06, revisedDate=1744128000000, revisedDateStr=2025-04-09, acceptedDate=null, acceptedDateStr=null, onlineDate=1794315207411, onlineDateStr=2026-11-10, pubDate=1764518400000, pubDateStr=2025-12-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794315207411, onlineIssueDateStr=2026-11-10, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794315207411, creator=13701087609, updateTime=1794315207411, updator=13701087609, issue=Issue{id=1327017337032651028, tenantId=1146029695717560320, journalId=1324759914146529478, year='2025', volume='62', issue='12', pageStart='2889', pageEnd='3146', issueExtLink='null', onlineDate='null', pubDate='1764518400000', pubDateStr='2025-12-01', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794315187938, creator='13701087609', updateTime=1794377025235, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1327276701995872766, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327017337032651028, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1327276701995872767, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327017337032651028, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=2895, endPage=2928, ext={EN=ArticleExt(id=1327017418930631621, articleId=1327017418712527812, tenantId=1146029695717560320, journalId=1324759914146529478, language=EN, title=Survey on Object Detection Models, columnId=1325489891789910943, journalTitle=Journal of Computer Research and Development, columnName=Artificial Intelligence, runingTitle=null, highlight=null, articleAbstract=
Object detection technology, as a pivotal component in computer vision, plays a vital role in diverse practical applications. Over decades of evolution, the field has progressed from early methods relying on handcrafted feature extraction to the widespread adoption of deep learning models. Currently, there remains a lack of systematic reviews tracing the developmental trajectory of object detection through improvements in deep learning foundation models. Addressing this gap, this paper organizes the technological evolution around the progression of foundation models in artificial intelligence. We systematically survey detection models built upon various foundation models, compare their strengths and weaknesses, and analyze improvement strategies. The paper also surveys evaluation metrics and technological advancements across different eras, with particular emphasis on how deep learning has driven remarkable performance gains. We discuss persistent challenges in handling diverse scenarios, improving real-time efficiency, and enhancing accuracy. Furthermore, we explore prospective research directions, including model generalization capabilities, computational efficiency, and integration with complex tasks, proposing potential enhancement strategies. This work aims to provide a clear perspective on technological evolution to facilitate further research and applications in object detection.
, authors=Chengye Li
1, 2, 3, 4, Zhen Zhang
1, 2, 3, 4, Zheheng Liang
5, 6, Chaosheng Yao
5, 6, Jinbo Zhang
5, 6, Rongjie Yan
2, 3, 4, *, Peng Wu
2, 3, 4, authorsList=Chengye Li, Zhen Zhang, Zheheng Liang, Chaosheng Yao, Jinbo Zhang, Rongjie Yan, Peng Wu, authorCompany=null, correspAuthors=Rongjie Yan, authorNote=
born in 1999. Master candidate. Student member of CCF. His main research interests include trustworthy AI and deep learning
born in 1995. PhD candidate. Student member of CCF. His main research interests include anomaly detection, deep learning, computer vision, and natural language processing
born in 1986. Master, senior engineer. Member of CCF. His main research interest includes digital evaluation technology
born in 1989. Bachelor, engineer. Member of CCF. His main research interest includes project quality control
born in 1979. Master, senior engineer. His main research interest includes information system testing
born in 1977. PhD, associate professor. Senior member of CCF. Her main research interest includes testing and validation of intelligent software and autonomous unmanned systems
born in 1977. PhD, associate professor. Senior member of CCF. His main research interests include formal method, concurrent testing, and machine learning
, correspAuthorsNote=null, copyrightStatement=Copyright © 2025 Journal of Computer Research and Development. All rights reserved., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1327017423842161652, articleId=1327017418712527812, tenantId=1146029695717560320, journalId=1324759914146529478, language=CN, title=目标检测模型综述, columnId=1325489892104483745, journalTitle=计算机研究与发展, columnName=人工智能, runingTitle=null, highlight=null, articleAbstract=
目标检测技术是计算机视觉领域的关键组成部分,它在各种实际应用中扮演着至关重要的角色. 目标检测技术经历了几十年的发展,从早期依赖于手工特征提取的方法,到当前深度学习模型的广泛应用. 目前在目标检测领域缺少以深度学习基础模型技术的改进为发展脉络的总结研究下,以人工智能领域基础模型的发展过程为线索,围绕不同种类基础模型概述了基于这些模型的不同目标检测模型的发展,同时对这些基于不同模型的目标检测算法进行了比较,并分析不同模型的优缺点以及制定不同模型的改进策略. 概述了目标检测技术的评估指标以及不同阶段的技术,特别强调了深度学习如何推动目标检测性能的显著提升,讨论了目标检测在处理多样化场景以及提高实时性和准确性方面的挑战,并对未来可能的研究方向进行了深度探讨,包括但不限于模型的泛化能力、计算效率以及与更复杂任务的结合,为多个未来研究方向提出了可能的提高策略. 旨在提供一个清晰的技术演进视角,以促进目标检测领域的进一步研究和应用.
, authors=李承烨
1, 2, 3, 4, 张震
1, 2, 3, 4, 梁哲恒
5, 6, 姚潮生
5, 6, 张金波
5, 6, 晏荣杰
2, 3, 4, *, 吴鹏
2, 3, 4, authorsList=李承烨, 张震, 梁哲恒, 姚潮生, 张金波, 晏荣杰, 吴鹏, authorCompany=null, correspAuthors=晏荣杰, authorNote=
 |
1999年生. 硕士研究生. CCF学生会员. 主要研究方向为可信人工智能、深度学习 |
 |
1995年生. 博士研究生. CCF学生会员. 主要研究方向为异常检测、深度学习、计算机视觉、自然语言处理 |
 |
1986年生. 硕士,高级工程师. CCF会员. 主要研究方向为数字化评测技术 |
 |
1989年生. 学士,工程师. CCF会员. 主要研究方向为项目质量管控 |
 |
1979年生. 硕士,高级工程师. 主要研究方向为信息系统测试 |
 |
1977年生. 博士,副研究员. CCF高级会员. 主要研究方向为智能软件、自主无人系统的测试与验证 |
 |
1977年生. 博士,副研究员. CCF高级会员. 主要研究方向为形式化方法、并发测试、机器学习 |
, correspAuthorsNote=
, copyrightStatement=版权所有 © 2025 计算机研究与发展编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=oQPgQPRZvu6EgvNEgA9bxA==, magXml=y5a9/MbYwZ1QH0xbTHldRw==, pdfUrl=null, pdf=Ww5/bn5Wul+J4NtWjIcxiw==, pdfFileSize=6173585, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=IZZAqq1lSoEAcGGbJyRVoA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=uC6xGN/2pe/AD1vT0Lzz/w==, mapNumber=null, fund=null)}, authors=[Author(id=1327017424752324615, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=licy@ios.ac.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327017424844599308, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, authorId=1327017424752324615, language=EN, stringName=Chengye Li, firstName=Chengye, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, 3, 4, address=
1Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024
2CAS Key Laboratory of System Software, Beijing 100190
3State Key Laboratory of Computer Science (Institute of Software, Chinese Academy of Sciences), Beijing 100190
4University of Chinese Academy of Sciences, Beijing 100049, bio={"content":"
born in 1999. Master candidate. Student member of CCF. His main research interests include trustworthy AI and deep learning
"}, bioImg=null, bioContent=
born in 1999. Master candidate. Student member of CCF. His main research interests include trustworthy AI and deep learning
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327017424907513869, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, authorId=1327017424752324615, language=CN, stringName=李承烨, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, 3, 4, address=
1中国科学院大学杭州高等研究院 杭州 310024
2中国科学院基础软件与系统重点实验室 北京 100190
3计算机科学国家重点实验室(中国科学院软件研究所) 北京 100190
4中国科学院大学 北京 100049, bio={"img":"dm5uy1IKRxfmKCXO9E0axQ==","content":"
1999年生. 硕士研究生. CCF学生会员. 主要研究方向为可信人工智能、深度学习
"}, bioImg=dm5uy1IKRxfmKCXO9E0axQ==, bioContent=
1999年生. 硕士研究生. CCF学生会员. 主要研究方向为可信人工智能、深度学习
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327017424098014197, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, xref=1, ext=[AuthorCompanyExt(id=1327017424110597110, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424098014197, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024), AuthorCompanyExt(id=1327017424123180023, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424098014197, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1中国科学院大学杭州高等研究院 杭州 310024)]), AuthorCompany(id=1327017424215454712, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, xref=2, ext=[AuthorCompanyExt(id=1327017424228037625, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424215454712, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2CAS Key Laboratory of System Software, Beijing 100190), AuthorCompanyExt(id=1327017424240620538, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424215454712, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2中国科学院基础软件与系统重点实验室 北京 100190)]), AuthorCompany(id=1327017424324506619, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, xref=3, ext=[AuthorCompanyExt(id=1327017424337089532, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424324506619, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3State Key Laboratory of Computer Science (Institute of Software, Chinese Academy of Sciences), Beijing 100190), AuthorCompanyExt(id=1327017424345478141, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424324506619, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3计算机科学国家重点实验室(中国科学院软件研究所) 北京 100190)]), AuthorCompany(id=1327017424437752830, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, xref=4, ext=[AuthorCompanyExt(id=1327017424450335743, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424437752830, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
4University of Chinese Academy of Sciences, Beijing 100049), AuthorCompanyExt(id=1327017424458724352, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424437752830, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
4中国科学院大学 北京 100049)])]), Author(id=1327017424991399951, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327017425104646164, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, authorId=1327017424991399951, language=EN, stringName=Zhen Zhang, firstName=Zhen, middleName=null, lastName=Zhang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, 3, 4, address=
1Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024
2CAS Key Laboratory of System Software, Beijing 100190
3State Key Laboratory of Computer Science (Institute of Software, Chinese Academy of Sciences), Beijing 100190
4University of Chinese Academy of Sciences, Beijing 100049, bio={"content":"
born in 1995. PhD candidate. Student member of CCF. His main research interests include anomaly detection, deep learning, computer vision, and natural language processing
"}, bioImg=null, bioContent=
born in 1995. PhD candidate. Student member of CCF. His main research interests include anomaly detection, deep learning, computer vision, and natural language processing
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327017425184337941, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, authorId=1327017424991399951, language=CN, stringName=张震, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, 3, 4, address=
1中国科学院大学杭州高等研究院 杭州 310024
2中国科学院基础软件与系统重点实验室 北京 100190
3计算机科学国家重点实验室(中国科学院软件研究所) 北京 100190
4中国科学院大学 北京 100049, bio={"img":"wil4WX8HonpwsiD443JbjA==","content":"
1995年生. 博士研究生. CCF学生会员. 主要研究方向为异常检测、深度学习、计算机视觉、自然语言处理
"}, bioImg=wil4WX8HonpwsiD443JbjA==, bioContent=
1995年生. 博士研究生. CCF学生会员. 主要研究方向为异常检测、深度学习、计算机视觉、自然语言处理
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327017424098014197, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, xref=1, ext=[AuthorCompanyExt(id=1327017424110597110, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424098014197, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024), AuthorCompanyExt(id=1327017424123180023, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424098014197, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1中国科学院大学杭州高等研究院 杭州 310024)]), AuthorCompany(id=1327017424215454712, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, xref=2, ext=[AuthorCompanyExt(id=1327017424228037625, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424215454712, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2CAS Key Laboratory of System Software, Beijing 100190), AuthorCompanyExt(id=1327017424240620538, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424215454712, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2中国科学院基础软件与系统重点实验室 北京 100190)]), AuthorCompany(id=1327017424324506619, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, xref=3, ext=[AuthorCompanyExt(id=1327017424337089532, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424324506619, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3State Key Laboratory of Computer Science (Institute of Software, Chinese Academy of Sciences), Beijing 100190), AuthorCompanyExt(id=1327017424345478141, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424324506619, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3计算机科学国家重点实验室(中国科学院软件研究所) 北京 100190)]), AuthorCompany(id=1327017424437752830, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, xref=4, ext=[AuthorCompanyExt(id=1327017424450335743, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424437752830, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
4University of Chinese Academy of Sciences, Beijing 100049), AuthorCompanyExt(id=1327017424458724352, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424437752830, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
4中国科学院大学 北京 100049)])]), Author(id=1327017425276612631, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327017425394053146, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, authorId=1327017425276612631, language=EN, stringName=Zheheng Liang, firstName=Zheheng, middleName=null, lastName=Liang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
5, 6, address=
5Joint Laboratory on Cyberspace Security (China Southern Power Grid Co., Ltd.), Guangzhou 510620
6Guangdong Power Grid Co., Ltd., Guangzhou 510620, bio={"content":"
born in 1986. Master, senior engineer. Member of CCF. His main research interest includes digital evaluation technology
"}, bioImg=null, bioContent=
born in 1986. Master, senior engineer. Member of CCF. His main research interest includes digital evaluation technology
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327017427138883611, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, authorId=1327017425276612631, language=CN, stringName=梁哲恒, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
5, 6, address=
5网络空间安全联合实验室(中国南方电网有限公司)广州 510620
6广东电网有限责任公司 广州 510620, bio={"img":"WsX3F1pNLGojjS0RbjrdCw==","content":"
1986年生. 硕士,高级工程师. CCF会员. 主要研究方向为数字化评测技术
"}, bioImg=WsX3F1pNLGojjS0RbjrdCw==, bioContent=
1986年生. 硕士,高级工程师. CCF会员. 主要研究方向为数字化评测技术
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327017424550998016, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, xref=5, ext=[AuthorCompanyExt(id=1327017424559386625, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424550998016, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
5Joint Laboratory on Cyberspace Security (China Southern Power Grid Co., Ltd.), Guangzhou 510620), AuthorCompanyExt(id=1327017424563580930, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424550998016, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
5网络空间安全联合实验室(中国南方电网有限公司)广州 510620)]), AuthorCompany(id=1327017424660049923, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, xref=6, ext=[AuthorCompanyExt(id=1327017424668438532, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424660049923, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
6Guangdong Power Grid Co., Ltd., Guangzhou 510620), AuthorCompanyExt(id=1327017424681021445, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424660049923, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
6广东电网有限责任公司 广州 510620)])]), Author(id=1327017427231158301, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327017427323432992, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, authorId=1327017427231158301, language=EN, stringName=Chaosheng Yao, firstName=Chaosheng, middleName=null, lastName=Yao, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
5, 6, address=
5Joint Laboratory on Cyberspace Security (China Southern Power Grid Co., Ltd.), Guangzhou 510620
6Guangdong Power Grid Co., Ltd., Guangzhou 510620, bio={"content":"
born in 1989. Bachelor, engineer. Member of CCF. His main research interest includes project quality control
"}, bioImg=null, bioContent=
born in 1989. Bachelor, engineer. Member of CCF. His main research interest includes project quality control
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327017427398930465, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, authorId=1327017427231158301, language=CN, stringName=姚潮生, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
5, 6, address=
5网络空间安全联合实验室(中国南方电网有限公司)广州 510620
6广东电网有限责任公司 广州 510620, bio={"img":"UdkDsHjxVznZlcT5jOWF2g==","content":"
1989年生. 学士,工程师. CCF会员. 主要研究方向为项目质量管控
"}, bioImg=UdkDsHjxVznZlcT5jOWF2g==, bioContent=
1989年生. 学士,工程师. CCF会员. 主要研究方向为项目质量管控
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327017424550998016, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, xref=5, ext=[AuthorCompanyExt(id=1327017424559386625, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424550998016, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
5Joint Laboratory on Cyberspace Security (China Southern Power Grid Co., Ltd.), Guangzhou 510620), AuthorCompanyExt(id=1327017424563580930, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424550998016, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
5网络空间安全联合实验室(中国南方电网有限公司)广州 510620)]), AuthorCompany(id=1327017424660049923, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, xref=6, ext=[AuthorCompanyExt(id=1327017424668438532, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424660049923, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
6Guangdong Power Grid Co., Ltd., Guangzhou 510620), AuthorCompanyExt(id=1327017424681021445, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424660049923, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
6广东电网有限责任公司 广州 510620)])]), Author(id=1327017427457650723, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327017427549925414, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, authorId=1327017427457650723, language=EN, stringName=Jinbo Zhang, firstName=Jinbo, middleName=null, lastName=Zhang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
5, 6, address=
5Joint Laboratory on Cyberspace Security (China Southern Power Grid Co., Ltd.), Guangzhou 510620
6Guangdong Power Grid Co., Ltd., Guangzhou 510620, bio={"content":"
born in 1979. Master, senior engineer. His main research interest includes information system testing
"}, bioImg=null, bioContent=
born in 1979. Master, senior engineer. His main research interest includes information system testing
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327017427625422887, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, authorId=1327017427457650723, language=CN, stringName=张金波, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
5, 6, address=
5网络空间安全联合实验室(中国南方电网有限公司)广州 510620
6广东电网有限责任公司 广州 510620, bio={"img":"pkfLamfJKu/ioyvhYlzKiw==","content":"
1979年生. 硕士,高级工程师. 主要研究方向为信息系统测试
"}, bioImg=pkfLamfJKu/ioyvhYlzKiw==, bioContent=
1979年生. 硕士,高级工程师. 主要研究方向为信息系统测试
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327017424550998016, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, xref=5, ext=[AuthorCompanyExt(id=1327017424559386625, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424550998016, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
5Joint Laboratory on Cyberspace Security (China Southern Power Grid Co., Ltd.), Guangzhou 510620), AuthorCompanyExt(id=1327017424563580930, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424550998016, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
5网络空间安全联合实验室(中国南方电网有限公司)广州 510620)]), AuthorCompany(id=1327017424660049923, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, xref=6, ext=[AuthorCompanyExt(id=1327017424668438532, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424660049923, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
6Guangdong Power Grid Co., Ltd., Guangzhou 510620), AuthorCompanyExt(id=1327017424681021445, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424660049923, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
6广东电网有限责任公司 广州 510620)])]), Author(id=1327017427709308969, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yrj@ios.ac.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1327017427839332397, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, authorId=1327017427709308969, language=EN, stringName=Rongjie Yan, firstName=Rongjie, middleName=null, lastName=Yan, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, 3, 4, *, address=
2CAS Key Laboratory of System Software, Beijing 100190
3State Key Laboratory of Computer Science (Institute of Software, Chinese Academy of Sciences), Beijing 100190
4University of Chinese Academy of Sciences, Beijing 100049, bio={"content":"
born in 1977. PhD, associate professor. Senior member of CCF. Her main research interest includes testing and validation of intelligent software and autonomous unmanned systems
"}, bioImg=null, bioContent=
born in 1977. PhD, associate professor. Senior member of CCF. Her main research interest includes testing and validation of intelligent software and autonomous unmanned systems
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327017427923218478, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, authorId=1327017427709308969, language=CN, stringName=晏荣杰, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, 3, 4, *, address=
2中国科学院基础软件与系统重点实验室 北京 100190
3计算机科学国家重点实验室(中国科学院软件研究所) 北京 100190
4中国科学院大学 北京 100049, bio={"img":"JABXkbiDzQk31fbV4zVkrA==","content":"
1977年生. 博士,副研究员. CCF高级会员. 主要研究方向为智能软件、自主无人系统的测试与验证
"}, bioImg=JABXkbiDzQk31fbV4zVkrA==, bioContent=
1977年生. 博士,副研究员. CCF高级会员. 主要研究方向为智能软件、自主无人系统的测试与验证
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327017424215454712, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, xref=2, ext=[AuthorCompanyExt(id=1327017424228037625, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424215454712, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2CAS Key Laboratory of System Software, Beijing 100190), AuthorCompanyExt(id=1327017424240620538, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424215454712, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2中国科学院基础软件与系统重点实验室 北京 100190)]), AuthorCompany(id=1327017424324506619, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, xref=3, ext=[AuthorCompanyExt(id=1327017424337089532, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424324506619, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3State Key Laboratory of Computer Science (Institute of Software, Chinese Academy of Sciences), Beijing 100190), AuthorCompanyExt(id=1327017424345478141, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424324506619, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3计算机科学国家重点实验室(中国科学院软件研究所) 北京 100190)]), AuthorCompany(id=1327017424437752830, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, xref=4, ext=[AuthorCompanyExt(id=1327017424450335743, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424437752830, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
4University of Chinese Academy of Sciences, Beijing 100049), AuthorCompanyExt(id=1327017424458724352, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424437752830, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
4中国科学院大学 北京 100049)])]), Author(id=1327017427977744432, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, orderNo=6, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327017428099379252, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, authorId=1327017427977744432, language=EN, stringName=Peng Wu, firstName=Peng, middleName=null, lastName=Wu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, 3, 4, address=
2CAS Key Laboratory of System Software, Beijing 100190
3State Key Laboratory of Computer Science (Institute of Software, Chinese Academy of Sciences), Beijing 100190
4University of Chinese Academy of Sciences, Beijing 100049, bio={"content":"
born in 1977. PhD, associate professor. Senior member of CCF. His main research interests include formal method, concurrent testing, and machine learning
"}, bioImg=null, bioContent=
born in 1977. PhD, associate professor. Senior member of CCF. His main research interests include formal method, concurrent testing, and machine learning
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327017428170682421, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, authorId=1327017427977744432, language=CN, stringName=吴鹏, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, 3, 4, address=
2中国科学院基础软件与系统重点实验室 北京 100190
3计算机科学国家重点实验室(中国科学院软件研究所) 北京 100190
4中国科学院大学 北京 100049, bio={"img":"J8k7KtvEuF/FDJfQuHoG6Q==","content":"
1977年生. 博士,副研究员. CCF高级会员. 主要研究方向为形式化方法、并发测试、机器学习
"}, bioImg=J8k7KtvEuF/FDJfQuHoG6Q==, bioContent=
1977年生. 博士,副研究员. CCF高级会员. 主要研究方向为形式化方法、并发测试、机器学习
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327017424215454712, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, xref=2, ext=[AuthorCompanyExt(id=1327017424228037625, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424215454712, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2CAS Key Laboratory of System Software, Beijing 100190), AuthorCompanyExt(id=1327017424240620538, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424215454712, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2中国科学院基础软件与系统重点实验室 北京 100190)]), AuthorCompany(id=1327017424324506619, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, xref=3, ext=[AuthorCompanyExt(id=1327017424337089532, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424324506619, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3State Key Laboratory of Computer Science (Institute of Software, Chinese Academy of Sciences), Beijing 100190), AuthorCompanyExt(id=1327017424345478141, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424324506619, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3计算机科学国家重点实验室(中国科学院软件研究所) 北京 100190)]), AuthorCompany(id=1327017424437752830, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, xref=4, ext=[AuthorCompanyExt(id=1327017424450335743, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424437752830, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
4University of Chinese Academy of Sciences, Beijing 100049), AuthorCompanyExt(id=1327017424458724352, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424437752830, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
4中国科学院大学 北京 100049)])])], keywords=[Keyword(id=1327017428271345718, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, orderNo=1, keyword=object detection), Keyword(id=1327017428363620407, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, orderNo=2, keyword=deep learning), Keyword(id=1327017428443312184, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, orderNo=3, keyword=model architecture), Keyword(id=1327017428510421049, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, orderNo=4, keyword=artificial intelligence), Keyword(id=1327017428581724218, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, orderNo=5, keyword=computer vision), Keyword(id=1327017428640444475, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, orderNo=1, keyword=目标检测), Keyword(id=1327017428703359036, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, orderNo=2, keyword=深度学习), Keyword(id=1327017428774662205, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, orderNo=3, keyword=模型架构), Keyword(id=1327017428841771070, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, orderNo=4, keyword=人工智能), Keyword(id=1327017428908879935, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, orderNo=5, keyword=计算机视觉)], refs=[Reference(id=1327017437364596852, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=Deng Jia, Dong Wei, Socher R, et al. ImageNet: A large-scale hierarchical image database[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2009: 248−255, articleTitle=null, refAbstract=null), Reference(id=1327017437431705717, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin T Y, Maire M, Belongie S, et al. Microsoft COCO: Common objects in context[C]//Proc of the 13th European Conf on Computer Vision. Berlin: Springer, 2014: 740−755, articleTitle=null, refAbstract=null), Reference(id=1327017437528174710, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=Viola P, Jones M. Rapid object detection using a boosted cascade of simple features[C]//Proc of the IEEE Computer Society Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2001: 511−518, articleTitle=null, refAbstract=null), Reference(id=1327017437620449399, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=Viola P, Jones M J. Robust real-time object detection[J]. International Journal of Computer Vision, 2001, 57(2): 137−154, articleTitle=null, refAbstract=null), Reference(id=1327017437704335480, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=Freund Y, Schapire R E. A desicion-theoretic generalization of on-line learning and an application to boosting[C]//Proc of the 2nd European Conf on Computational Learning Theory. Berlin: Springer, 1995: 23−37, articleTitle=null, refAbstract=null), Reference(id=1327017437813387385, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=Dalal N, Triggs B. Histograms of oriented gradients for human detection[C]//Proc of the IEEE Computer Society Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2005: 886−893, articleTitle=null, refAbstract=null), Reference(id=1327017437888884858, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=Cortes C, Vapnik V. Support-vector networks[J]. Machine Learning, 1995, 20: 273−297, articleTitle=null, refAbstract=null), Reference(id=1327017438010519675, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Felzenszwalb P, McAllester D, Ramanan D. A discriminatively trained, multiscale, deformable part model[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2008: 1−8, articleTitle=null, refAbstract=null), Reference(id=1327017438161514620, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=LeCun Y, Boser B, Denker J S, et al. Backpropagation applied to handwritten zip code recognition[J]. Neural Computation, 1989, 1(4): 541−551, articleTitle=null, refAbstract=null), Reference(id=1327017438249595005, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=LeCun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278−2324, articleTitle=null, refAbstract=null), Reference(id=1327017438354452606, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[C]//Proc of the 26th Advances in Neural Information Processing Systems. Cambridge, MA: MIT, 2012: 1106- 1114, articleTitle=null, refAbstract=null), Reference(id=1327017438429950079, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint, arXiv: 1409.1556, 20134, articleTitle=null, refAbstract=null), Reference(id=1327017438522224768, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Deep residual learning for image recognition[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2016: 770−778, articleTitle=null, refAbstract=null), Reference(id=1327017438606110849, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2014: 580−587, articleTitle=null, refAbstract=null), Reference(id=1327017438681608322, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904−1916, articleTitle=null, refAbstract=null), Reference(id=1327017438778077315, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Girshick R. Fast R-CNN[C]//Proc of the IEEE Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2015: 1440−1448, articleTitle=null, refAbstract=null), Reference(id=1327017440493547652, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Neubeck A, Van G L. Efficient non-maximum suppression[C]//Proc of the 18th Int Conf on Pattern Recognition. Piscataway, NJ: IEEE, 2006: 850−855, articleTitle=null, refAbstract=null), Reference(id=1327017440594210949, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Ren Shaoqing, He Kaiming, Girshick R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[C]//Proc of the 29th Advances in Neural Information Processing Systems. Cambridge, MA: MIT, 2015: 91−99, articleTitle=null, refAbstract=null), Reference(id=1327017440661319814, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Redmon J, Divvala S, Girshick R, et al. You only look once: Unified, real-time object detection[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2016: 779−788, articleTitle=null, refAbstract=null), Reference(id=1327017440736817287, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Redmon J, Farhadi A. YOLO9000: Better, faster, stronger[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 7263−7271, articleTitle=null, refAbstract=null), Reference(id=1327017440808120456, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Loffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift[C]//Proc of the 32nd Int Conf on Machine Learning. New York: ACM, 2015: 448−456, articleTitle=null, refAbstract=null), Reference(id=1327017440883617929, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Redmon J, Farhadi A. YOLOv3: An incremental improvement[J]. arXiv preprint, arXiv: 1804.02767, 2018, articleTitle=null, refAbstract=null), Reference(id=1327017440946532490, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=Bochkovskiy A, Wang C Y, Liao H Y M. YOLOv4: Optimal speed and accuracy of object detection[J]. arXiv preprint, arXiv: 2004.10934, 2020, articleTitle=null, refAbstract=null), Reference(id=1327017441009447051, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Misra D. Mish: A self regularized non-monotonic activation function[J]. arXiv preprint, arXiv: 1908.08681, 2019, articleTitle=null, refAbstract=null), Reference(id=1327017441101721740, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Wei, Anguelov D, Erhan D, et al. SSD: Single shot multibox detector[C]//Proc of the 14th European Conf on Computer Vision. Berlin: Springer, 2016: 21−37, articleTitle=null, refAbstract=null), Reference(id=1327017441168830605, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin T Y, Dollár P, Girshick R, et al. Feature pyramid networks for object detection[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 2117−2125, articleTitle=null, refAbstract=null), Reference(id=1327017441252716686, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation[C]//Proc of the 18th Medical Image Computing and Computer-Assisted Intervention. Berlin: Springer, 2015: 234−241, articleTitle=null, refAbstract=null), Reference(id=1327017441328214159, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin T Y, Goyal P, Girshick R, et al. Focal loss for dense object detection[C]//Proc of the IEEE Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2017: 2980−2988, articleTitle=null, refAbstract=null), Reference(id=1327017441433071760, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Cai Zhaowei, Vasconcelos N. Cascade R-CNN: Delving into high quality object detection[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 6154−6162, articleTitle=null, refAbstract=null), Reference(id=1327017441500180625, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Law H, Deng J. CornerNet: Detecting objects as paired keypoints[C]//Proc of the European Conf on Computer Vision. Berlin: Springer, 2018: 734−750, articleTitle=null, refAbstract=null), Reference(id=1327017441584066706, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=Newell A, Yang K, Deng J. Stacked hourglass networks for human pose estimation[C]//Proc of the 14th European Conf on Computer Vision. Berlin: Springer, 2016: 483−499, articleTitle=null, refAbstract=null), Reference(id=1327017441663758483, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Xingyi, Wang Dequan, Krähenbühl P. Objects as points[J]. arXiv preprint, arXiv: 1904.07850, 2019, articleTitle=null, refAbstract=null), Reference(id=1327017441739255956, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Duan Kaiwen, Bai Song, Xie Lingxi, et al. CenterNet: Keypoint triplets for object detection[C]//Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2019: 6569−6578, articleTitle=null, refAbstract=null), Reference(id=1327017441806364821, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2015: 3431−3440, articleTitle=null, refAbstract=null), Reference(id=1327017441890250902, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=Tian Zhi, Shen Chunhua, Chen Hao, et al. FCOS: Fully convolutional one-stage object detection[C]//Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2019: 9627−9636, articleTitle=null, refAbstract=null), Reference(id=1327017441953165463, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=Sun Peize, Zhang Rufen, Jiang Yi, et al. Sparse R-CNN: End-to-end object detection with learnable proposals[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 14454−14463, articleTitle=null, refAbstract=null), Reference(id=1327017442041245848, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=Carion N, Massa F, Synnaeve G, et al. End-to-end object detection with transformers[C]//Proc of the 16th European Conf on Computer Vision. Berlin: Springer, 2020: 213−229, articleTitle=null, refAbstract=null), Reference(id=1327017442125131929, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=38, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Qiang, Wang Yingming, Yang Tong, et al. You only look one-level feature[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 13039−13048, articleTitle=null, refAbstract=null), Reference(id=1327017442188046490, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=39, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=Xie Saining, Girshick R, Dollár P, et al. Aggregated residual transformations for deep neural networks[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 1492−1500, articleTitle=null, refAbstract=null), Reference(id=1327017442255155355, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=40, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=Ge Zheng, Liu Songtao, Wang Feng, et al. YOLOx: Exceeding YOLO series in 2021[J]. arXiv preprint, arXiv: 2107.08430, 2021, articleTitle=null, refAbstract=null), Reference(id=1327017442313875612, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Chien-Yao, Liao H Y M, Wu Y H, et al. CSPNet: A new backbone that can enhance learning capability of CNN[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition Workshops. Piscataway, NJ: IEEE, 2020: 390−391, articleTitle=null, refAbstract=null), Reference(id=1327017442389373085, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=42, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang C Y, Bochkovskiy A, Liao H Y M. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023: 7464−7475, articleTitle=null, refAbstract=null), Reference(id=1327017442452287646, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=43, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=Ding Xiaohan, Zhang Xiangyu, Ma Ningning, et al. RepVGG: Making VGG-style convnets great again[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 13733−13742, articleTitle=null, refAbstract=null), Reference(id=1327017442515202207, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=44, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16×16 words: Transformers for image recognition at scale[C/OL]//Proc of the 8th Int Conf on Learning Representations. Washington: ICLR, 2020[2023-11-01]. https://openreview.net/pdf?id=YicbFdNTTy, articleTitle=null, refAbstract=null), Reference(id=1327017442594893985, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=45, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Zhuang, Mao Hanzi, Wu Chaoyuan, et al. A convnet for the 2020s[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 11976−11986, articleTitle=null, refAbstract=null), Reference(id=1327017442703945890, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=46, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=Ding Xiaohan, Zhang Xiangyu, Han Jungong, et al. Scaling up your kernels to 31×31: Revisiting large kernel design in CNNs[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 11963−11975, articleTitle=null, refAbstract=null), Reference(id=1327017442771054755, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=47, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Shiwei, Chen Tianlong, Chen Xiaohan, et al. More convNets in the 2020s: Scaling up kernels beyond 51×51 using sparsity[C/OL]//Proc of the 11th Int Conf on Learning Representations. Washington: ICLR, 2023[2023-11-02]. https://openreview.net/pdf?id=bXNl-myZkJl, articleTitle=null, refAbstract=null), Reference(id=1327017442842357924, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=48, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=Ding Xiaohan, Zhang Yiyuan, Ge Yixiao, et al. UniRepLKNet: A universal perception large-kernel ConvNet for audio, video, point cloud, time-series and image recognition[J]. arXiv preprint, arXiv: 2311.15599, 2023, articleTitle=null, refAbstract=null), Reference(id=1327017442905272485, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=49, rfOrder=48, authorNames=null, journalName=null, refType=null, unstructuredReference=Howard A G, Zhu Menglong, Chen Bo, et al. MobileNets: Efficient convolutional neural networks for mobile vision applications[J]. arXiv preprint, arXiv: 1704.04861, 2017, articleTitle=null, refAbstract=null), Reference(id=1327017442963992742, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=50, rfOrder=49, authorNames=null, journalName=null, refType=null, unstructuredReference=Sandler M, Howard A, Zhu Menglong, et al. MobileNetv2: Inverted residuals and linear bottlenecks[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 4510−4520, articleTitle=null, refAbstract=null), Reference(id=1327017443039490215, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=51, rfOrder=50, authorNames=null, journalName=null, refType=null, unstructuredReference=Howard A, Sandler M, Chu G, et al. Searching for mobileNetv3[C]//Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2019: 1314−1324, articleTitle=null, refAbstract=null), Reference(id=1327017443110793384, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=52, rfOrder=51, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Daquan, Hou Qibin, Chen Yunpeng, et al. Rethinking bottleneck structure for efficient mobile network design[C]//Proc of the 16th European Conf on Computer Vision. Berlin: Springer, 2020: 680−697, articleTitle=null, refAbstract=null), Reference(id=1327017443177902249, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=53, rfOrder=52, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Xiangyu, Zhou Xinyu, Lin Mengxiao, et al. ShuffleNet: An extremely efficient convolutional neural network for mobile devices[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 6848−6856, articleTitle=null, refAbstract=null), Reference(id=1327017443261788330, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=54, rfOrder=53, authorNames=null, journalName=null, refType=null, unstructuredReference=Ma Ningning, Zhang Xiangyu, Zheng Haitao, et al. ShuffleNet v2: Practical guidelines for efficient cnn architecture design[C]//Proc of the 15th European Conf on Computer Vision. Berlin: Springer, 2018: 116−131, articleTitle=null, refAbstract=null), Reference(id=1327017443324702891, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=55, rfOrder=54, authorNames=null, journalName=null, refType=null, unstructuredReference=Tan Mingxing, Le Q. EfficientNet: Rethinking model scaling for convolutional neural networks[C]//Proc of the 36th Int Conf on Machine Learning. New York: ACM, 2019: 6105−6114, articleTitle=null, refAbstract=null), Reference(id=1327017444981452972, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=56, rfOrder=55, authorNames=null, journalName=null, refType=null, unstructuredReference=Tan Mingxing, Le Q. EfficientNetv2: Smaller models and faster training[C]//Proc of the 38th Int Conf on Machine Learning. New York: ACM, 2021: 10096−10106, articleTitle=null, refAbstract=null), Reference(id=1327017445048561837, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=57, rfOrder=56, authorNames=null, journalName=null, refType=null, unstructuredReference=Tan Mingxing, Pang Ruoming, Le Q V. EfficientDet: Scalable and efficient object detection[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2020: 10781−10790, articleTitle=null, refAbstract=null), Reference(id=1327017445111476398, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=58, rfOrder=57, authorNames=null, journalName=null, refType=null, unstructuredReference=Han Kai, Wang Yunhe, Tian Qi, et al. GhostNet: More features from cheap operations[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2020: 1580−1589, articleTitle=null, refAbstract=null), Reference(id=1327017445170196655, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=59, rfOrder=58, authorNames=null, journalName=null, refType=null, unstructuredReference=Tang Yehui, Han Kai, Guo Jianyuan, et al. GhostNetv2: Enhance cheap operation with long-range attention[C]//Proc of the 36th Advances in Neural Information Processing Systems. Cambridge, MA: MIT, 2022: 9969−9982, articleTitle=null, refAbstract=null), Reference(id=1327017445241499824, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=60, rfOrder=59, authorNames=null, journalName=null, refType=null, unstructuredReference=Vasu P K A, Gabriel J, Zhu J, et al. MobileOne: An improved one millisecond mobile backbone[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023: 7907−7917, articleTitle=null, refAbstract=null), Reference(id=1327017445300220081, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=61, rfOrder=60, authorNames=null, journalName=null, refType=null, unstructuredReference=Mnih V, Heess N, Graves A, et al. Recurrent models of visual attention[C]//Proc of the 28th Advances in Neural Information Processing Systems. Cambridge, MA: MIT, 2014: 2204−2212, articleTitle=null, refAbstract=null), Reference(id=1327017445363134642, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=62, rfOrder=61, authorNames=null, journalName=null, refType=null, unstructuredReference=Jaderberg M, Simonyan K, Zisserman A, et al. Spatial transformer networks[C]//Proc of the 29th Advances in Neural Information Processing Systems. Cambridge, MA: MIT, 2015: 2017−2025, articleTitle=null, refAbstract=null), Reference(id=1327017445426049203, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=63, rfOrder=62, authorNames=null, journalName=null, refType=null, unstructuredReference=Dai Jifeng, Qi Haozhi, Xiong Yuwen, et al. Deformable convolutional networks[C]//Proc of the 16th IEEE Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2017: 764−773, articleTitle=null, refAbstract=null), Reference(id=1327017445488963764, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=64, rfOrder=63, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhu Xizhou, Hu Han, Lin S, et al. Deformable ConvNets v2: More deformable, better results[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 9308−9316, articleTitle=null, refAbstract=null), Reference(id=1327017445556072629, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=65, rfOrder=64, authorNames=null, journalName=null, refType=null, unstructuredReference=Hu Jie, Shen Li, Sun Gang. Squeeze-and-excitation networks[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 7132−7141, articleTitle=null, refAbstract=null), Reference(id=1327017445627375798, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=66, rfOrder=65, authorNames=null, journalName=null, refType=null, unstructuredReference=Woo S, Park J, Lee J Y, et al. Cbam: Convolutional block attention module[C]//Proc of the 15th European Conf on Computer Vision. Berlin: Springer, 2018: 3−19, articleTitle=null, refAbstract=null), Reference(id=1327017445707067575, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=67, rfOrder=66, authorNames=null, journalName=null, refType=null, unstructuredReference=Gao Zilin, Xie Jiangtao, Wang Qilong, et al. Global second-order pooling convolutional networks[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 3024−3033, articleTitle=null, refAbstract=null), Reference(id=1327017445774176440, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=68, rfOrder=67, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Qilong, Wu Banggu, Zhu Pengfei, et al. ECA-Net: Efficient channel attention for deep convolutional neural networks[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2020: 11534−11542, articleTitle=null, refAbstract=null), Reference(id=1327017445845479609, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=69, rfOrder=68, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Xiaolong, Girshick R, Gupta A, et al. Non-local neural networks[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 7794−7803, articleTitle=null, refAbstract=null), Reference(id=1327017445912588474, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=70, rfOrder=69, authorNames=null, journalName=null, refType=null, unstructuredReference=Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Proc of the 31st Advances in Neural Information Processing Systems. Cambridge, MA: MIT, 2017: 5998−6008, articleTitle=null, refAbstract=null), Reference(id=1327017445971308731, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=71, rfOrder=70, authorNames=null, journalName=null, refType=null, unstructuredReference=Devlin J, Chang Mingwei, Lee K, et al. BERT: Pre-training of deep bidirectional transformers for language understanding[C]//Proc of the Conf of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, PA: ACL, 2019: 4171−4186, articleTitle=null, refAbstract=null), Reference(id=1327017446038417596, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=72, rfOrder=71, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhu Xizhou, Su Weijie, Lu Lewei, et al. Deformable DETR: Deformable transformers for end-to-end object detection[C/OL]//Proc of the 9th Int Conf on Learning Representations. Washington: ICLR, 2021[2023-11-01]. https://openreview.net/pdf?id=gZ9hCDWe6ke, articleTitle=null, refAbstract=null), Reference(id=1327017446105526461, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=73, rfOrder=72, authorNames=null, journalName=null, refType=null, unstructuredReference=Yao Zhuyu, Ai Jiangbo, Li Boxun, et al. Efficient DETR: Improving end-to-end object detector with dense prior[J]. arXiv preprint, arXiv: 2104.01318, 2021, articleTitle=null, refAbstract=null), Reference(id=1327017446172635326, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=74, rfOrder=73, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Tao, Yuan Li, Chen Yunpeng, et al. Pnp-DETR: Towards efficient visual analysis with transformers[C]//Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2021: 4661−4670, articleTitle=null, refAbstract=null), Reference(id=1327017446248132799, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=75, rfOrder=74, authorNames=null, journalName=null, refType=null, unstructuredReference=Roh B, Shin J W, Shin W, et al. Sparse DETR: Efficient end-to-end object detection with learnable sparsity[C/OL]//Proc of the 9th Int Conf on Learning Representations. Washington: ICLR, 2021[2023-10-04]. https://openreview.net/pdf?id=RRGVCN8kjim, articleTitle=null, refAbstract=null), Reference(id=1327017446332018880, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=76, rfOrder=75, authorNames=null, journalName=null, refType=null, unstructuredReference=Caron M, Bojanowski P, Joulin A, et al. Deep clustering for unsupervised learning of visual features[C]//Proc of the 15th European Conf on Computer Vision. Berlin: Springer, 2018: 132−149, articleTitle=null, refAbstract=null), Reference(id=1327017446394933441, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=77, rfOrder=76, authorNames=null, journalName=null, refType=null, unstructuredReference=Asano Y M, Rupprecht C, Vedaldi A. Self-labelling via simultaneous clustering and representation learning[J]. arXiv preprint, arXiv: 1911.05371, 2019, articleTitle=null, refAbstract=null), Reference(id=1327017446466236610, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=78, rfOrder=77, authorNames=null, journalName=null, refType=null, unstructuredReference=Cao Yue, Xie Zhenda, Liu Bin, et al. Parametric instance classification for unsupervised visual feature learning[C]//Proc of the 34th Advances in Neural Information Processing Systems. Cambridge, MA: MIT, 2020: 15614−15624, articleTitle=null, refAbstract=null), Reference(id=1327017446533345475, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=79, rfOrder=78, authorNames=null, journalName=null, refType=null, unstructuredReference=Dai Zhigang, Cai Bolun, Lin Yugeng, et al. UP-DETR: Unsupervised pre-training for object detection with transformers[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 1601−1610, articleTitle=null, refAbstract=null), Reference(id=1327017446613037252, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=80, rfOrder=79, authorNames=null, journalName=null, refType=null, unstructuredReference=Radford A, Narasimhan K, Salimans T, et al. Improving language understanding by generative pre-training[R/OL]. OpenAI, 2018[2024-02-01]. https://openai.com/research/language-unsupervised, articleTitle=null, refAbstract=null), Reference(id=1327017446680146117, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=81, rfOrder=80, authorNames=null, journalName=null, refType=null, unstructuredReference=Radford A, Wu J, Child R, et al. Language models are unsupervised multitask learners[R/OL]. OpenAI blog, 2019[2024-01-01]. https://insightcivic.s3.us-east-1.amazonaws.com/language-models.pdf, articleTitle=null, refAbstract=null), Reference(id=1327017446738866374, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=82, rfOrder=81, authorNames=null, journalName=null, refType=null, unstructuredReference=He Kaiming, Fan Haoqi, Wu Yuxin, et al. Momentum contrast for unsupervised visual representation learning[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2020: 9729−9738, articleTitle=null, refAbstract=null), Reference(id=1327017446801780935, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=83, rfOrder=82, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Ting, Kornblith S, Norouzi M, et al. A simple framework for contrastive learning of visual representations[C]//Proc of the 37th Int Conf on Machine Learning. New York: ACM, 2020: 1597−1607, articleTitle=null, refAbstract=null), Reference(id=1327017446852112584, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=84, rfOrder=83, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Xinlei, Fan Haoqi, Girshick R, et al. Improved baselines with momentum contrastive learning[J]. arXiv preprint, arXiv: 2003.04297, 2020, articleTitle=null, refAbstract=null), Reference(id=1327017446915027145, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=85, rfOrder=84, authorNames=null, journalName=null, refType=null, unstructuredReference=Caron M, Misra I, Mairal J, et al. Unsupervised learning of visual features by contrasting cluster assignments[C]//Proc of the 34th Advances in Neural Information Processing Systems. Cambridge, MA: MIT, 2020: 9912−9924, articleTitle=null, refAbstract=null), Reference(id=1327017446986330314, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=86, rfOrder=85, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Wenhai, Xie Enze, Li Xiang, et al. Pyramid vision transformer: A versatile backbone for dense prediction without convolutions[C]//Proc of the 18th IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2021: 568−578, articleTitle=null, refAbstract=null), Reference(id=1327017447057633483, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=87, rfOrder=86, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Ze, Lin Yutong, Cao Yue, et al. Swin Transformer: Hierarchical vision Transformer using shifted windows[C]//Proc of the 18th IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2021: 10012−10022, articleTitle=null, refAbstract=null), Reference(id=1327017447120548044, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=88, rfOrder=87, authorNames=null, journalName=null, refType=null, unstructuredReference=Fang Yuxin, Liao Bencheng, Wang Xinggang, et al. You only look at one sequence: Rethinking transformer in vision through object detection[J]. Proc of the 35th Advances in Neural Information Processing Systems. Cambrige, MA: MIT, 2021: 26183−26197, articleTitle=null, refAbstract=null), Reference(id=1327017447208628429, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=89, rfOrder=88, authorNames=null, journalName=null, refType=null, unstructuredReference=Li L H, Zhang Pengchuan, Zhang Haotian, et al. Grounded language-image pre-training[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 10965−10975, articleTitle=null, refAbstract=null), Reference(id=1327017447267348686, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=90, rfOrder=89, authorNames=null, journalName=null, refType=null, unstructuredReference=Radford A, Kim J W, Hallacy C, et al. Learning transferable visual models from natural language supervision[C]//Proc of the 38th Int Conf on Machine Learning. New York: ACM, 2021: 8748−8763, articleTitle=null, refAbstract=null), Reference(id=1327017447334457551, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=91, rfOrder=90, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Shilong, Li Feng, Zhang Hao, et al. DAB-DETR: Dynamic anchor boxes are better queries for DETR[C/OL]//Proc of the 9th Int Conf on Learning Representations. Washington: ICLR, 2021[2023-10-02]. https://openreview.net/pdf?id=oMI9PjOb9Jl, articleTitle=null, refAbstract=null), Reference(id=1327017447401566416, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=92, rfOrder=91, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Feng, Zhang Hao, Liu Shilong, et al. Dn-DETR: Accelerate DETR training by introducing query denoising[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 13619−13627, articleTitle=null, refAbstract=null), Reference(id=1327017447468675281, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=93, rfOrder=92, authorNames=null, journalName=null, refType=null, unstructuredReference=Zong Zhuofan, Song Guanglu, Liu Yu. DETRs with collaborative hybrid assignments training[C]//Proc of the 19th IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2023: 6748−6758, articleTitle=null, refAbstract=null), Reference(id=1327017447535784146, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=94, rfOrder=93, authorNames=null, journalName=null, refType=null, unstructuredReference=Hatamizadeh A, Yin H, Heinrich G, et al. Global context vision transformers[C]//Proc of the 40th Int Conf on Machine Learning. New York: ACM, 2023: 12633−12646, articleTitle=null, refAbstract=null), Reference(id=1327017447623864531, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=95, rfOrder=94, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Gongjie, Luo Zhipeng, Tian Zichen, et al. Towards efficient use of multi-scale features in transformer-based object detectors[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023: 6206−6216, articleTitle=null, refAbstract=null), Reference(id=1327017447699362004, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=96, rfOrder=95, authorNames=null, journalName=null, refType=null, unstructuredReference=Han Kai, Wang Yunhe, Chen Hanting, et al. A survey on vision Transformer[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 45(1): 87−110, articleTitle=null, refAbstract=null), Reference(id=1327017447766470869, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=97, rfOrder=96, authorNames=null, journalName=null, refType=null, unstructuredReference=Khan S, Naseer M, Hayat M, et al. Transformers in vision: A survey[J]. ACM Computing Surveys, 2022, 54(10s): 1−41, articleTitle=null, refAbstract=null), Reference(id=1327017447841968342, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=98, rfOrder=97, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Yang, Zhang Yao, Wang Yixin, et al. A survey of visual transformers[J]. IEEE Transactions on Neural Networks and Learning Systems, 2023, 36(6): 7478−7498, articleTitle=null, refAbstract=null), Reference(id=1327017449494524119, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=99, rfOrder=98, authorNames=null, journalName=null, refType=null, unstructuredReference=Shehzadi T, Hashmi K A, Stricker D, et al. 2D object detection with transformers: A review[J]. arXiv preprint, arXiv: 2306.04670, 2023, articleTitle=null, refAbstract=null), Reference(id=1327017449565827288, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=100, rfOrder=99, authorNames=null, journalName=null, refType=null, unstructuredReference=Zuo Shuangquan, Xiao Yun, Chang Xiaojun, et al. Vision transformers for dense prediction: A survey[J]. Knowledge-Based Systems, 2022, 253: 109552, articleTitle=null, refAbstract=null), Reference(id=1327017449628741849, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=101, rfOrder=100, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Peng, Zhu Xiatian, Clifton D A. Multimodal learning with transformers: A survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(10): 12113−12132, articleTitle=null, refAbstract=null), Reference(id=1327017449716822234, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=102, rfOrder=101, authorNames=null, journalName=null, refType=null, unstructuredReference=Lahoud J, Cao Jiale, Khan F S, et al. 3D vision with transformers: A survey[J]. arXiv preprint, arXiv: 2208.04309, 2022, articleTitle=null, refAbstract=null), Reference(id=1327017449779736795, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=103, rfOrder=102, authorNames=null, journalName=null, refType=null, unstructuredReference=Ali A M, Benjdira B, Koubaa A, et al. Vision transformers in image restoration: A survey[J]. Sensors, 2023, 23(5): 2385, articleTitle=null, refAbstract=null), Reference(id=1327017449851039964, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=104, rfOrder=103, authorNames=null, journalName=null, refType=null, unstructuredReference=Thisanke H, Deshan C, Chamith K, et al. Semantic segmentation using vision transformers: A survey[J]. Engineering Applications of Artificial Intelligence, 2023, 126: 106669, articleTitle=null, refAbstract=null), Reference(id=1327017449905565917, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=105, rfOrder=104, authorNames=null, journalName=null, refType=null, unstructuredReference=Aleissaee A A, Kumar A, Anwer R M, et al. Transformers in remote sensing: A survey[J]. Remote Sensing, 2023, 15(7): 1860, articleTitle=null, refAbstract=null), Reference(id=1327017449968480478, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=106, rfOrder=105, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Hongming, Xu Qi, Cong Fengyu, et al. Vision transformers for computational histopathology[J]. IEEE Reviews in Biomedical Engineering, 2023, 17: 63−79, articleTitle=null, refAbstract=null), Reference(id=1327017450031395039, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=107, rfOrder=106, authorNames=null, journalName=null, refType=null, unstructuredReference=Shamshad F, Khan S, Zamir S W, et al. Transformers in medical imaging: A survey[J]. Medical Image Analysis, 2023, 88: 102802, articleTitle=null, refAbstract=null), Reference(id=1327017450115281120, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=108, rfOrder=107, authorNames=null, journalName=null, refType=null, unstructuredReference=Tolstikhin I, Houlsby N, Kolesnikov A, et al. MLP-Mixer: An all-MLP architecture for vision[C]//Proc of the 35th Advances in Neural Information Processing Systems. Cambridge, MA: MIT, 2021: 24261−24272, articleTitle=null, refAbstract=null), Reference(id=1327017450194972897, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=109, rfOrder=108, authorNames=null, journalName=null, refType=null, unstructuredReference=Touvron H, Bojanowski P, Caron M, et al. ResMLP: Feedforward networks for image classification with data-efficient training[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 45(4): 5314−5321, articleTitle=null, refAbstract=null), Reference(id=1327017450266276066, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=110, rfOrder=109, authorNames=null, journalName=null, refType=null, unstructuredReference=Ding Xiaohan, Xia Chunlong, Zhang Xiangyu, et al. RepMLP: Re-parameterizing convolutions into fully-connected layers for image recognition[J]. arXiv preprint, arXiv: 2105.01883, 2021: 24261−24272, articleTitle=null, refAbstract=null), Reference(id=1327017450333384931, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=111, rfOrder=110, authorNames=null, journalName=null, refType=null, unstructuredReference=Hou Qibin, Jiang Zihang, Yuan Li, et al. Vision Permutator: A permutable MLP-like architecture for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(1): 1328−1334, articleTitle=null, refAbstract=null), Reference(id=1327017450408882404, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=112, rfOrder=111, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Hanxiao, Dai Zihang, So D, et al. Pay attention to MLPs[C]//Proc of the 35th Advances in Neural Information Processing Systems. Cambridge, MA: MIT, 2021: 9204−9215, articleTitle=null, refAbstract=null), Reference(id=1327017450492768485, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=113, rfOrder=112, authorNames=null, journalName=null, refType=null, unstructuredReference=Yu Tan, Li Xu, Cai Yunfeng, et al. S2-MLP: Spatial-shift MLP architecture for vision[C]//Proc of the IEEE/CVF Winter Conf on Applications of Computer Vision. Piscataway, NJ: IEEE, 2022: 297−306, articleTitle=null, refAbstract=null), Reference(id=1327017450564071654, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=114, rfOrder=113, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Ziyu, Jiang Wenhao, Zhu Yiming, et al. DynaMixer: A vision MLP architecture with dynamic mixing[C]//Proc of the 39th Int Conf on Machine Learning. New York: ACM, 2022: 22691−22701, articleTitle=null, refAbstract=null), Reference(id=1327017450647957735, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=115, rfOrder=114, authorNames=null, journalName=null, refType=null, unstructuredReference=Lian Dongze, Yu Zehao, Sun Xing, et al. As-MLP: An axial shifted MLP architecture for vision[C/OL]//Proc of the 9th Int Conf on Learning Representations. Washington: ICLR, 2021[2023-10-02]. https://openreview.net/pdf?id=fvLLcIYmXb, articleTitle=null, refAbstract=null), Reference(id=1327017450736038120, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=116, rfOrder=115, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Shoufa , Xie Enze, Ge Chongjian, et al. CycleMLP: A MLP-like architecture for dense prediction[C/OL]//Proc of the 9th Int Conf on Learning Representations. Washington: ICLR, 2021[2023-10-02]. https://openreview.net/pdf?id=NMEceG4v69Y, articleTitle=null, refAbstract=null), Reference(id=1327017450807341289, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=117, rfOrder=116, authorNames=null, journalName=null, refType=null, unstructuredReference=Guo Jianyuan, Tang Yehui, Han Kai, et al. Hire-MLP: Vision MLP via hierarchical rearrangement[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 826−836, articleTitle=null, refAbstract=null), Reference(id=1327017450899615978, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=117, rfOrder=117, authorNames=null, journalName=null, refType=null, unstructuredReference=Guo Jianyuan, Tang Yehui, Han Kai, et al. Hire-MLP: Vision MLP via hierarchical rearrangement[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 826−836, articleTitle=null, refAbstract=null), Reference(id=1327017450979307755, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=118, rfOrder=118, authorNames=null, journalName=null, refType=null, unstructuredReference=Tang Yehui, Han Kai, Guo Jianyuan, et al. An image patch is a wave: Phase-aware vision MLP[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 10935−10944, articleTitle=null, refAbstract=null), Reference(id=1327017451054805228, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=118, rfOrder=119, authorNames=null, journalName=null, refType=null, unstructuredReference=Tang Yehui, Han Kai, Guo Jianyuan, et al. An image patch is a wave: Phase-aware vision MLP[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 10935−10944, articleTitle=null, refAbstract=null), Reference(id=1327017451117719789, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=119, rfOrder=120, authorNames=null, journalName=null, refType=null, unstructuredReference=Lai Shenqi, Du Xi, Guo Jia, et al. RaMLP: Vision MLP via region-aware mixing[C]//Proc of the 32nd Int Joint Conf on Artificial Intelligence. San Francisco, CA: Morgan Kaufmann, 2023: 999−1007, articleTitle=null, refAbstract=null), Reference(id=1327017451201605870, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=120, rfOrder=121, authorNames=null, journalName=null, refType=null, unstructuredReference=Sohl-Dickstein J, Weiss E, aheswaranathan N, et al. Deep unsupervised learning using nonequilibrium thermodynamics[C]//Proc of the 32nd Int Conf on Machine Learning. New York: ACM, 2015: 2256−2265, articleTitle=null, refAbstract=null), Reference(id=1327017451272909039, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=121, rfOrder=122, authorNames=null, journalName=null, refType=null, unstructuredReference=Ho J, Jain A, Abbeel P. Denoising diffusion probabilistic models[C]//Proc of the 34th Advances in Neural Information Processing Systems. Cambridge, MA: MIT, 2020: 6840−6851, articleTitle=null, refAbstract=null), Reference(id=1327017451331629296, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=122, rfOrder=123, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Shoufa, Sun Peize, Song Yibing, et al. DiffusionDet: Diffusion model for object detection[C]//Proc of the 19th IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2023: 19830−19843, articleTitle=null, refAbstract=null), Reference(id=1327017451419709681, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=123, rfOrder=124, authorNames=null, journalName=null, refType=null, unstructuredReference=Song Jiaming, Meng Chenlin, Ermon S. Denoising diffusion implicit models[C/OL]//Proc of the 8th Int Conf on Learning Representations. Washington: ICLR, 2020[2023-10-02]. https://openreview.net/pdf?id=St1giarCHLP, articleTitle=null, refAbstract=null), Reference(id=1327017451474235634, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=124, rfOrder=125, authorNames=null, journalName=null, refType=null, unstructuredReference=Deng Jiacheng, Lu Jiahao, Zhang Tianzhu. Diff3DETR: Agent-based diffusion model for semi-supervised 3D object detection[C]///Proc of the 18th European Conf on Computer Vision. Berlin: Springer, 2024: 57−73, articleTitle=null, refAbstract=null), Reference(id=1327017451616841971, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=125, rfOrder=126, authorNames=null, journalName=null, refType=null, unstructuredReference=Ranasinghe Y, Hegde D, Patel V M. MonoDiff: Monocular 3D object detection and pose estimation with diffusion models[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2024: 10659−10670, articleTitle=null, refAbstract=null), Reference(id=1327017451679756532, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=126, rfOrder=127, authorNames=null, journalName=null, refType=null, unstructuredReference=Hu Ronghang, Dollár P, He K, et al. Learning to segment every thing[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 4233−4241, articleTitle=null, refAbstract=null), Reference(id=1327017451746865397, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=127, rfOrder=128, authorNames=null, journalName=null, refType=null, unstructuredReference=Kirillov A, Mintun E, Ravi N, et al. Segment anything[C]//Proc of the 19th IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2023: 4015−4026, articleTitle=null, refAbstract=null), Reference(id=1327017451822362870, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=128, rfOrder=129, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Rongsheng, Duan Yaofei, Li Yukun. Segment anything also detect anything[R/OL]. EasyChair, 2023[2024-02-01]. https://easychair.org/publications/preprint/T1rc, articleTitle=null, refAbstract=null), Reference(id=1327017451897860343, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=129, rfOrder=130, authorNames=null, journalName=null, refType=null, unstructuredReference=Tang Lv, Xiao Haoke, Li Bo. Can SAM segment anything? When SAM meets camouflaged object detection[J]. arXiv preprint, arXiv: 2304.04709, 2023, articleTitle=null, refAbstract=null), Reference(id=1327017451960774905, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=130, rfOrder=131, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Dingyuan, Liang Dingkang, Yang Hongcheng, et al. SAM3D: Zero-shot 3D object detection via segment anything model[J]. arXiv preprint, arXiv: 2306.02245, 2023, articleTitle=null, refAbstract=null), Reference(id=1327017452040466682, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=131, rfOrder=132, authorNames=null, journalName=null, refType=null, unstructuredReference=Cui Ruikai, He Siyuan, Qiu Shi. Adaptive low rank adaptation of segment anything to salient object detection[J]. arXiv preprint, arXiv: 2308.05426, 2023, articleTitle=null, refAbstract=null), Reference(id=1327017452103381243, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=132, rfOrder=133, authorNames=null, journalName=null, refType=null, unstructuredReference=Deng Ruining, Cui Can, Liu Quan, et al. Segment anything model (SAM) for digital pathology: Assess zero-shot segmentation on whole slide imaging[J]. arXiv preprint, arXiv: 2304.04155, 2023, articleTitle=null, refAbstract=null), Reference(id=1327017452162101500, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=133, rfOrder=134, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Junfeng, Jiang Yi, Liu Qihao, et al. General object foundation model for images and videos at scale[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2024: 3783−3795, articleTitle=null, refAbstract=null), Reference(id=1327017452237598973, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=134, rfOrder=135, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhan Yufei, Zhu Yousong, Chen Zhiyang, et al. Griffon: Spelling out all object locations at any granularity with large language models[C]//Proc of the 18th European Conf on Computer Vision. Berlin: Springer, 2024: 405−422, articleTitle=null, refAbstract=null), Reference(id=1327017452317290750, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=135, rfOrder=136, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhao Yucheng, Wang Guangting, Tang Chuanxin, et al. A battle of network structures: An empirical study of CNN, transformer, and MLP[J]. arXiv preprint, arXiv: 2108.13002, 2021, articleTitle=null, refAbstract=null), Reference(id=1327017453982429439, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=136, rfOrder=137, authorNames=null, journalName=null, refType=null, unstructuredReference=Gupta A, Dollár P, Girshick R. LVIS: A dataset for large vocabulary instance segmentation[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 5356−5364, articleTitle=null, refAbstract=null), Reference(id=1327017454045344000, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=137, rfOrder=138, authorNames=null, journalName=null, refType=null, unstructuredReference=Dai Xuerui, Yuan Xue, Wei Xueye. TIRNet: Object detection in thermal infrared images for autonomous driving[J]. Applied Intelligence, 2021, 51(3): 1244−1261, articleTitle=null, refAbstract=null), Reference(id=1327017454099869953, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=138, rfOrder=139, authorNames=null, journalName=null, refType=null, unstructuredReference=Bergmann P, Fauser M, Sattlegger D, et al. MVTec AD—A comprehensive real-world dataset for unsupervised anomaly detection[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 9592−9600, articleTitle=null, refAbstract=null), Reference(id=1327017454166978818, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=139, rfOrder=140, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Yu, Wang Tao, Kang Bingyi, et al. Overcoming classifier imbalance for long-tail object detection with balanced group softmax[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2020: 10991−11000, articleTitle=null, refAbstract=null), Reference(id=1327017454225699075, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=140, rfOrder=141, authorNames=null, journalName=null, refType=null, unstructuredReference=郭伟, 唐思涛, 王春艳. 基于YOLOv7道路交通热红外图像目标检测算法[J/OL]. 计算机技术与发展, 2024[2024-08-19]. https://doi.org/10.20165/j.cnki.ISSN1673-629X.2024.0223, articleTitle=null, refAbstract=null), Reference(id=1327017454288613636, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=140, rfOrder=142, authorNames=null, journalName=null, refType=null, unstructuredReference=Guo Wei, Tang Sitao, Wang Chunyan. Object detection algorithm of road traffic thermal infrared image based on YOLOv7[J/OL]. Computer Technology and Development, 2014[2024-08-19]. https://doi.org/10.20165/j.cnki.ISSN1673-629X.2024.0223 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327017454359916805, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=141, rfOrder=143, authorNames=null, journalName=null, refType=null, unstructuredReference=尹嘉超, 吕耀文, 索科, 等. 基于EfficientNetV2的PCB缺陷检测算法[J/OL]. 计算机辅助设计与图形学学报, 2024, 7: 1260−1269, articleTitle=null, refAbstract=null), Reference(id=1327017454422831366, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=141, rfOrder=144, authorNames=null, journalName=null, refType=null, unstructuredReference=Yin Jiachao, Lü Chaowen, Suo Ke, et al. PCB defect detection algorithm based on EfficientNetV2[J/OL]. Journal of Computer-Aided Design & Computer Graphics, 2024, 7: 1260−1269 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327017454489940231, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=142, rfOrder=145, authorNames=null, journalName=null, refType=null, unstructuredReference=Kuznetsova A, Rom H, Alldrin N, et al. The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale[J]. International Journal of Computer Vision, 2020, 128(7): 1956−1981, articleTitle=null, refAbstract=null), Reference(id=1327017454557049096, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=143, rfOrder=146, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Yuhua, Li Wen, Sakaridis C, et al. Domain adaptive faster R-CNN for object detection in the wild[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 3339−3348, articleTitle=null, refAbstract=null), Reference(id=1327017454615769353, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=144, rfOrder=147, authorNames=null, journalName=null, refType=null, unstructuredReference=Kang Bingyi, Liu Zhuang, Wang Xin, et al. Few-shot object detection via feature reweighting[C]//Proc of the 17th IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2019: 8420−8429, articleTitle=null, refAbstract=null), Reference(id=1327017454682878218, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=145, rfOrder=148, authorNames=null, journalName=null, refType=null, unstructuredReference=Tseng H Y, Lee H Y, Huang J B, et al. Cross-domain few-shot classification via learned feature-wise transformation[C/OL]//Proc of the 8th Int Conf on Learning Representations. Washington: ICLR, 2020[2023-10-02]. https://openreview.net/pdf?id=SJl5Np4tPr, articleTitle=null, refAbstract=null), Reference(id=1327017454741598475, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=146, rfOrder=149, authorNames=null, journalName=null, refType=null, unstructuredReference=Qiao Siyuan, Chen L C, Yuille A. Detectors: Detecting objects with recursive feature pyramid and switchable atrous convolution[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 10213−10224, articleTitle=null, refAbstract=null), Reference(id=1327017454808707340, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=147, rfOrder=150, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Yuxin, He Kaiming. Group normalization[C]//Proc of the European Conf on Computer Vision. Berlin: Springer, 2018: 3−19, articleTitle=null, refAbstract=null), Reference(id=1327017454863233293, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=148, rfOrder=151, authorNames=null, journalName=null, refType=null, unstructuredReference=Bai Yancheng, Zhang Yongqiang, Ding Mingli, et al. Sod-mtgan: Small object detection via multi-task generative adversarial network[C]//Proc of the 15th European Conf on Computer Vision. Berlin: Springer, 2018: 206−221, articleTitle=null, refAbstract=null), Reference(id=1327017454921953550, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=149, rfOrder=152, authorNames=null, journalName=null, refType=null, unstructuredReference=Noh J, Bae W, Lee W, et al. Better to follow, follow to be better: Towards precise supervision of feature super-resolution for small object detection[C]//Proc of the 19th IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2019: 9725−9734, articleTitle=null, refAbstract=null), Reference(id=1327017454976479503, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=150, rfOrder=153, authorNames=null, journalName=null, refType=null, unstructuredReference=Deng Deng, Guo Jia, Ververas E, et al. Retinaface: Single-shot multi-level face localisation in the wild[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2020: 5203−5212, articleTitle=null, refAbstract=null), Reference(id=1327017455047782672, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=151, rfOrder=154, authorNames=null, journalName=null, refType=null, unstructuredReference=Gong Yuqi, Yu Xuehui, Ding Yao, et al. Effective fusion factor in FPN for tiny object detection[C]//Proc of the IEEE/CVF Winter Conf on Applications of Computer Vision. Piscataway, NJ: IEEE, 2021: 1160−1168, articleTitle=null, refAbstract=null), Reference(id=1327017455110697233, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=152, rfOrder=155, authorNames=null, journalName=null, refType=null, unstructuredReference=Ying Xinyi, Liu Li, Wang Yingqian, et al. Mapping degeneration meets label evolution: Learning infrared small target detection with single point supervision[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023: 15528−15538, articleTitle=null, refAbstract=null), Reference(id=1327017455177806098, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=153, rfOrder=156, authorNames=null, journalName=null, refType=null, unstructuredReference=Yuan Xiang, Cheng Gong, Yan Kebing, et al. Small object detection via coarse-to-fine proposal generation and imitation learning[C]//Proc of the 19th IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2023: 6317−6327, articleTitle=null, refAbstract=null), Reference(id=1327017455232332051, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=154, rfOrder=157, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Tianxiang, Tan Zhentao, Gong Tao, et al. Mim-iSTd: Mamba-in-Mamba for efficient infrared small target detection[J]. arXiv preprint, arXiv: 2403.02148, 2024, articleTitle=null, refAbstract=null), Reference(id=1327017455295246612, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=155, rfOrder=158, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Qiankun, Liu Rui, Zheng Bolun, et al. Infrared small target detection with scale and location sensitivity[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2024: 17490−17499, articleTitle=null, refAbstract=null), Reference(id=1327017455353966869, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=156, rfOrder=159, authorNames=null, journalName=null, refType=null, unstructuredReference=许嘉怡. 基于超分辨率重建的空中小目标检测算法研究[D/OL]. 长沙: 湖南大学, 2023. DOI: 10.27135/d.cnki.ghudu.2023.000566, articleTitle=null, refAbstract=null), Reference(id=1327017455442047254, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=156, rfOrder=160, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Jiayi. The research on the aerial small object detection algorithm based on super-resolution[D/OL]. Changsha: Hunan University, 2023. DOI:10.27135/d.cnki.ghudu.2023.000566 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327017455500767511, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=157, rfOrder=161, authorNames=null, journalName=null, refType=null, unstructuredReference=Bilen H, Vedaldi A. Weakly supervised deep detection networks[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2016: 2846−2854, articleTitle=null, refAbstract=null), Reference(id=1327017455580459288, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=158, rfOrder=162, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Dong, Huang Jia Bin, Li Yali, et al. Weakly supervised object localization with progressive domain adaptation[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2016: 3512−3520, articleTitle=null, refAbstract=null), Reference(id=1327017455647568153, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=159, rfOrder=163, authorNames=null, journalName=null, refType=null, unstructuredReference=Yin Yufei, Deng Jiajun, Zhou Wengang, et al. Cyclic-bootstrap labeling for weakly supervised object detection[C]//Proc of the 19th IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2023: 7008−7018, articleTitle=null, refAbstract=null), Reference(id=1327017455727259930, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=160, rfOrder=164, authorNames=null, journalName=null, refType=null, unstructuredReference=Gao Shuyong, Xing Haozhe, Zhang Wei, et al. Weakly supervised video salient object detection via point supervision[C]//Proc of the 30th ACM Int Conf on Multimedia. New York: ACM, 2022: 3656−3665, articleTitle=null, refAbstract=null), Reference(id=1327017455798563099, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=161, rfOrder=165, authorNames=null, journalName=null, refType=null, unstructuredReference=Tang Zongheng, Sun Yifan, Liu Si, et al. DETR with additional global aggregation for cross-domain weakly supervised object detection[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023: 11422−11432, articleTitle=null, refAbstract=null), Reference(id=1327017455861477660, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=162, rfOrder=166, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Chang, Zhang Weiming, Lin Xiangru, et al. Ambiguity-resistant semi-supervised learning for dense object detection[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023: 15579−15588, articleTitle=null, refAbstract=null), Reference(id=1327017455928586525, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=163, rfOrder=167, authorNames=null, journalName=null, refType=null, unstructuredReference=Yang Yanchao, Loquercio A, Scaramuzza D, et al. Unsupervised moving object detection via contextual information separation[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 879−888, articleTitle=null, refAbstract=null), Reference(id=1327017455999889694, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=164, rfOrder=168, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Yangtao, Shen Xi, Hu S X, et al. Self-supervised transformers for unsupervised object discovery using normalized cut[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 14543−14553, articleTitle=null, refAbstract=null), Reference(id=1327017456054415647, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=165, rfOrder=169, authorNames=null, journalName=null, refType=null, unstructuredReference=Xie Enze, Ding Jian, Wang Wenhai, et al. DetCo: Unsupervised contrastive learning for object detection[C]//Proc of the 18th IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2021: 8392−8401, articleTitle=null, refAbstract=null), Reference(id=1327017456113135904, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=166, rfOrder=170, authorNames=null, journalName=null, refType=null, unstructuredReference=Inoue N, Furuta R, Yamasaki T, et al. Cross-domain weakly-supervised object detection through progressive domain adaptation[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 5001−5009, articleTitle=null, refAbstract=null), Reference(id=1327017456167661857, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=167, rfOrder=171, authorNames=null, journalName=null, refType=null, unstructuredReference=Kim T, Jeong M, Kim S, et al. Diversify and match: A domain adaptive representation learning paradigm for object detection[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 12456−12465, articleTitle=null, refAbstract=null), Reference(id=1327017456222187810, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=168, rfOrder=172, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhu Xinge, Pang Jiangmiao, Yang Ceyuan, et al. Adapting object detectors via selective cross-domain alignment[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 687−696, articleTitle=null, refAbstract=null), Reference(id=1327017456297685283, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=169, rfOrder=173, authorNames=null, journalName=null, refType=null, unstructuredReference=Vs V, Gupta V, Oza P, et al. Mega-cda: Memory guided attention for category-aware unsupervised domain adaptive object detection[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 4516−4526, articleTitle=null, refAbstract=null), Reference(id=1327017456356405540, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=170, rfOrder=174, authorNames=null, journalName=null, refType=null, unstructuredReference=He Zhenwei, Zhang Lei. Domain adaptive object detection via asymmetric tri-way faster-RCNN[C]//Proc of the 16th European Conf on Computer Vision. Berlin: Springer, 2020: 309−324, articleTitle=null, refAbstract=null), Reference(id=1327017456419320101, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=171, rfOrder=175, authorNames=null, journalName=null, refType=null, unstructuredReference=Cao Shengcao, Joshi D, Gui L Y, et al. Contrastive mean teacher for domain adaptive object detectors[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023: 23839−23848, articleTitle=null, refAbstract=null), Reference(id=1327017456478040358, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=172, rfOrder=176, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Wenyu, Shen Li, Foo C S. Rethinking the role of pre-trained networks in source-free domain adaptation[C]//Proc of the 19th IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2023: 18841−18851, articleTitle=null, refAbstract=null), Reference(id=1327017456532566311, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=173, rfOrder=177, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Xingxuan, Xu Zekai, Xu Renzhe, et al. Towards domain generalization in object detection[J]. arXiv preprint, arXiv: 2203.14387, 2022, articleTitle=null, refAbstract=null), Reference(id=1327017456587092264, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=174, rfOrder=178, authorNames=null, journalName=null, refType=null, unstructuredReference=Vidit V, Engilberge M, Salzmann M. Clip the gap: A single domain generalization approach for object detection[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023: 3219−3229, articleTitle=null, refAbstract=null), Reference(id=1327017456645812521, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=175, rfOrder=179, authorNames=null, journalName=null, refType=null, unstructuredReference=Lehner A, Gasperini S, Marcos-Ramiro A, et al. 3D-VField: Adversarial augmentation of point clouds for domain generalization in 3D object detection[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 17295−17304, articleTitle=null, refAbstract=null), Reference(id=1327017456725504298, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=176, rfOrder=180, authorNames=null, journalName=null, refType=null, unstructuredReference=Long Shaocong, Zhou Qianyu, Ying Chenhao, et al. Rethinking domain generalization: Discriminability and generalizability[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2024, 34(11): 11783−11797, articleTitle=null, refAbstract=null), Reference(id=1327017456809390379, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=177, rfOrder=181, authorNames=null, journalName=null, refType=null, unstructuredReference=Fan Qi, Zhuo Wei, Tang C K, et al. Few-shot object detection with attention-RPN and multi-relation detector[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2020: 4013−4022, articleTitle=null, refAbstract=null), Reference(id=1327017456872304940, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=178, rfOrder=182, authorNames=null, journalName=null, refType=null, unstructuredReference=Qiao Limeng, Zhao Yuxuan, Li Zhiyuan, et al. DeFRCN: Decoupled Faster R-CNN for few-shot object detection[C]//Proc of the 18th IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2021: 8681−8690, articleTitle=null, refAbstract=null), Reference(id=1327017458512277805, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=179, rfOrder=183, authorNames=null, journalName=null, refType=null, unstructuredReference=Xiao Yang, Lepetit V, Marlet R. Few-shot object detection and viewpoint estimation for objects in the wild[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 45(3): 3090−3106, articleTitle=null, refAbstract=null), Reference(id=1327017458575192366, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=180, rfOrder=184, authorNames=null, journalName=null, refType=null, unstructuredReference=Jiang Xinyu, Li Zhengjia, Tian Maoqing, et al. Few-shot object detection via improved classification features[C]//Proc of the IEEE/CVF Winter Conf on Applications of Computer Vision. Piscataway, NJ: IEEE, 2023: 5386−5395, articleTitle=null, refAbstract=null), Reference(id=1327017458633912623, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=181, rfOrder=185, authorNames=null, journalName=null, refType=null, unstructuredReference=Dong Na, Zhang Yongqiang, Ding Mingli, et al. Incremental-DETR: Incremental few-shot object detection via self-supervised learning[C]//Proc of the 37th AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2023: 543−551, articleTitle=null, refAbstract=null), Reference(id=1327017458696827184, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=182, rfOrder=186, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Yaohui, Zhou Qifeng, Chen Haoxing, et al. The Devil is in the few shots: Iterative visual knowledge completion for few-shot learning[J]. arXiv preprint, arXiv: 2404.09778, 2024, articleTitle=null, refAbstract=null), Reference(id=1327017458772324657, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=183, rfOrder=187, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Xiaozhi, Ma Huimin, Wan Ji, et al. Multi-view 3D object detection network for autonomous driving[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 1907−1915, articleTitle=null, refAbstract=null), Reference(id=1327017458835239218, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=184, rfOrder=188, authorNames=null, journalName=null, refType=null, unstructuredReference=Yang Bin, Luo Wenjie, Urtasun R. Pixor: Real-time 3D object detection from point clouds[C]//Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 7652−7660, articleTitle=null, refAbstract=null), Reference(id=1327017458898153779, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=185, rfOrder=189, authorNames=null, journalName=null, refType=null, unstructuredReference=Pan Xuran, Xia Zhuofan, Song Shiji, et al. 3D object detection with pointformer[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 7463−7472, articleTitle=null, refAbstract=null), Reference(id=1327017458961068340, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=186, rfOrder=190, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Yukang, Liu Jianhui, Zhang Xiangyu, et al. Voxelnext: Fully sparse voxelnet for 3D object detection and tracking[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023: 21674−21683, articleTitle=null, refAbstract=null), Reference(id=1327017459032371509, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=187, rfOrder=191, authorNames=null, journalName=null, refType=null, unstructuredReference=Jiang Xiaohui, Li Shuailin, Liu Yingfei, et al. Far3D: Expanding the horizon for surround-view 3D object detection[C]//Proc of the 38th AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2024, 38(3): 2561−2569, articleTitle=null, refAbstract=null), Reference(id=1327017459091091766, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=188, rfOrder=192, authorNames=null, journalName=null, refType=null, unstructuredReference=Shmelkov K, Schmid C, Alahari K. Incremental learning of object detectors without catastrophic forgetting[C]//Proc of the 16th IEEE Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2017: 3400−3409, articleTitle=null, refAbstract=null), Reference(id=1327017459162394935, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=189, rfOrder=193, authorNames=null, journalName=null, refType=null, unstructuredReference=Perez-Rua J M, Zhu Xiatian, Hospedales T M, et al. Incremental few-shot object detection[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2020: 13846−13855, articleTitle=null, refAbstract=null), Reference(id=1327017459221115192, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=190, rfOrder=194, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Junting, Zhang Jie, Ghosh S, et al. Class-incremental learning via deep model consolidation[C]//Proc of the IEEE/CVF Winter Conf on Applications of Computer Vision. Piscataway, NJ: IEEE, 2020: 1131−1140, articleTitle=null, refAbstract=null), Reference(id=1327017459296612665, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=191, rfOrder=195, authorNames=null, journalName=null, refType=null, unstructuredReference=Joseph K, Rajasegaran J, Khan S, et al. Incremental object detection via meta-learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 44(12): 9209−9216, articleTitle=null, refAbstract=null), Reference(id=1327017459367915834, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=192, rfOrder=196, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Yaoyao, Schiele B, Vedaldi A, et al. Continual detection transformer for incremental object detection[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023: 23799−23808, articleTitle=null, refAbstract=null), Reference(id=1327017459430830395, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=193, rfOrder=197, authorNames=null, journalName=null, refType=null, unstructuredReference=Joseph K, Khan S, Khan F S, et al. Towards open world object detection[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 5830−5840, articleTitle=null, refAbstract=null), Reference(id=1327017459493744956, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=194, rfOrder=198, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Zhenyu, Li Yali, Chen Xi, et al. Detecting everything in the open world: Towards universal object detection[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023: 11433−11443, articleTitle=null, refAbstract=null), Reference(id=1327017459556659517, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=195, rfOrder=199, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Zhiheng, Lu Yue, Chen Xingyu, et al. UC-OWOD: Unknown-classified open world object detection[C]//Proc of the 16th European Conf on Computer Vision. Berlin: Springer, 2022: 193−210, articleTitle=null, refAbstract=null), Reference(id=1327017459627962686, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=196, rfOrder=200, authorNames=null, journalName=null, refType=null, unstructuredReference=Zohar O, Wang K C, Yeung S. Prob: Probabilistic objectness for open world object detection[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023: 11444−11453, articleTitle=null, refAbstract=null), Reference(id=1327017459695071551, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=197, rfOrder=201, authorNames=null, journalName=null, refType=null, unstructuredReference=Ma Zeyu, Yang Yang, Wang Guoqing, et al. Rethinking open-world object detection in autonomous driving scenarios[C]//Proc of the 30th ACM Int Conf on Multimedia. New York: ACM, 2022: 1279−1288, articleTitle=null, refAbstract=null), Reference(id=1327017459762180416, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=198, rfOrder=202, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Yanghao, Yue Zhongqi, Hua X S, et al. Random boxes are open-world object detectors[C]//Proc of the 19th IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2023: 6233−6243, articleTitle=null, refAbstract=null), Reference(id=1327017459846066497, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=199, rfOrder=203, authorNames=null, journalName=null, refType=null, unstructuredReference=Kim D, Lin T Y, Angelova A, et al. Learning open-world object proposals without learning to classify[J]. IEEE Robotics and Automation Letters, 2022, 7(2): 5453−5460, articleTitle=null, refAbstract=null), Reference(id=1327017459925758274, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=200, rfOrder=204, authorNames=null, journalName=null, refType=null, unstructuredReference=Zareian A, Rosa K D, Hu D H, et al. Open-vocabulary object detection using captions[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 14393−14402, articleTitle=null, refAbstract=null), Reference(id=1327017460001255747, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=201, rfOrder=205, authorNames=null, journalName=null, refType=null, unstructuredReference=Gu Xiuye, Lin T Y, Kuo Weicheng, et al. Open-vocabulary object detection via vision and language knowledge distillation[C/OL]//Proc of the 9th Int Conf on Learning Representations. Washington: ICLR, 2021[2023-10-02 ]. https://arxiv.org/abs/2104.13921, articleTitle=null, refAbstract=null), Reference(id=1327017460064170308, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=202, rfOrder=206, authorNames=null, journalName=null, refType=null, unstructuredReference=Du Yu, Wei Fangyun, Zhang Zihe, et al. Learning to prompt for open-vocabulary object detection with vision-language model[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 14084−14093, articleTitle=null, refAbstract=null), Reference(id=1327017460139667781, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=203, rfOrder=207, authorNames=null, journalName=null, refType=null, unstructuredReference=Minderer M, Gritsenko A, Stone A, et al. Simple open-vocabulary object detection[C]//Proc of the 17th European Conf on Computer Vision. Berlin: Springer, 2022: 728−755, articleTitle=null, refAbstract=null), Reference(id=1327017460210970950, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=204, rfOrder=208, authorNames=null, journalName=null, refType=null, unstructuredReference=Kim D, Angelova A, Kuo Weicheng. Region-aware pretraining for open-vocabulary object detection with vision transformers[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023: 11144−11154, articleTitle=null, refAbstract=null), Reference(id=1327017460269691207, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=205, rfOrder=209, authorNames=null, journalName=null, refType=null, unstructuredReference=Shi Cheng, Yang Sibei. Edadet: Open-vocabulary object detection using early dense alignment[C]//Proc of the 19th IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2023: 15724−15734, articleTitle=null, refAbstract=null), Reference(id=1327017460328411464, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=206, rfOrder=210, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Tao. Learning to detect and segment for open vocabulary object detection[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway. NJ: IEEE, 2023: 7051−7060, articleTitle=null, refAbstract=null), Reference(id=1327017460387131721, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=207, rfOrder=211, authorNames=null, journalName=null, refType=null, unstructuredReference=Bai Yutong, Geng Xinyang, Mangalam K, et al. Sequential modeling enables scalable learning for large vision models[J]. arXiv preprint, arXiv: 2312.00785, 2023, articleTitle=null, refAbstract=null), Reference(id=1327017460458434890, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=208, rfOrder=212, authorNames=null, journalName=null, refType=null, unstructuredReference=陈瑶, 吕青, 戚晓峰. 开发基于乳腺超声人工智能的移动终端应用软件: DeepBC[J]. 中国普外基础与临床杂志, 2022, 29(1): 46−50, articleTitle=null, refAbstract=null), Reference(id=1327017460521349451, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=208, rfOrder=213, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Yao, Lü Qing, Qi Xiaofeng. Develop mobile phone terminal application software DeepBC based on breast ultrasound artificial intelligence[J]. Chinese Journal of Bases and Clinics in General Surgery, 2022, 29(1): 46−50 (in Chinese), articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1327017424098014197, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, xref=1, ext=[AuthorCompanyExt(id=1327017424110597110, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424098014197, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024), AuthorCompanyExt(id=1327017424123180023, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424098014197, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1中国科学院大学杭州高等研究院 杭州 310024)]), AuthorCompany(id=1327017424215454712, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, xref=2, ext=[AuthorCompanyExt(id=1327017424228037625, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424215454712, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2CAS Key Laboratory of System Software, Beijing 100190), AuthorCompanyExt(id=1327017424240620538, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424215454712, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2中国科学院基础软件与系统重点实验室 北京 100190)]), AuthorCompany(id=1327017424324506619, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, xref=3, ext=[AuthorCompanyExt(id=1327017424337089532, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424324506619, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3State Key Laboratory of Computer Science (Institute of Software, Chinese Academy of Sciences), Beijing 100190), AuthorCompanyExt(id=1327017424345478141, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424324506619, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3计算机科学国家重点实验室(中国科学院软件研究所) 北京 100190)]), AuthorCompany(id=1327017424437752830, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, xref=4, ext=[AuthorCompanyExt(id=1327017424450335743, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424437752830, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
4University of Chinese Academy of Sciences, Beijing 100049), AuthorCompanyExt(id=1327017424458724352, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424437752830, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
4中国科学院大学 北京 100049)]), AuthorCompany(id=1327017424550998016, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, xref=5, ext=[AuthorCompanyExt(id=1327017424559386625, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424550998016, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
5Joint Laboratory on Cyberspace Security (China Southern Power Grid Co., Ltd.), Guangzhou 510620), AuthorCompanyExt(id=1327017424563580930, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424550998016, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
5网络空间安全联合实验室(中国南方电网有限公司)广州 510620)]), AuthorCompany(id=1327017424660049923, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, xref=6, ext=[AuthorCompanyExt(id=1327017424668438532, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424660049923, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
6Guangdong Power Grid Co., Ltd., Guangzhou 510620), AuthorCompanyExt(id=1327017424681021445, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, companyId=1327017424660049923, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
6广东电网有限责任公司 广州 510620)])], figs=[ArticleFig(id=1327017429034709056, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, label=Figure 1, caption=
The number of publications on object detection, figureFileSmall=xYl11xbjxMZHKZrUXaCODA==, figureFileBig=IZZAqq1lSoEAcGGbJyRVoA==, tableContent=null), ArticleFig(id=1327017429114400833, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, label=图1, caption=
关于目标检测文献的发表数量, figureFileSmall=xYl11xbjxMZHKZrUXaCODA==, figureFileBig=IZZAqq1lSoEAcGGbJyRVoA==, tableContent=null), ArticleFig(id=1327017429357670466, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, label=Figure 2, caption=
Development context diagram of the target detection model introduced in this paper, figureFileSmall=7iH7c1yNkOtDf1Ppm0e9/w==, figureFileBig=RJk+VXVBLiz/+2CktNYS8A==, tableContent=null), ArticleFig(id=1327017429449945155, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, label=图2, caption=
本文介绍的目标检测模型的发展脉络图, figureFileSmall=7iH7c1yNkOtDf1Ppm0e9/w==, figureFileBig=RJk+VXVBLiz/+2CktNYS8A==, tableContent=null), ArticleFig(id=1327017429533831236, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, label=Figure 3, caption=
Overview of CNN-based object detection models, figureFileSmall=2CW5S7r1tdd1nmGMML8WlQ==, figureFileBig=VOcYYHdPUxOrvzYzcw5HgQ==, tableContent=null), ArticleFig(id=1327017429596745797, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, label=图3, caption=
基于CNN的目标检测模型的概述, figureFileSmall=2CW5S7r1tdd1nmGMML8WlQ==, figureFileBig=VOcYYHdPUxOrvzYzcw5HgQ==, tableContent=null), ArticleFig(id=1327017429693214790, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, label=Figure 4, caption=
Overview of MLP-based object detection models, figureFileSmall=OaQI4SRNHDSrHk9AFIOuJg==, figureFileBig=Py19DQUT0H4H24bXTH9Alg==, tableContent=null), ArticleFig(id=1327017429760323655, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, label=图4, caption=
基于MLP的目标检测模型的概述, figureFileSmall=OaQI4SRNHDSrHk9AFIOuJg==, figureFileBig=Py19DQUT0H4H24bXTH9Alg==, tableContent=null), ArticleFig(id=1327017429852598344, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, label=Figure 5, caption=
Visualization of detection results for different object detection models, figureFileSmall=+QVbwEXGJGtoiIBZU47d+A==, figureFileBig=NiL4LYCtBt+J4DITvNa+LA==, tableContent=null), ArticleFig(id=1327017431584845897, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, label=图5, caption=
不同目标检测模型的检测结果可视化, figureFileSmall=+QVbwEXGJGtoiIBZU47d+A==, figureFileBig=NiL4LYCtBt+J4DITvNa+LA==, tableContent=null), ArticleFig(id=1327017431685509194, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, label=Figure 6, caption=
Small object detection trends, figureFileSmall=jMsGMIFgLts61VNaEOet1A==, figureFileBig=c7GQwK8IiJf1lAiug8zO6Q==, tableContent=null), ArticleFig(id=1327017431769395275, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, label=图6, caption=
小目标检测趋势, figureFileSmall=jMsGMIFgLts61VNaEOet1A==, figureFileBig=c7GQwK8IiJf1lAiug8zO6Q==, tableContent=null), ArticleFig(id=1327017431891030092, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, label=Figure 7, caption=
Weakly-supervised object detection trend, figureFileSmall=uw56MoUPqwSqZOKicquObg==, figureFileBig=3EaUPMFHopKSWowEOP0jyA==, tableContent=null), ArticleFig(id=1327017431995887693, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, label=图7, caption=
弱监督目标检测趋势, figureFileSmall=uw56MoUPqwSqZOKicquObg==, figureFileBig=3EaUPMFHopKSWowEOP0jyA==, tableContent=null), ArticleFig(id=1327017432104939598, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, label=Figure 8, caption=
Unsupervised object detection trend, figureFileSmall=RzzA9yhzirkS3olTs9cQFQ==, figureFileBig=hQ2lTaA7MXQSFTjZ5AEsCw==, tableContent=null), ArticleFig(id=1327017432306266191, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, label=图8, caption=
无监督目标检测趋势, figureFileSmall=RzzA9yhzirkS3olTs9cQFQ==, figureFileBig=hQ2lTaA7MXQSFTjZ5AEsCw==, tableContent=null), ArticleFig(id=1327017432398540880, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, label=Figure 9, caption=
Domain adaptive and generalized object detection trends, figureFileSmall=dcYDV3dmLcJb5NjMliwdhg==, figureFileBig=xiLYRRmrF2ma4oU2X+jQvA==, tableContent=null), ArticleFig(id=1327017432486621265, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, label=图9, caption=
域适应与域泛化目标检测趋势, figureFileSmall=dcYDV3dmLcJb5NjMliwdhg==, figureFileBig=xiLYRRmrF2ma4oU2X+jQvA==, tableContent=null), ArticleFig(id=1327017432557924434, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, label=Figure 10, caption=
Few-shot object detection trend, figureFileSmall=A6tCixVj24ia00EYwXhvQg==, figureFileBig=+XGKmBW19BLSkvklWkLllQ==, tableContent=null), ArticleFig(id=1327017432625033299, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, label=图10, caption=
少样本目标检测趋势, figureFileSmall=A6tCixVj24ia00EYwXhvQg==, figureFileBig=+XGKmBW19BLSkvklWkLllQ==, tableContent=null), ArticleFig(id=1327017432734085204, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, label=Figure 11, caption=
3D object detection trend, figureFileSmall=nP0692IenPzAbBseyULgkw==, figureFileBig=/C+k+xbWQpmnxZ+Y8PzZDA==, tableContent=null), ArticleFig(id=1327017432830554197, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, label=图11, caption=
3维目标检测趋势, figureFileSmall=nP0692IenPzAbBseyULgkw==, figureFileBig=/C+k+xbWQpmnxZ+Y8PzZDA==, tableContent=null), ArticleFig(id=1327017432897663062, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, label=Figure 12, caption=
Incremental learning object detection trend, figureFileSmall=eFvF5JRp7Z61IW06yEqRZg==, figureFileBig=h9EgW3QW7Ptd9QespUPUgQ==, tableContent=null), ArticleFig(id=1327017432985743447, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, label=图12, caption=
增量学习目标检测趋势, figureFileSmall=eFvF5JRp7Z61IW06yEqRZg==, figureFileBig=h9EgW3QW7Ptd9QespUPUgQ==, tableContent=null), ArticleFig(id=1327017433082212440, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, label=Figure 13, caption=
Open-world and open-vocabulary object detection trend, figureFileSmall=6FqRQ0cJ7FAOJyMpSEbS5g==, figureFileBig=+J5jNQIalh2bq5/ywMAK3Q==, tableContent=null), ArticleFig(id=1327017433149321306, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, label=图13, caption=
开放世界和开放词汇目标检测趋势, figureFileSmall=6FqRQ0cJ7FAOJyMpSEbS5g==, figureFileBig=+J5jNQIalh2bq5/ywMAK3Q==, tableContent=null), ArticleFig(id=1327017433270956123, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, label=Figure 14, caption=
zero-shot object detection trend, figureFileSmall=/LC4dt/JZsK3XU9aPOE2DA==, figureFileBig=CDSwC1SuXGbWm8rO4D3gEQ==, tableContent=null), ArticleFig(id=1327017433342259292, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, label=图14, caption=
zero-shot目标检测趋势, figureFileSmall=/LC4dt/JZsK3XU9aPOE2DA==, figureFileBig=CDSwC1SuXGbWm8rO4D3gEQ==, tableContent=null), ArticleFig(id=1327017433426145373, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, label=Figure 15, caption=
Result diagram of the target detection system when the Tesla autonomous vehicle accident occurs, figureFileSmall=BjdpJbHgBYsanUdim9eiUg==, figureFileBig=zNUsRumDzcrX7c+WYaRe9w==, tableContent=null), ArticleFig(id=1327017433556168798, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, label=图15, caption=
Tesla自动驾驶车辆事故发生时目标检测系统结果图, figureFileSmall=BjdpJbHgBYsanUdim9eiUg==, figureFileBig=zNUsRumDzcrX7c+WYaRe9w==, tableContent=null), ArticleFig(id=1327017433644249183, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, label=Table 1, caption=
Overview of the Common Datasets for Object Detection, figureFileSmall=null, figureFileBig=null, tableContent=
| 数据集 | | 类别 | | 训练集 | 验证集 | 训练-验证集 | 测试集 |
|---|
| 注:括号外数值表示数据集包含的图像数量,括号内数值表示对应数据集包含的目标实例数量. |
| PASCAL VOC 2007 | | 20类:人、鸟、猫、牛、狗、马、羊、飞机、自行车、船、巴士、汽车、摩托车、火车、瓶子、椅子、餐桌、盆栽、沙发和电视/显示器 | | 2 501(6 301) | 2 510(6307) | 5 011(12608) | 4 952(12032) |
| PASCAL VOC 2012 | | | 5717(13609) | 5823(13841) | 11540(27450) | |
| MS COCO 2014 | | 80类:人、自行车、汽车、摩托车、飞机、巴士、火车、卡车、船、交通灯、消防栓、停车标志、停车表、长凳、鸟、猫、狗、马、羊、牛、大象、熊、斑马、长颈鹿、背包、雨伞、手提包、领带、行李箱、飞盘、滑雪板、滑雪板、运动球、风筝、棒球棍、棒球手套、滑板、冲浪板、网球拍、瓶子、红酒杯、杯子、叉子、刀、勺、碗、香蕉、苹果、三明治、橙子、西兰花、胡萝卜、热狗、披萨、甜甜圈、蛋糕、椅子、沙发、盆栽、床、餐桌、厕所、电视、笔记本电脑、鼠标、遥控器、键盘、手机、微波炉、烤箱、烤面包机、水槽、冰箱、书、时钟、花瓶、剪刀、泰迪熊、吹风机和牙刷 | | 82783 | 40504 | 123287 | 40775 |
| MS COCO 2015 | | | 82783 | 40504 | 123287 | 81434 |
| MS COCO 2017 | | | 118287 | 5000 | 123287 | 40670 |
), ArticleFig(id=1327017433749106784, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, label=表1, caption=
目标检测常用数据集概览
, figureFileSmall=null, figureFileBig=null, tableContent=
| 数据集 | | 类别 | | 训练集 | 验证集 | 训练-验证集 | 测试集 |
|---|
| 注:括号外数值表示数据集包含的图像数量,括号内数值表示对应数据集包含的目标实例数量. |
| PASCAL VOC 2007 | | 20类:人、鸟、猫、牛、狗、马、羊、飞机、自行车、船、巴士、汽车、摩托车、火车、瓶子、椅子、餐桌、盆栽、沙发和电视/显示器 | | 2 501(6 301) | 2 510(6307) | 5 011(12608) | 4 952(12032) |
| PASCAL VOC 2012 | | | 5717(13609) | 5823(13841) | 11540(27450) | |
| MS COCO 2014 | | 80类:人、自行车、汽车、摩托车、飞机、巴士、火车、卡车、船、交通灯、消防栓、停车标志、停车表、长凳、鸟、猫、狗、马、羊、牛、大象、熊、斑马、长颈鹿、背包、雨伞、手提包、领带、行李箱、飞盘、滑雪板、滑雪板、运动球、风筝、棒球棍、棒球手套、滑板、冲浪板、网球拍、瓶子、红酒杯、杯子、叉子、刀、勺、碗、香蕉、苹果、三明治、橙子、西兰花、胡萝卜、热狗、披萨、甜甜圈、蛋糕、椅子、沙发、盆栽、床、餐桌、厕所、电视、笔记本电脑、鼠标、遥控器、键盘、手机、微波炉、烤箱、烤面包机、水槽、冰箱、书、时钟、花瓶、剪刀、泰迪熊、吹风机和牙刷 | | 82783 | 40504 | 123287 | 40775 |
| MS COCO 2015 | | | 82783 | 40504 | 123287 | 81434 |
| MS COCO 2017 | | | 118287 | 5000 | 123287 | 40670 |
), ArticleFig(id=1327017433849770081, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, label=Table 2, caption=
Technical Points of Target Detection Model Based on CNN, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 骨干网络 | 端到端 | 阶段 | 区域建议 | 多尺度特征 | NMS | 输出层 |
|---|
| 注:✗为不支持的特性;✓为支持的特性;SS为选择性搜索;SVM为支持向量机;FC为全连接层;Conv为卷积层. |
| R-CNN | AlexNet | ✗ | 2阶段 | SS | ✗ | ✗ | SVM |
| SPP-Net | AlexNet | ✗ | 2阶段 | SS | ✓ | ✓ | SVM |
| Fast R-CNN | VGG | (训练)✓,(推理)✗ | 2阶段 | SS | ✗ | ✓ | FC |
| Faster R-CNN | VGG | ✓ | 2阶段 | RPN | ✗ | ✓ | FC |
| YOLO | DarkNet | ✓ | 1阶段 | ✗(网络) | ✗ | ✓ | FC |
| YOLO9000 | DarkNet-19 | ✓ | 1阶段 | ✗ | ✗ | ✓ | Conv |
| YOLOv3 | DarkNet-53 | ✓ | 1阶段 | ✗ | ✓ | ✓ | Conv |
| SSD | VGG-16 | ✓ | 1阶段 | ✗ | ✓ | ✓ | Conv |
| FPN | ResNet-101 | ✗ | 2阶段 | RPN | ✓ | ✓ | FC |
| RetinaNet | ResNeXt-101 | ✓ | 1阶段 | ✗ | ✓ | ✓ | Conv |
| Cascade R-CNN | ResNet-101 | ✓ | 2阶段 | RPN | ✓ | ✓ | FC |
| CornerNet | Hourglass-104 | ✓ | 1阶段 | ✗ | ✓ | ✓ | Conv |
| CenterNet | Hourglass-104 | ✓ | 1阶段 | ✗ | ✓ | ✗ | Conv |
| FCOS | ResNeXt | ✓ | 1阶段 | ✗ | ✓ | ✓ | Conv |
| Sparse R-CNN | ResNeXt-101 | ✓ | | 可学习的提议目标框 | ✗ | ✗ | FC |
| YOLOF | ResNet | ✓ | 1阶段 | ✗ | ✓ | ✓ | Conv |
| YOLOX | Modified CSP | ✓ | 1阶段 | ✗ | | ✓ | Conv |
), ArticleFig(id=1327017434034319458, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, label=表2, caption=
基于CNN的目标检测模型技术点
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 骨干网络 | 端到端 | 阶段 | 区域建议 | 多尺度特征 | NMS | 输出层 |
|---|
| 注:✗为不支持的特性;✓为支持的特性;SS为选择性搜索;SVM为支持向量机;FC为全连接层;Conv为卷积层. |
| R-CNN | AlexNet | ✗ | 2阶段 | SS | ✗ | ✗ | SVM |
| SPP-Net | AlexNet | ✗ | 2阶段 | SS | ✓ | ✓ | SVM |
| Fast R-CNN | VGG | (训练)✓,(推理)✗ | 2阶段 | SS | ✗ | ✓ | FC |
| Faster R-CNN | VGG | ✓ | 2阶段 | RPN | ✗ | ✓ | FC |
| YOLO | DarkNet | ✓ | 1阶段 | ✗(网络) | ✗ | ✓ | FC |
| YOLO9000 | DarkNet-19 | ✓ | 1阶段 | ✗ | ✗ | ✓ | Conv |
| YOLOv3 | DarkNet-53 | ✓ | 1阶段 | ✗ | ✓ | ✓ | Conv |
| SSD | VGG-16 | ✓ | 1阶段 | ✗ | ✓ | ✓ | Conv |
| FPN | ResNet-101 | ✗ | 2阶段 | RPN | ✓ | ✓ | FC |
| RetinaNet | ResNeXt-101 | ✓ | 1阶段 | ✗ | ✓ | ✓ | Conv |
| Cascade R-CNN | ResNet-101 | ✓ | 2阶段 | RPN | ✓ | ✓ | FC |
| CornerNet | Hourglass-104 | ✓ | 1阶段 | ✗ | ✓ | ✓ | Conv |
| CenterNet | Hourglass-104 | ✓ | 1阶段 | ✗ | ✓ | ✗ | Conv |
| FCOS | ResNeXt | ✓ | 1阶段 | ✗ | ✓ | ✓ | Conv |
| Sparse R-CNN | ResNeXt-101 | ✓ | | 可学习的提议目标框 | ✗ | ✗ | FC |
| YOLOF | ResNet | ✓ | 1阶段 | ✗ | ✓ | ✓ | Conv |
| YOLOX | Modified CSP | ✓ | 1阶段 | ✗ | | ✓ | Conv |
), ArticleFig(id=1327017434155954275, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, label=Table 3, caption=
Advantages and Disadvantages of CNN-Based Target Detection Models, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 出版物 | 优点 | 缺点 |
|---|
| R-CNN | 文献[14] | 第1个使用CNN的目标检测模型 | 需要大量冗余的特征 计算 |
| SPP-Net | 文献[15] | 避免重复计算 特征图 | 仍然需要多个二分类支持向量机 |
| Fast R-CNN | 文献[16] | 使用全连接层来输出结果 | 速度受选择性搜索算法影响 |
| Faster R-CNN | 文献[18] | 引入区域建议网络生成候选区域 | 2阶段网络速度慢,算法较复杂 |
| YOLO | 文献[19] | 第1个1阶段算法,运行速度快 | 对小尺寸目标识别能 力差 |
| YOLO9000 | 文献[20] | 可识别种类更多,速度更快 | 仍未完全解决小目标检测能力差的问题 |
| YOLOv3 | 文献[22] | 引入多尺度特征图 | 检测能力仍然较1阶段检测器差 |
| SSD | 文献[25] | 使用纯卷积结构和多尺度特征图 | 手工设计先验框非常依赖经验 |
| FPN | 文献[26] | 引入里程碑式的特征金字塔结构 | 略微增加了模型的复杂度和计算开销 |
| RetinaNet | 文献[28] | 解决正负样本 不均衡问题 | 训练过程可能更复杂 |
| Cascade R-CNN | 文献[29] | 通过级联的方式显著提升检测精度 | 增加了计算成本且可能导致运行速度变慢 |
| CornerNet | 文献[30] | 以2个角点来建模目标检测 | 角点匹配较难,没有考虑物体本身的特征 |
| CenterNet | 文献[32] | 直接预测目标的 中心点 | 无法处理中心点接近重叠的情况 |
| FCOS | 文献[35] | 完全由卷积结构组成,结构简单 | 重叠目标多的场景可能需要更复杂的后处理 |
| Sparse R-CNN | 文献[36] | 以完全稀疏化的操作来建模目标检测 | 学习高质量候选区域需要更多训练过程 |
| YOLOF | 文献[38] | 取得更好的正负 样本均衡 | 仅使用最高层特征会限制多尺度检测能力 |
| YOLOX | 文献[40] | YOLO结构的 进一步优化 | 对非常小的目标性能 不佳 |
| YOLOv7 | 文献[42] | 具有更强大的 实时性 | 最高精度可能不如其他检测算法 |
), ArticleFig(id=1327017434311143524, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, label=表3, caption=
基于CNN的目标检测模型优缺点
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 出版物 | 优点 | 缺点 |
|---|
| R-CNN | 文献[14] | 第1个使用CNN的目标检测模型 | 需要大量冗余的特征 计算 |
| SPP-Net | 文献[15] | 避免重复计算 特征图 | 仍然需要多个二分类支持向量机 |
| Fast R-CNN | 文献[16] | 使用全连接层来输出结果 | 速度受选择性搜索算法影响 |
| Faster R-CNN | 文献[18] | 引入区域建议网络生成候选区域 | 2阶段网络速度慢,算法较复杂 |
| YOLO | 文献[19] | 第1个1阶段算法,运行速度快 | 对小尺寸目标识别能 力差 |
| YOLO9000 | 文献[20] | 可识别种类更多,速度更快 | 仍未完全解决小目标检测能力差的问题 |
| YOLOv3 | 文献[22] | 引入多尺度特征图 | 检测能力仍然较1阶段检测器差 |
| SSD | 文献[25] | 使用纯卷积结构和多尺度特征图 | 手工设计先验框非常依赖经验 |
| FPN | 文献[26] | 引入里程碑式的特征金字塔结构 | 略微增加了模型的复杂度和计算开销 |
| RetinaNet | 文献[28] | 解决正负样本 不均衡问题 | 训练过程可能更复杂 |
| Cascade R-CNN | 文献[29] | 通过级联的方式显著提升检测精度 | 增加了计算成本且可能导致运行速度变慢 |
| CornerNet | 文献[30] | 以2个角点来建模目标检测 | 角点匹配较难,没有考虑物体本身的特征 |
| CenterNet | 文献[32] | 直接预测目标的 中心点 | 无法处理中心点接近重叠的情况 |
| FCOS | 文献[35] | 完全由卷积结构组成,结构简单 | 重叠目标多的场景可能需要更复杂的后处理 |
| Sparse R-CNN | 文献[36] | 以完全稀疏化的操作来建模目标检测 | 学习高质量候选区域需要更多训练过程 |
| YOLOF | 文献[38] | 取得更好的正负 样本均衡 | 仅使用最高层特征会限制多尺度检测能力 |
| YOLOX | 文献[40] | YOLO结构的 进一步优化 | 对非常小的目标性能 不佳 |
| YOLOv7 | 文献[42] | 具有更强大的 实时性 | 最高精度可能不如其他检测算法 |
), ArticleFig(id=1327017436009836646, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, label=Table 4, caption=
Experimental Results of CNN-Based Object Detection Model on Public Datasets %, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | VOC 2007 test | VOC 2010 test | VOC 2012 test | | COCO val | | COCO test-dev |
|---|
| AP | AP | AP | | AP | AP50 | | AP | AP50 |
|---|
| 注:“-”表示在原始论文中没有进行实验或未公开的实验结果,☝表示2017年版本的MS COCO数据集实验结果,AP50表示在交并比大于50%时的AP. |
| R-CNN | 58.5 | 53.7 | | | - | - | | - | - |
| SPP-Net | 59.2 | - | | | - | - | | - | - |
| Fast R-CNN | 70.0 | 68.8 | 68.4 | | - | - | | - | - |
| Faster R-CNN | 69.9 | - | 70.4 | | 21.2 | 41.5 | | 21.9 | 42.7 |
| YOLO | 63.4 | - | 57.9 | | - | - | | - | - |
| YOLO9000 | 78.6 | - | 73.4 | | - | - | | 21.6 | 44.0 |
| YOLOv3 | - | - | - | | - | - | | 33.0 | 57.9 |
| SSD | 76.8 | - | 80.0 | | - | - | | 26.8 | 46.5 |
| FPN | - | - | - | | - | - | | 36.2 | 59.1 |
| RetinaNet | - | - | - | | - | - | | 40.8 | 61.1 |
| Cascade R-CNN | - | - | - | | - | - | | 42.8 | 61.1 |
| CornerNet | - | - | - | | - | - | | 42.2 | 57.8 |
| CenterNet(Zhou) | 80.7 | - | - | | 45.1 | 63.5 | | 45.1 | 63.9 |
| CenterNet(Duan) | - | - | - | | 41.3 | 59.2 | | 47.0 | 64.5 |
| FCOS | - | - | - | | - | - | | 44.7 | 64.1 |
| Sparse R-CNN | - | - | - | | 46.4☝ | 64.6☝ | | 51.5☝ | 71.7☝ |
| YOLOF | - | - | - | | 47.1☝ | 66.4☝ | | 44.3☝ | 62.9☝ |
| YOLOX | - | - | - | | 47.3☝ | - | | 51.2☝ | 69.6☝ |
| YOLOv7 | - | - | - | | 55.9☝ | 73.5☝ | | 56.0☝ | 73.5☝ |
), ArticleFig(id=1327017436144054375, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, label=表4, caption=
基于CNN的目标检测模型在公开数据集上的实验结果
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | VOC 2007 test | VOC 2010 test | VOC 2012 test | | COCO val | | COCO test-dev |
|---|
| AP | AP | AP | | AP | AP50 | | AP | AP50 |
|---|
| 注:“-”表示在原始论文中没有进行实验或未公开的实验结果,☝表示2017年版本的MS COCO数据集实验结果,AP50表示在交并比大于50%时的AP. |
| R-CNN | 58.5 | 53.7 | | | - | - | | - | - |
| SPP-Net | 59.2 | - | | | - | - | | - | - |
| Fast R-CNN | 70.0 | 68.8 | 68.4 | | - | - | | - | - |
| Faster R-CNN | 69.9 | - | 70.4 | | 21.2 | 41.5 | | 21.9 | 42.7 |
| YOLO | 63.4 | - | 57.9 | | - | - | | - | - |
| YOLO9000 | 78.6 | - | 73.4 | | - | - | | 21.6 | 44.0 |
| YOLOv3 | - | - | - | | - | - | | 33.0 | 57.9 |
| SSD | 76.8 | - | 80.0 | | - | - | | 26.8 | 46.5 |
| FPN | - | - | - | | - | - | | 36.2 | 59.1 |
| RetinaNet | - | - | - | | - | - | | 40.8 | 61.1 |
| Cascade R-CNN | - | - | - | | - | - | | 42.8 | 61.1 |
| CornerNet | - | - | - | | - | - | | 42.2 | 57.8 |
| CenterNet(Zhou) | 80.7 | - | - | | 45.1 | 63.5 | | 45.1 | 63.9 |
| CenterNet(Duan) | - | - | - | | 41.3 | 59.2 | | 47.0 | 64.5 |
| FCOS | - | - | - | | - | - | | 44.7 | 64.1 |
| Sparse R-CNN | - | - | - | | 46.4☝ | 64.6☝ | | 51.5☝ | 71.7☝ |
| YOLOF | - | - | - | | 47.1☝ | 66.4☝ | | 44.3☝ | 62.9☝ |
| YOLOX | - | - | - | | 47.3☝ | - | | 51.2☝ | 69.6☝ |
| YOLOv7 | - | - | - | | 55.9☝ | 73.5☝ | | 56.0☝ | 73.5☝ |
), ArticleFig(id=1327017436265689192, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, label=Table 5, caption=
Advantages and Disadvantages of the Target Detection Model Based on Transformer, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 出版物 | 优点 | 缺点 |
|---|
| DETR | 文献[37] | 将Transformer结构引入目标检测流程 | 计算复杂度高,训练难以收敛 |
| Deformable DETR | 文献[72] | 通过稀疏化的采样来选取参考点来加速 | 查询数增加至300,有较高的浮点操作次数 |
| Efficient DETR | 文献[73] | 减少了Transformer块数,加速网络收敛 | 浮点操作次数较DETR有显著增加 |
| PnP-DETR | 文献[74] | 自适应地在空间上 分配计算 | 模型实现较标准DETR更复杂 |
| Sparse-DETR | 文献[75] | 有选择地更新编码器中的tokens | 对超参数的选择可能更敏感 |
| ViT | 文献[44] | 使用纯粹Transformer 的视觉骨干结构 | 计算复杂度高且难以直接迁移 |
| UP-DETR | 文献[79] | 为DETR引入无监督预训练方法 | 比优化后的DETR需要更多的训练轮次 |
| PVT | 文献[86] | 为ViT引入特征 金字塔结构 | 网络消耗资源快速增长 |
| Swin-Transformer | 文献[87] | 引入滑动窗口赋予 模型局部感受野 | 训练和推理速度较慢,需要更多计算资源 |
| YOLOS | 文献[88] | 以接近于原始ViT的结构实现目标检测 | 需要更多训练时间 |
| GLIP | 文献[89] | 使用文本-图像多模态预训练模型的算法 | 需要多种模态的训练数据,推理速度较慢 |
| DAB-DETR | 文献[91] | 引入更好的空间先验 知识 | 引入了额外的复杂性 |
| DN-DETR | 文献[92] | 将网络的训练过程定义为一个去噪任务 | 只考虑操作正样本,增加模型计算负担 |
| Co-DETR | 文献[93] | 通过1对多方式分配正样本,增强能力 | 增加了训练过程的计算负担 |
| GCViT | 文献[94] | 全局自注意力和局部自注意力结合 | 计算成本更高,不便用于资源受限的环境 |
| IMFA | 文献[95] | 只对潜在的感兴趣区域计算多尺度特征 | 检测精度可能下降 |
), ArticleFig(id=1327017436374741097, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, label=表5, caption=
基于Transformer的目标检测模型优缺点
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 出版物 | 优点 | 缺点 |
|---|
| DETR | 文献[37] | 将Transformer结构引入目标检测流程 | 计算复杂度高,训练难以收敛 |
| Deformable DETR | 文献[72] | 通过稀疏化的采样来选取参考点来加速 | 查询数增加至300,有较高的浮点操作次数 |
| Efficient DETR | 文献[73] | 减少了Transformer块数,加速网络收敛 | 浮点操作次数较DETR有显著增加 |
| PnP-DETR | 文献[74] | 自适应地在空间上 分配计算 | 模型实现较标准DETR更复杂 |
| Sparse-DETR | 文献[75] | 有选择地更新编码器中的tokens | 对超参数的选择可能更敏感 |
| ViT | 文献[44] | 使用纯粹Transformer 的视觉骨干结构 | 计算复杂度高且难以直接迁移 |
| UP-DETR | 文献[79] | 为DETR引入无监督预训练方法 | 比优化后的DETR需要更多的训练轮次 |
| PVT | 文献[86] | 为ViT引入特征 金字塔结构 | 网络消耗资源快速增长 |
| Swin-Transformer | 文献[87] | 引入滑动窗口赋予 模型局部感受野 | 训练和推理速度较慢,需要更多计算资源 |
| YOLOS | 文献[88] | 以接近于原始ViT的结构实现目标检测 | 需要更多训练时间 |
| GLIP | 文献[89] | 使用文本-图像多模态预训练模型的算法 | 需要多种模态的训练数据,推理速度较慢 |
| DAB-DETR | 文献[91] | 引入更好的空间先验 知识 | 引入了额外的复杂性 |
| DN-DETR | 文献[92] | 将网络的训练过程定义为一个去噪任务 | 只考虑操作正样本,增加模型计算负担 |
| Co-DETR | 文献[93] | 通过1对多方式分配正样本,增强能力 | 增加了训练过程的计算负担 |
| GCViT | 文献[94] | 全局自注意力和局部自注意力结合 | 计算成本更高,不便用于资源受限的环境 |
| IMFA | 文献[95] | 只对潜在的感兴趣区域计算多尺度特征 | 检测精度可能下降 |
), ArticleFig(id=1327017436483793002, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, label=Table 6, caption=
Experimental Results of the Transformer-Based Object Detection Model on Public Datasets, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | AP/% | AP50/% | 浮点运算 量/GFLOP | 检测速 度/fps | 参数量 |
|---|
| DETR | 44.9 | 64.7 | 253 | 10 | 60×106 |
| Deformable DETR | 46.2 | 65.2 | 173 | 19 | 40×106 |
| Efficient DETR | 45.7 | 64.1 | 289 | | 54×106 |
| PnP-DETR | 43.1 | 63.4 | | | |
| Sparse DETR | 49.3 | 69.5 | 144 | 17.2 | 41×106 |
| UP-DETR | 42.8 | 63.0 | | | 41.3×106 |
| PVT(RetinaNet) | 41.9 | 63.1 | | | 53.9×106 |
| YOLOS | 42.0 | | 538 | 2.7 | 127×106 |
| DAB-DETR | 46.6 | | 296 | | 63×106 |
| DN-DETR | 48.6 | 67.4 | 195 | | 48×106 |
| Co-DETR | 65.9 | | | | 304×106 |
| IMFA | 45.5 | 65.0 | 108 | | 53×106 |
), ArticleFig(id=1327017436563484779, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, label=表6, caption=
基于Transformer的目标检测模型在公开数据集上的实验结果
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | AP/% | AP50/% | 浮点运算 量/GFLOP | 检测速 度/fps | 参数量 |
|---|
| DETR | 44.9 | 64.7 | 253 | 10 | 60×106 |
| Deformable DETR | 46.2 | 65.2 | 173 | 19 | 40×106 |
| Efficient DETR | 45.7 | 64.1 | 289 | | 54×106 |
| PnP-DETR | 43.1 | 63.4 | | | |
| Sparse DETR | 49.3 | 69.5 | 144 | 17.2 | 41×106 |
| UP-DETR | 42.8 | 63.0 | | | 41.3×106 |
| PVT(RetinaNet) | 41.9 | 63.1 | | | 53.9×106 |
| YOLOS | 42.0 | | 538 | 2.7 | 127×106 |
| DAB-DETR | 46.6 | | 296 | | 63×106 |
| DN-DETR | 48.6 | 67.4 | 195 | | 48×106 |
| Co-DETR | 65.9 | | | | 304×106 |
| IMFA | 45.5 | 65.0 | 108 | | 53×106 |
), ArticleFig(id=1327017436638982252, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, label=Table 7, caption=
Advantages and Disadvantages of the Target Detection Model Based on MLP, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 出版物 | 优点 | 缺点 |
|---|
| MLP-Mixer | 文献[108] | 在计算机视觉领域重 新提出纯MLP结构 | 固定输入大小,不易 有效转移到下游任务 |
| AS-MLP | 文献[115] | 轴向移动特征为模型 提供局部感受野 | 特征提取能力不如SOTA方法 |
| CycleMLP | 文献[116] | 使用循环采样进行 上下文聚合 | 结构复杂,可能丢失 重要信息 |
| Hire-MLP | 文献[117] | 通过区域重排捕获 更多局部信息 | 重排操作可能破坏 位置先验信息 |
| Wave-MLP | 文献[118] | 赋予神经网络复数 操作的优势特性 | 实现相对复杂 |
| RaMLP | 文献[119] | 通过区域感知混合操 作增强局部感受野 | 混合然后恢复可能 破坏原始信息 |
), ArticleFig(id=1327017436739645549, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, label=表7, caption=
基于MLP的目标检测模型优缺点
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 出版物 | 优点 | 缺点 |
|---|
| MLP-Mixer | 文献[108] | 在计算机视觉领域重 新提出纯MLP结构 | 固定输入大小,不易 有效转移到下游任务 |
| AS-MLP | 文献[115] | 轴向移动特征为模型 提供局部感受野 | 特征提取能力不如SOTA方法 |
| CycleMLP | 文献[116] | 使用循环采样进行 上下文聚合 | 结构复杂,可能丢失 重要信息 |
| Hire-MLP | 文献[117] | 通过区域重排捕获 更多局部信息 | 重排操作可能破坏 位置先验信息 |
| Wave-MLP | 文献[118] | 赋予神经网络复数 操作的优势特性 | 实现相对复杂 |
| RaMLP | 文献[119] | 通过区域感知混合操 作增强局部感受野 | 混合然后恢复可能 破坏原始信息 |
), ArticleFig(id=1327017436815143022, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, label=Table 8, caption=
Experimental Results of the Target Detection Model Based on MLP on Public Datasets, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | AP/% | AP50/% | 参数量 | 浮点运算量/GFLOP |
|---|
| AS-MLP | 51.5 | 70.0 | 145.0×106 | 961.0 |
| Cycle-MLP | 42.7 | 63.3 | 85.9×106 | |
| HireMLP | 44.9 | | 105.8×106 | 424.5 |
| Wave-MLP | 44.2 | 65.1 | 66.1×106 | 333.9 |
| RaMLP | 46.4 | 67.7 | 70.0×106 | |
), ArticleFig(id=1327017436899029103, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, label=表8, caption=
基于MLP的目标检测模型在公开数据集上的实验结果
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | AP/% | AP50/% | 参数量 | 浮点运算量/GFLOP |
|---|
| AS-MLP | 51.5 | 70.0 | 145.0×106 | 961.0 |
| Cycle-MLP | 42.7 | 63.3 | 85.9×106 | |
| HireMLP | 44.9 | | 105.8×106 | 424.5 |
| Wave-MLP | 44.2 | 65.1 | 66.1×106 | 333.9 |
| RaMLP | 46.4 | 67.7 | 70.0×106 | |
), ArticleFig(id=1327017436974526576, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, label=Table 9, caption=
Comprehensive Experimental Comparison on COCO 2017 test Dataset (Similar Training Costs), figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 训练显存/GB | 骨干网络 | mAP/% | mAP50/% | mAP75/% | mAPsmall/% | mAPmedium/% | mAPlarge/% |
|---|
| CenterNet | 3.45 | ResNet-18 | 25.9 | 42.6 | 27.1 | 9.1 | 30.1 | 40.3 |
| YOLOX-tiny | 3.5 | | 31.8 | 49.1 | 33.8 | 12.4 | 34.9 | 47.3 |
| FCOS | 3.6 | ResNet-50 | 36.6 | 56.0 | 38.8 | 21.1 | 40.7 | 47.1 |
| Faster R-CNN | 3.8 | ResNet-50 | 37.8 | 58.6 | 41.0 | 21.6 | 41.5 | 49.3 |
| YOLO v3 | 3.8 | DarkNet-53 | 30.8 | 52.8 | 32.0 | 14.4 | 33.4 | 44.7 |
| RetinaNet | 3.8 | ResNet-50 | 36.5 | 55.4 | 39.1 | 20.4 | 40.3 | 48.1 |
| Cascade R-CNN | 4.2 | ResNet-50 | 40.4 | 58.9 | 44.1 | 22.8 | 43.7 | 54.0 |
| YOLO v3 | 7.4 | DarkNet-54 | 33.7 | 56.6 | 35.3 | 19.4 | 36.8 | 44.3 |
| Cascade R-CNN | 7.6 | ResNeXt-101 | 43.7 | 62.3 | 47.7 | 25.1 | 47.6 | 57.3 |
| YOLOX-S | 7.6 | | 40.3 | 59.1 | 43.4 | 23.5 | 44.5 | 59.4 |
| DETR | 7.9 | ResNet-50 | 39.9 | 60.4 | 41.7 | 17.6 | 43.5 | 59.4 |
| YOLOF | 8.3 | ResNet-50 | 37.5 | 57.0 | 40.4 | 19.0 | 44.2 | 53.2 |
| CornerNet | 9.5 | Hourglass-104 | 39.6 | 55.0 | 42.2 | 20.7 | 41.8 | 54.4 |
| RetinaNet | 10.0 | ResNeXt-101 | 40.8 | 60.5 | 43.7 | 22.9 | 44.4 | 54.6 |
| FCOS | 10.0 | ResNeXt-101 | 42.7 | 62.5 | 45.7 | 26.0 | 46.5 | 54.7 |
| Faster R-CNN | 10.3 | ResNeXt-101 | 42.1 | 63.0 | 46.3 | 24.8 | 46.2 | 55.2 |
| Cascade R-CNN | 10.7 | ResNeXt-101 | 44.7 | 63.6 | 48.9 | 26.1 | 48.6 | 58.6 |
| CornerNet | 13.9 | Hourglass-104 | 40.4 | 55.9 | 43.2 | 20.2 | 42.7 | 58.4 |
| RetinaNet | 14.5 | PVT-s | 40.4 | 61.3 | 43.1 | 24.8 | 43.2 | 54.8 |
| Deformable DETR | | ResNet-50 | 44.3 | 63.2 | 48.6 | 26.8 | 47.7 | 58.8 |
| Conditional DETR | | ResNet | 41.0 | 61.9 | 43.5 | 20.4 | 44.5 | 59.9 |
| DAB-DETR | | ResNet-50 | 42.3 | 62.9 | 45.2 | 21.6 | 46.1 | 61.3 |
| DiffusionDet | | ResNet-50 | 45.4 | 65.1 | 48.7 | 28.3 | 47.9 | 61.5 |
| ViTDet | | ViT-B | 51.5 | 72.1 | 56.6 | 35.3 | 55.5 | 66.3 |
| Co-DETR | 19.2 | ResNet-50 | 52.1 | 69.4 | 57.1 | 35.4 | 55.4 | 65.8 |
| Co-DETR | | Swin-L | 58.9 | 76.9 | 64.8 | 42.5 | 62.7 | 75.1 |
), ArticleFig(id=1327017437070995569, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, label=表9, caption=
COCO 2017 test数据集综合实验对比(训练开销相近)
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 训练显存/GB | 骨干网络 | mAP/% | mAP50/% | mAP75/% | mAPsmall/% | mAPmedium/% | mAPlarge/% |
|---|
| CenterNet | 3.45 | ResNet-18 | 25.9 | 42.6 | 27.1 | 9.1 | 30.1 | 40.3 |
| YOLOX-tiny | 3.5 | | 31.8 | 49.1 | 33.8 | 12.4 | 34.9 | 47.3 |
| FCOS | 3.6 | ResNet-50 | 36.6 | 56.0 | 38.8 | 21.1 | 40.7 | 47.1 |
| Faster R-CNN | 3.8 | ResNet-50 | 37.8 | 58.6 | 41.0 | 21.6 | 41.5 | 49.3 |
| YOLO v3 | 3.8 | DarkNet-53 | 30.8 | 52.8 | 32.0 | 14.4 | 33.4 | 44.7 |
| RetinaNet | 3.8 | ResNet-50 | 36.5 | 55.4 | 39.1 | 20.4 | 40.3 | 48.1 |
| Cascade R-CNN | 4.2 | ResNet-50 | 40.4 | 58.9 | 44.1 | 22.8 | 43.7 | 54.0 |
| YOLO v3 | 7.4 | DarkNet-54 | 33.7 | 56.6 | 35.3 | 19.4 | 36.8 | 44.3 |
| Cascade R-CNN | 7.6 | ResNeXt-101 | 43.7 | 62.3 | 47.7 | 25.1 | 47.6 | 57.3 |
| YOLOX-S | 7.6 | | 40.3 | 59.1 | 43.4 | 23.5 | 44.5 | 59.4 |
| DETR | 7.9 | ResNet-50 | 39.9 | 60.4 | 41.7 | 17.6 | 43.5 | 59.4 |
| YOLOF | 8.3 | ResNet-50 | 37.5 | 57.0 | 40.4 | 19.0 | 44.2 | 53.2 |
| CornerNet | 9.5 | Hourglass-104 | 39.6 | 55.0 | 42.2 | 20.7 | 41.8 | 54.4 |
| RetinaNet | 10.0 | ResNeXt-101 | 40.8 | 60.5 | 43.7 | 22.9 | 44.4 | 54.6 |
| FCOS | 10.0 | ResNeXt-101 | 42.7 | 62.5 | 45.7 | 26.0 | 46.5 | 54.7 |
| Faster R-CNN | 10.3 | ResNeXt-101 | 42.1 | 63.0 | 46.3 | 24.8 | 46.2 | 55.2 |
| Cascade R-CNN | 10.7 | ResNeXt-101 | 44.7 | 63.6 | 48.9 | 26.1 | 48.6 | 58.6 |
| CornerNet | 13.9 | Hourglass-104 | 40.4 | 55.9 | 43.2 | 20.2 | 42.7 | 58.4 |
| RetinaNet | 14.5 | PVT-s | 40.4 | 61.3 | 43.1 | 24.8 | 43.2 | 54.8 |
| Deformable DETR | | ResNet-50 | 44.3 | 63.2 | 48.6 | 26.8 | 47.7 | 58.8 |
| Conditional DETR | | ResNet | 41.0 | 61.9 | 43.5 | 20.4 | 44.5 | 59.9 |
| DAB-DETR | | ResNet-50 | 42.3 | 62.9 | 45.2 | 21.6 | 46.1 | 61.3 |
| DiffusionDet | | ResNet-50 | 45.4 | 65.1 | 48.7 | 28.3 | 47.9 | 61.5 |
| ViTDet | | ViT-B | 51.5 | 72.1 | 56.6 | 35.3 | 55.5 | 66.3 |
| Co-DETR | 19.2 | ResNet-50 | 52.1 | 69.4 | 57.1 | 35.4 | 55.4 | 65.8 |
| Co-DETR | | Swin-L | 58.9 | 76.9 | 64.8 | 42.5 | 62.7 | 75.1 |
), ArticleFig(id=1327017437167464562, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=EN, label=Table 10, caption=
Comprehensive Experimental Comparison on COCO 2017 test Dataset (Similar Overall Performance) %, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 骨干网络 | mAP | mAP50 | mAP75 | mAPsmall | mAPmedium | mAPlarge |
|---|
| RetinaNet | ResNet-50 | 36.5 | 55.4 | 39.1 | 20.4 | 40.3 | 48.1 |
| FOCS | ResNet-50 | 36.6 | 56.0 | 38.8 | 21.1 | 40.7 | 47.1 |
| YOLOF | ResNet-50 | 37.5 | 57.0 | 40.4 | 19.0 | 44.2 | 53.2 |
| Faster R-CNN | ResNet-50 | 37.8 | 58.6 | 41.0 | 21.6 | 41.5 | 49.3 |
| Sparse R-CNN | ResNet-50 | 37.9 | 56.0 | 40.5 | 20.7 | 40.0 | 53.5 |
| CycleMLP | CycleMLP-B1 | 38.6 | 59.1 | 40.8 | 21.9 | 41.8 | 50.7 |
| DETR | ResNet-50 | 39.9 | 60.4 | 41.7 | 17.6 | 43.5 | 59.4 |
| DAB-DETR | ResNet-50 | 42.3 | 62.9 | 45.2 | 21.6 | 46.1 | 61.3 |
| Cascade R-CNN | ResNet-101 | 42.4 | 60.9 | 46.1 | 23.8 | 46.2 | 56.4 |
| FCOS | ResNeXt-101 | 42.7 | 62.5 | 45.7 | 26.0 | 46.5 | 54.7 |
| Cascade R-CNN | ResNeXt-101 | 43.7 | 62.3 | 47.7 | 25.1 | 47.6 | 57.3 |
| Wave-MLP | Wave-MLP-B | 44.2 | 65.1 | 47.1 | 27.1 | 47.8 | 58.9 |
| Deformable DETR | ResNet-50 | 44.3 | 63.2 | 48.6 | 26.8 | 47.7 | 58.8 |
| DiffusionDet | ResNet-50 | 45.4 | 65.1 | 48.7 | 28.3 | 47.9 | 61.5 |
), ArticleFig(id=1327017437255544947, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327017418712527812, language=CN, label=表10, caption=
COCO 2017 test数据集综合实验对比(总体性能相近)
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 骨干网络 | mAP | mAP50 | mAP75 | mAPsmall | mAPmedium | mAPlarge |
|---|
| RetinaNet | ResNet-50 | 36.5 | 55.4 | 39.1 | 20.4 | 40.3 | 48.1 |
| FOCS | ResNet-50 | 36.6 | 56.0 | 38.8 | 21.1 | 40.7 | 47.1 |
| YOLOF | ResNet-50 | 37.5 | 57.0 | 40.4 | 19.0 | 44.2 | 53.2 |
| Faster R-CNN | ResNet-50 | 37.8 | 58.6 | 41.0 | 21.6 | 41.5 | 49.3 |
| Sparse R-CNN | ResNet-50 | 37.9 | 56.0 | 40.5 | 20.7 | 40.0 | 53.5 |
| CycleMLP | CycleMLP-B1 | 38.6 | 59.1 | 40.8 | 21.9 | 41.8 | 50.7 |
| DETR | ResNet-50 | 39.9 | 60.4 | 41.7 | 17.6 | 43.5 | 59.4 |
| DAB-DETR | ResNet-50 | 42.3 | 62.9 | 45.2 | 21.6 | 46.1 | 61.3 |
| Cascade R-CNN | ResNet-101 | 42.4 | 60.9 | 46.1 | 23.8 | 46.2 | 56.4 |
| FCOS | ResNeXt-101 | 42.7 | 62.5 | 45.7 | 26.0 | 46.5 | 54.7 |
| Cascade R-CNN | ResNeXt-101 | 43.7 | 62.3 | 47.7 | 25.1 | 47.6 | 57.3 |
| Wave-MLP | Wave-MLP-B | 44.2 | 65.1 | 47.1 | 27.1 | 47.8 | 58.9 |
| Deformable DETR | ResNet-50 | 44.3 | 63.2 | 48.6 | 26.8 | 47.7 | 58.8 |
| DiffusionDet | ResNet-50 | 45.4 | 65.1 | 48.7 | 28.3 | 47.9 | 61.5 |
)], attaches=null, journal=Journal(id=1324759606947315908, delFlag=0, nameCn=计算机研究与发展, nameEn=Journal of Computer Research and Development, nameHistory1=null, nameHistory2=null, issn=1000-1239, eissn=null, cn=11-1777/TP, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=k2l8zgqwstuxxevFX2qxVA==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Computer Research and Development, journalRemark=null, publicationField=null, createdTime=1793776903141, updatedTime=1793850698612, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=J, firstLetterEn=J, subjectCode=Electronic Information, subjectName=null, subjectCodeEn=Electronic Information, subjectNameEn=null, picCn=k2l8zgqwstuxxevFX2qxVA==, picEn=r6k0Ry+RD+c/VXj5QarmDw==, jcr=null, cjcr=null, exts=[JournalExt(id=1325069127710286688, language=CN, name=计算机研究与发展, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1793850698640, updatedTime=1793850698640, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://crad.ict.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://crad.ict.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://crad.ict.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=https://crad.ict.ac.cn/journalx/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1325069127777395553, language=EN, name=Journal of Computer Research and Development, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1793850698656, updatedTime=1793850698656, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://crad.ict.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://crad.ict.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://crad.ict.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=https://crad.ict.ac.cn/journalx/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1324759914146529478, websiteList=[Website(id=1325070300139892771, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1324759914146529478, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN, language=CN, createTime=1793850978169, createBy=18614031015, updateTime=1793851040259, updateBy=18614031015, name=计算机研究与发展-中文, tplId=1146099689490845704, title=计算机研究与发展, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1325070893751349360, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=articleTextType, value=kx, createTime=1793851119697, updateTime=1793851119697, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893730377837, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=banner, value=null, createTime=1793851119692, updateTime=1793851119692, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893772320883, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=grayFlag, value=0, createTime=1793851119702, updateTime=1793851119702, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893721989228, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=logo, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/file/pic?fileId=U27tDsy717YF7XSPA+Vwdw==, createTime=1793851119690, updateTime=1793851119690, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893784903797, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=minRunFlag, value=0, createTime=1793851119705, updateTime=1793851119705, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893742960751, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/file/pic, createTime=1793851119695, updateTime=1793851119695, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893780709492, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=silenceFlag, value=0, createTime=1793851119704, updateTime=1793851119704, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893738766446, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1793851119694, updateTime=1793851119694, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893755543665, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=themeColor, value=null, createTime=1793851119698, updateTime=1793851119698, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893763932274, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=themeStyle, value=null, createTime=1793851119700, updateTime=1793851119700, creator=18614031015, updator=18614031015)]), Website(id=1325070300580294698, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1324759914146529478, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN, language=EN, createTime=1793850978274, createBy=18614031015, updateTime=1793851036638, updateBy=18614031015, name=计算机研究与发展-英文, tplId=1146101810881728533, title=Journal of Computer Research and Development, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1325070925288321148, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=articleTextType, value=kx, createTime=1793851127216, updateTime=1793851127216, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925263155321, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=banner, value=null, createTime=1793851127210, updateTime=1793851127210, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925309292671, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=grayFlag, value=0, createTime=1793851127221, updateTime=1793851127221, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925254766712, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=logo, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/file/pic?fileId=U27tDsy717YF7XSPA+Vwdw==, createTime=1793851127208, updateTime=1793851127208, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925326069889, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=minRunFlag, value=0, createTime=1793851127225, updateTime=1793851127225, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925279932539, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/file/pic, createTime=1793851127214, updateTime=1793851127214, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925317681280, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=silenceFlag, value=0, createTime=1793851127223, updateTime=1793851127223, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925271543930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1793851127212, updateTime=1793851127212, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925292515453, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=themeColor, value=null, createTime=1793851127217, updateTime=1793851127217, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925300904062, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=themeStyle, value=null, createTime=1793851127219, updateTime=1793851127219, creator=18614031015, updator=18614031015)])], journalTitle=计算机研究与发展, weixinUrl=null, journalUrl=https://crad.ict.ac.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Computer Research and Development, journalPhotoCn=k2l8zgqwstuxxevFX2qxVA==, journalPhotoEn=r6k0Ry+RD+c/VXj5QarmDw==, journalFirstLetter=J, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/10.7544/issn1000-1239.202440315, detailUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202440315, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/PDF/10.7544/issn1000-1239.202440315, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/PDF/10.7544/issn1000-1239.202440315, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1764518400000, fullTextJson=null, articleText=null, reference=null)