Article(id=1327018554244837828, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327018536993665336, articleNumber=null, orderNo=null, doi=10.7544/issn1000-1239.202440048, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1706457600000, receivedDateStr=2024-01-29, revisedDate=1740412800000, revisedDateStr=2025-02-25, acceptedDate=1740931200000, acceptedDateStr=2025-03-03, onlineDate=1794315478144, onlineDateStr=2026-11-10, pubDate=1753977600000, pubDateStr=2025-08-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794315478144, onlineIssueDateStr=2026-11-10, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794315478144, creator=13701087609, updateTime=1794315478144, updator=13701087609, issue=Issue{id=1327018536993665336, tenantId=1146029695717560320, journalId=1324759914146529478, year='2025', volume='62', issue='8', pageStart='1833', pageEnd='2124', issueExtLink='null', onlineDate='null', pubDate='1753977600000', pubDateStr='2025-08-01', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794315474031, creator='13701087609', updateTime=1794376881014, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1327276097470837643, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327018536993665336, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1327276097470837644, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327018536993665336, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=1862, endPage=1874, ext={EN=ArticleExt(id=1327018554420998597, articleId=1327018554244837828, tenantId=1146029695717560320, journalId=1324759914146529478, language=EN, title=Neural Architecture Search on Temporal Convolutions for Complex Action Recognition, columnId=1325489891789910943, journalTitle=Journal of Computer Research and Development, columnName=Artificial Intelligence, runingTitle=null, highlight=null, articleAbstract=
In the field of complex action recognition in videos, the structural design of the model plays a crucial role in its final performance. However, manually designed network structures often rely heavily on the knowledge and experience of researchers. Therefore, neural architecture search (NAS) has received widespread attention from researchers in the field of image processing because of its automated network structure design. Currently, neural architecture search has achieved tremendous development in the image field. Some NAS methods even reduce the number of graphics processing unit (GPU) days required for automated model design to single digits, and the model structures they search show strong competitive potential. This encourages us to extend automated model structure design to the video domain. But it faces two serious challenges: 1) How to capture the long-range contextual temporal association in video as much as possible; 2) How to reduce the computational surge caused by 3D convolution as much as possible. To address the above challenges, we propose a novel neural architecture search on temporal convolutions for complex action recognition (NAS-TC). NAS-TC is a two-stage framework. In the first stage, we use the classic convolutional neural network (CNN) network as the backbone network to complete the computationally intensive feature extraction task. In the second stage, we propose a neural architecture search layer temporal convolutional layer (NAS-TC) to accomplish relatively lightweight long-range temporal model design and information extraction. This ensures that our method will have a more reasonable parameter allocation and can handle minute-level videos. Finally, the proposed method achieves an average performance gain of 2.3% mAP on three complex action recognition benchmark data sets compared with similar methods, and the number of parameters is reduced by 28.5%.
, authors=Pengzhen Ren
1, 2, Xiaodan Liang
1, 3, Xiaojun Chang
4, Ziying Zhao
1, Yun Xiao
5, *, authorsList=Pengzhen Ren, Xiaodan Liang, Xiaojun Chang, Ziying Zhao, Yun Xiao, authorCompany=null, correspAuthors=Yun Xiao, authorNote=
born in 1993. PhD, engineer. His main research interests include multi-modal representation learning, visual language pre-training, and model automation design
born in 1991. PhD, professor, PhD supervisor. Member of CCF. Her main research interests include computer vision, natural language understanding, and smart driving
born in 1986. PhD, professor, PhD supervisor. His main research interests include multi-modal learning, computer vision, and green artificial intelligence
born in 1985. PhD, senior engineer, PhD supervisor. Her main research interests include artificial intelligence and spatial analysis, and the application of large model technology
born in 1978. PhD, professor, PhD supervisor. Senior member of CCF. Her main research interests include data mining, machine learning, and artificial intelligence algorithm research and applications
, 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=1327018557684167132, articleId=1327018554244837828, tenantId=1146029695717560320, journalId=1324759914146529478, language=CN, title=基于时间卷积神经架构搜索的复杂动作识别, columnId=1325489892104483745, journalTitle=计算机研究与发展, columnName=人工智能, runingTitle=null, highlight=null, articleAbstract=
在视频的复杂动作识别领域中,模型的结构设计对其最终的性能起着至关重要的作用. 然而,人工设计的网络结构往往严重依赖于研究人员的知识和经验. 因此,神经架构搜索(neural architecture search,NAS)因其自动化的网络结构设计在图像处理领域受到研究人员的广泛关注. 当前,神经架构搜索已经在图像领域获得了巨大的发展,一些 NAS方法甚至将模型自动化设计所需的 GPU天数减少到了个位数,并且其搜索的模型结构表现出了强大的竞争潜力,这鼓励将自动化模型结构设计拓展到视频领域. 但它面临2个严峻的挑战:1)如何尽可能捕获视频中的长程上下文时间关联;2)如何尽可能降低 3D卷积所带来的计算激增的问题. 为了应对上述挑战,提出了一个基于时间卷积的神经架构搜索复杂动作识别(neural architecture search on temporal convolutions for complex action recognition,NAS-TC)模型. 具体地,NAS-TC具有2个阶段:在第1阶段,采用经典的CNN 网络作为骨干网络,来完成计算密集型的特征提取任务. 在第2阶段,提出了一个神经架构搜索时间卷积层来完成相对轻量级的长程时间模型设计和信息提取. 这确保了提出的方法具有更合理的参数分配并且可以处理分钟级的视频. 最后,提出的方法在3个复杂动作识别基准数据集上与同类型方法相比平均获得了2.3个百分点的mAP的性能增益,并且参数量下降了28.5%.
, authors=任鹏真
1, 2, 梁小丹
1, 3, 常晓军
4, 赵子莹
1, 肖云
5, *, authorsList=任鹏真, 梁小丹, 常晓军, 赵子莹, 肖云, authorCompany=null, correspAuthors=肖云, authorNote=
 |
1993年生. 博士,工程师. 主要研究方向为多模态表示学习、视觉语言预训练、模型自动化设计 |
 |
1991年生. 博士,教授,博士生导师. CCF会员. 主要研究方向为计算机视觉、自然语言理解、智能驾驶 |
 |
1986年生. 博士,教授,博士生导师. 主要研究方向为多模态学习、计算机视觉、绿色人工智能 |
 |
1985年. 博士,高级工程师,博士生导师. 主要研究方向为人工智能与空间分析、大模型技术应用 |
 |
1978年生. 博士,教授,博士生导师. CCF高级会员. 主要研究方向为数据挖据、机器学习、人工智能算法研究及应用 |
, 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=uaSwO++p/2u1QqRz9VarDQ==, magXml=yTjmbJtymt0qb0kn2WbeKA==, pdfUrl=null, pdf=szJMyS0IYxJvwX4RfUC7Vg==, pdfFileSize=1761537, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=ygJ31Zukv17h5XVueCZRKg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=9yocdmIx4v6lSVbAm7LR9w==, mapNumber=null, fund=null)}, authors=[Author(id=1327018558317507053, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=pzhren@foxmail.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327018558397198832, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, authorId=1327018558317507053, language=EN, stringName=Pengzhen Ren, firstName=Pengzhen, middleName=null, lastName=Ren, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, address=
1Pengcheng Laboratory, Shenzhen, Guangdong 518000
2DarkMatter AI Research, Guangzhou 511466, bio={"content":"
born in 1993. PhD, engineer. His main research interests include multi-modal representation learning, visual language pre-training, and model automation design
"}, bioImg=null, bioContent=
born in 1993. PhD, engineer. His main research interests include multi-modal representation learning, visual language pre-training, and model automation design
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018558464307697, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, authorId=1327018558317507053, language=CN, stringName=任鹏真, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, address=
1鹏城实验室 广东深圳 518000
2暗物智能科技(广州)有限公司 广州 511466, bio={"img":"vLewxSG/eZrBy0h3QVJvEQ==","content":"
1993年生. 博士,工程师. 主要研究方向为多模态表示学习、视觉语言预训练、模型自动化设计
"}, bioImg=vLewxSG/eZrBy0h3QVJvEQ==, bioContent=
1993年生. 博士,工程师. 主要研究方向为多模态表示学习、视觉语言预训练、模型自动化设计
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018557881299421, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, xref=1, ext=[AuthorCompanyExt(id=1327018557893882334, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, companyId=1327018557881299421, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1Pengcheng Laboratory, Shenzhen, Guangdong 518000), AuthorCompanyExt(id=1327018557902270943, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, companyId=1327018557881299421, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1鹏城实验室 广东深圳 518000)]), AuthorCompany(id=1327018557965185504, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, xref=2, ext=[AuthorCompanyExt(id=1327018557973574113, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, companyId=1327018557965185504, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2DarkMatter AI Research, Guangzhou 511466), AuthorCompanyExt(id=1327018557981962722, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, companyId=1327018557965185504, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2暗物智能科技(广州)有限公司 广州 511466)])]), Author(id=1327018558543999475, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, 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=1327018558632079862, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, authorId=1327018558543999475, language=EN, stringName=Xiaodan Liang, firstName=Xiaodan, middleName=null, lastName=Liang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 3, address=
1Pengcheng Laboratory, Shenzhen, Guangdong 518000
3School of Intelligent Engineering, Sun Yat-sen University, Shenzhen, Guangdong 518107, bio={"content":"
born in 1991. PhD, professor, PhD supervisor. Member of CCF. Her main research interests include computer vision, natural language understanding, and smart driving
"}, bioImg=null, bioContent=
born in 1991. PhD, professor, PhD supervisor. Member of CCF. Her main research interests include computer vision, natural language understanding, and smart driving
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018558690800119, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, authorId=1327018558543999475, language=CN, stringName=梁小丹, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 3, address=
1鹏城实验室 广东深圳 518000
3中山大学智能工程学院 广东深圳 518107, bio={"img":"Xa7iu2iowhk9AXjVViFd3A==","content":"
1991年生. 博士,教授,博士生导师. CCF会员. 主要研究方向为计算机视觉、自然语言理解、智能驾驶
"}, bioImg=Xa7iu2iowhk9AXjVViFd3A==, bioContent=
1991年生. 博士,教授,博士生导师. CCF会员. 主要研究方向为计算机视觉、自然语言理解、智能驾驶
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018557881299421, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, xref=1, ext=[AuthorCompanyExt(id=1327018557893882334, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, companyId=1327018557881299421, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1Pengcheng Laboratory, Shenzhen, Guangdong 518000), AuthorCompanyExt(id=1327018557902270943, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, companyId=1327018557881299421, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1鹏城实验室 广东深圳 518000)]), AuthorCompany(id=1327018558074237411, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, xref=3, ext=[AuthorCompanyExt(id=1327018558078431716, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, companyId=1327018558074237411, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3School of Intelligent Engineering, Sun Yat-sen University, Shenzhen, Guangdong 518107), AuthorCompanyExt(id=1327018558086820325, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, companyId=1327018558074237411, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3中山大学智能工程学院 广东深圳 518107)])]), Author(id=1327018558757908985, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, 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=1327018558833406459, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, authorId=1327018558757908985, language=EN, stringName=Xiaojun Chang, firstName=Xiaojun, middleName=null, lastName=Chang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
4, address=
4School of Information Science and Technology, University of Science and Technology of China, Hefei 230026, bio={"content":"
born in 1986. PhD, professor, PhD supervisor. His main research interests include multi-modal learning, computer vision, and green artificial intelligence
"}, bioImg=null, bioContent=
born in 1986. PhD, professor, PhD supervisor. His main research interests include multi-modal learning, computer vision, and green artificial intelligence
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018558908903932, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, authorId=1327018558757908985, language=CN, stringName=常晓军, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
4, address=
4中国科学技术大学信息科学技术学院 合肥 230026, bio={"img":"7nfBgM9plMGc15stFS/Q1Q==","content":"
1986年生. 博士,教授,博士生导师. 主要研究方向为多模态学习、计算机视觉、绿色人工智能
"}, bioImg=7nfBgM9plMGc15stFS/Q1Q==, bioContent=
1986年生. 博士,教授,博士生导师. 主要研究方向为多模态学习、计算机视觉、绿色人工智能
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018558145540582, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, xref=4, ext=[AuthorCompanyExt(id=1327018558153929191, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, companyId=1327018558145540582, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
4School of Information Science and Technology, University of Science and Technology of China, Hefei 230026), AuthorCompanyExt(id=1327018558162317800, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, companyId=1327018558145540582, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
4中国科学技术大学信息科学技术学院 合肥 230026)])]), Author(id=1327018558976012798, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, 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=1327018559051510272, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, authorId=1327018558976012798, language=EN, stringName=Ziying Zhao, firstName=Ziying, middleName=null, lastName=Zhao, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1Pengcheng Laboratory, Shenzhen, Guangdong 518000, bio={"content":"
born in 1985. PhD, senior engineer, PhD supervisor. Her main research interests include artificial intelligence and spatial analysis, and the application of large model technology
"}, bioImg=null, bioContent=
born in 1985. PhD, senior engineer, PhD supervisor. Her main research interests include artificial intelligence and spatial analysis, and the application of large model technology
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018559127007745, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, authorId=1327018558976012798, language=CN, stringName=赵子莹, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1鹏城实验室 广东深圳 518000, bio={"img":"EC/YjyBPk+FlwJswLhbLQQ==","content":"
1985年. 博士,高级工程师,博士生导师. 主要研究方向为人工智能与空间分析、大模型技术应用
"}, bioImg=EC/YjyBPk+FlwJswLhbLQQ==, bioContent=
1985年. 博士,高级工程师,博士生导师. 主要研究方向为人工智能与空间分析、大模型技术应用
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018557881299421, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, xref=1, ext=[AuthorCompanyExt(id=1327018557893882334, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, companyId=1327018557881299421, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1Pengcheng Laboratory, Shenzhen, Guangdong 518000), AuthorCompanyExt(id=1327018557902270943, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, companyId=1327018557881299421, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1鹏城实验室 广东深圳 518000)])]), Author(id=1327018559202505219, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yxiao@nwu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1327018559273808389, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, authorId=1327018559202505219, language=EN, stringName=Yun Xiao, firstName=Yun, middleName=null, lastName=Xiao, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
5, *, address=
5School of Information Science and Technology, Northwest University, Xi’an 710127, bio={"content":"
born in 1978. PhD, professor, PhD supervisor. Senior member of CCF. Her main research interests include data mining, machine learning, and artificial intelligence algorithm research and applications
"}, bioImg=null, bioContent=
born in 1978. PhD, professor, PhD supervisor. Senior member of CCF. Her main research interests include data mining, machine learning, and artificial intelligence algorithm research and applications
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018559332528646, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, authorId=1327018559202505219, language=CN, stringName=肖云, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
5, *, address=
5西北大学信息科学与技术学院 西安 710127, bio={"img":"CEiclGkW3PcLlFojK7+s0A==","content":"
1978年生. 博士,教授,博士生导师. CCF高级会员. 主要研究方向为数据挖据、机器学习、人工智能算法研究及应用
"}, bioImg=CEiclGkW3PcLlFojK7+s0A==, bioContent=
1978年生. 博士,教授,博士生导师. CCF高级会员. 主要研究方向为数据挖据、机器学习、人工智能算法研究及应用
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018558225232361, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, xref=5, ext=[AuthorCompanyExt(id=1327018558233620970, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, companyId=1327018558225232361, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
5School of Information Science and Technology, Northwest University, Xi’an 710127), AuthorCompanyExt(id=1327018558242009579, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, companyId=1327018558225232361, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
5西北大学信息科学与技术学院 西安 710127)])])], keywords=[Keyword(id=1327018559416414727, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=EN, orderNo=1, keyword=complex action recognition), Keyword(id=1327018559483523592, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=EN, orderNo=2, keyword=neural architecture search), Keyword(id=1327018559563215369, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=EN, orderNo=3, keyword=convolution decomposition), Keyword(id=1327018559626129930, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=EN, orderNo=4, keyword=video understanding), Keyword(id=1327018559693238795, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=EN, orderNo=5, keyword=deep learning), Keyword(id=1327018559873593868, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=CN, orderNo=1, keyword=复杂动作识别), Keyword(id=1327018559953285645, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=CN, orderNo=2, keyword=神经架构搜索), Keyword(id=1327018561605841423, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=CN, orderNo=3, keyword=卷积分解), Keyword(id=1327018561698116112, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=CN, orderNo=4, keyword=视频理解), Keyword(id=1327018561748447761, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=CN, orderNo=5, keyword=深度学习)], refs=[Reference(id=1327018563791073835, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, 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=Chang Xiaojun, Yu Yaoliang, Yang Yi, et al. They are not equally reliable: Semantic event search using differentiated concept classifiers[C]//Proc of the 29th IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2016: 1884−1893, articleTitle=null, refAbstract=null), Reference(id=1327018563858182700, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, 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=Ji Yuzhu, Zhang Haijun, Zhang Zhao, et al. CNN-based encoder-decoder networks for salient object detection: A comprehensive review and recent advances[J]. Information Sciences, 2021, 546: 835−857, articleTitle=null, refAbstract=null), Reference(id=1327018563925291565, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, 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=Ren Jiahuan, Zhang Zhao, Hong Richang, et al. Robust low-rank convolution network for image denoising[C]//Proc of the 30th ACM Int Conf on Multimedia. New York: ACM, 2022: 6211−6219, articleTitle=null, refAbstract=null), Reference(id=1327018564009177646, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, 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=Wu Zhihao, Zhao Zhang, Fan Jicong. Graph convolutional kernel machine versus graph convolutional networks[C/OL]//Proc of the 37th Advances in Neural Information Processing Systems. 2023[2024-08-01]. https://proceedings.neurips.cc/paper_files/paper/2023/hash/3ec6c6fc9065aa57785eb05dffe7c3db-Abstract-Conference.html, articleTitle=null, refAbstract=null), Reference(id=1327018564076286511, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, 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=Zoph B, Vasudevan V, Shlens J, et al. Learning transferable architectures for scalable image recognition[C]//Proc of the 31st IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 8697−8710, articleTitle=null, refAbstract=null), Reference(id=1327018564135006768, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, 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=Real E, Aggarwal A, Huang Y, et al. Regularized evolution for image classifier architecture search[C]//Proc of the 23rd AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2019: 4780−4789, articleTitle=null, refAbstract=null), Reference(id=1327018564193727025, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, 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=Ren Pengzhen, Xiao Yun, Chang Xiaojun, et al. A comprehensive survey of neural architecture search: Challenges and solutions[J]. ACM Computing Surveys, 2021, 54(4): 1−34, articleTitle=null, refAbstract=null), Reference(id=1327018564252447282, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, 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=Zhang Xingwu, Ma Rui, Zhao Yu, et al. Differentiable sampling based efficient architecture search for automatic fault diagnosis[J]. Engineering Applications of Artificial Intelligence, 2024, 127(1): 107−214, articleTitle=null, refAbstract=null), Reference(id=1327018564323750451, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, 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=孟子尧,谷雪,梁艳春,等. 深度神经架构搜索综述[J]. 计算机研究与发展,2021,58(1):22−33, articleTitle=null, refAbstract=null), Reference(id=1327018564386665012, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Meng Ziyao, Gu Xue, Liang Yanchun, et al. Deep neural architecture search: A survey[J]. Journal of Computer Research and Development, 2021, 58(1): 22−33 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327018564483134005, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=Sigurdsson G A, Varol G, Wang Xiaolong, et al. Hollywood in homes: Crowdsourcing data collection for activity understanding[C]//Proc of the 14th European Conf on Computer Vision. Berlin: Springer, 2016: 510−526, articleTitle=null, refAbstract=null), Reference(id=1327018566139884086, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Cai Han, Chen Tianyao, Zhang Weinan, et al. Efficient architecture search by network transformation[C]//Proc of the 22nd AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2018: 2787−2794, articleTitle=null, refAbstract=null), Reference(id=1327018566223770167, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=Negrinho R, Geoff G. Deeparchitect: Automatically designing and training deep architectures[J]. arXiv preprint, arXiv: 1704.08792, 2017, articleTitle=null, refAbstract=null), Reference(id=1327018566282490424, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Chenxi, Zoph B, Neumann M, et al. Progressive neural architecture search[C]//Proc of the 15th European Conf on Computer Vision. Berlin: Springer, 2018: 19−34, articleTitle=null, refAbstract=null), Reference(id=1327018566349599289, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Kandasamy K, Neiswanger W, Schneider J, et al. Neural architecture search with Bayesian optimisation and optimal transport[C/OL]//Proc of the 32nd Advances in Neural Information Processing Systems. 2018[2023-10-01]. https://proceedings.neurips.cc/paper_files/paper/2018/hash/f33ba15effa5c10e873bf3842afb46a6-Abstract.html, articleTitle=null, refAbstract=null), Reference(id=1327018566446068282, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Hanxiao, Simonyan K, Yang Yiming. DARTS: Differentiable architecture search[J]. arXiv preprint, arXiv: 1806.09055, 2018, articleTitle=null, refAbstract=null), Reference(id=1327018566517371451, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Poliakov E, Hung Weijie, Huang Chingchun. Efficient constraint-aware neural architecture search for object detection[C]//Proc of the 15th Asia Pacific Signal and Information Processing Association Annual Summit and Conf. Piscataway, NJ: IEEE, 2023: 733−740, articleTitle=null, refAbstract=null), Reference(id=1327018566601257532, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Ozaeta M A A, Fajardo A C, Brazas F P, et al. Seagrass classification using differentiable architecture search[C]//Proc of the 26th Int Joint Conf on Computer Science and Software Engineering (JCSSE). Piscataway, NJ: IEEE, 2023: 123−128, articleTitle=null, refAbstract=null), Reference(id=1327018566685143613, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Howard Andrew 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=1327018566756446782, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=19, 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 31st IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 6848−6856, articleTitle=null, refAbstract=null), Reference(id=1327018566827749951, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Tong Zhan, Song Yibing, Wang Jue, et al. Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training[C/OL]//Proc of the 36th Advances in Neural Information Processing Systems. 2022[2023-08-17]. https://proceedings.neurips.cc/paper_files/paper/2022/hash/416f9cb3276121c42eebb86352a4354a-Abstract-Conference.html, articleTitle=null, refAbstract=null), Reference(id=1327018566899053120, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Zisserman A, Carreira J, Simonyan K, et al. The kinetics human action video dataset[J]. arXiv preprint, arXiv: 1705.06950, 2017, articleTitle=null, refAbstract=null), Reference(id=1327018566961967681, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=Goyal R, Ebrahimi Kahou S, Michalski V, et al. The “Something Something” video database for learning and evaluating visual common sense[C]//Proc of the 30th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE. 2017: 5842−5850, articleTitle=null, refAbstract=null), Reference(id=1327018567033270850, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Soomro K, Zamair A R, Shah M. UCF101: A dataset of 101 human actions classes from videos in the wild[J]. arXiv preprint, arXiv: 1212.0402, 2012, articleTitle=null, refAbstract=null), Reference(id=1327018567104574019, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Kuehne H, Jhuang H, Garrote E, et al. HMDB: A large video database for human motion recognition[C]//Proc of the 24th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2011: 2556−2563, articleTitle=null, refAbstract=null), Reference(id=1327018567171682884, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Schindler K, Van Gool L. Action snippets: How many frames does human action recognition require?[C/OL]//Proc of the 21st IEEE/CVF Conf on Computer Vision and Pattern Recognition. 2008[2023-10-15]. https://ieeexplore.ieee.org/document/4587730, articleTitle=null, refAbstract=null), Reference(id=1327018567247180357, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Hussein N, Gavves E, Smeulders A W. Timeception for complex action recognition[C]//Proc of the 32nd IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 254−263, articleTitle=null, refAbstract=null), Reference(id=1327018567322677830, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Hilde K, Ali A, Thomas S. The language of actions: Recovering the syntax and semantics of goal-directed human activities[C]//Proc of the 27th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2014: 780−787, articleTitle=null, refAbstract=null), Reference(id=1327018567393980999, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Yeung S, Russakovsky O, Jin N, et al. Every moment counts: Dense detailed labeling of actions in complex videos[J]. International Journal of Computer Vision, 2018, 126: 375−389, articleTitle=null, refAbstract=null), Reference(id=1327018567482061384, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Jiaming, Li Hanjun, Lin Kunyu, et al. Adafocus: Towards end-to-end weakly supervised learning for long-video action understanding[J]. arXiv preprint, arXiv: 2311.17118, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018567536587337, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=Vaswani A, Shazeer N, Parmar N. Attention is all you need[C/OL]//Proc of the 31st Advances in Neural Information Processing Systems. 2017[2023-10-15]. https://www.semanticscholar.org/reader/204e3073870fae3d05bcbc2f6a8e263d9b72e776, articleTitle=null, refAbstract=null), Reference(id=1327018567612084810, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Bertasius G, Wang H, Torresani L. Is space-time attention all you need for video understanding?[C/OL]//Proc of the 38th Int Conf on Machine Learning. 2021[2024-01-01]. https://proceedings.mlr.press/v139/bertasius21a/bertasius21a-supp.pdf, articleTitle=null, refAbstract=null), Reference(id=1327018567687582283, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Tong Zhan, Song Yibing, Wang Jue, et al. VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training[C]//Proc of the 36th Advances in Neural Information Processing Systems. 2022[2023-12-10]. https://proceedings.neurips.cc/paper_files/paper/2022/hash/416f9cb3276121c42eebb86352a4354a-Abstract-Conference.html, articleTitle=null, refAbstract=null), Reference(id=1327018567767274060, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=He Kaiming, Chen Xinlei, Xie Saining, et al. Masked autoencoders are scalable vision learners[C]//Proc of the 35th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 16000−16009, articleTitle=null, refAbstract=null), Reference(id=1327018567846965837, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=Ji Shuiwang, Xu Wei, Yang Ming, et al. 3D convolutional neural networks for human action recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 35(1): 221−231, articleTitle=null, refAbstract=null), Reference(id=1327018567918269006, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Chao, Zhong Qiaoyong, Xie Di, et al. Collaborative spatiotemporal feature learning for video action recognition[C]//Proc of the 32nd IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 7872−7881, articleTitle=null, refAbstract=null), Reference(id=1327018567981183567, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=Xie Saining, Sun Chen, Huang Jonathan, et al. Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification[C]//Proc of the 15th European Conf on Computer Vision. Berlin: Springer, 2018: 305−321, articleTitle=null, refAbstract=null), Reference(id=1327018568044098128, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Chaoyuan, Feichtenhofer C, Fan Haoqi, et al. Long-term feature banks for detailed video understanding[C]//Proc of the 32nd IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 284−293, articleTitle=null, refAbstract=null), Reference(id=1327018568123789905, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=38, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Chaoyuan, Li Yanghao, Mangalam K, et al. MeMViT: Memory-augmented multiscale vision transformer for efficient long-term video Recognition[C]//Proc of the 35th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 13587−13597, articleTitle=null, refAbstract=null), Reference(id=1327018568203481682, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=39, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=Zoph B. Neural architecture search with reinforcement learning[J]. arXiv preprint, arXiv: 1611.01578, 2016, articleTitle=null, refAbstract=null), Reference(id=1327018568320922195, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=40, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=Cai Han, Yang Jiacheng, Zhang Weinan, et al. Path-level network transformation for efficient architecture search[C/OL]//Proc of the 35th Int Conf on Machine Learning. 2018[2023-11-14]. https://proceedings.mlr.press/v80/cai18a.html, articleTitle=null, refAbstract=null), Reference(id=1327018568400613972, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=Real E, Moore S, Selle A, et al. Large-scale evolution of image classifiers[C/OL]//Proc of the 34th Int Conf on Machine Learning. 2017[2023-10-08]. https://proceedings.mlr.press/v70/real17a.html, articleTitle=null, refAbstract=null), Reference(id=1327018568471917141, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=42, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=Hussein N, Gavves E, Smeulders A W. Unified embedding and metric learning for zero-exemplar event detection[C]//Proc of the 30th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 1096−1105, articleTitle=null, refAbstract=null), Reference(id=1327018568547414614, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=43, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=Habibian A, Mensink T, Snoek C G M. Video2vec embeddings recognize events when examples are scarce[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 39(10): 2089−2103, articleTitle=null, refAbstract=null), Reference(id=1327018568643883607, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=44, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=Girdhar R, Ramanan D. Attentional pooling for action recognition[C/OL]//Proc of the 31st Advances in Neural Information Processing Systems. 2017[2023-10-13]. https://proceedings.neurips.cc/paper/2017/hash/67c6a1e7ce56d3d6fa748ab6d9af3fd7-Abstract.html, articleTitle=null, refAbstract=null), Reference(id=1327018568719381080, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=45, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=Fernando B, Gavves E, Oramas J, et al. Rank pooling for action recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 39(4): 773−787, articleTitle=null, refAbstract=null), Reference(id=1327018568807461465, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=46, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=Oneata D, Verbeek J, Schmid C. Action and event recognition with fisher vectors on a compact feature set[C]//Proc of the 26th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2013: 1817−1824, articleTitle=null, refAbstract=null), Reference(id=1327018568903930458, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=47, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=Cosmin D I, Ionescu B, Aizawa K, et al. Spatio-temporal vector of locally max pooled features for action recognition in videos[C]//Proc of the 30th IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 3097−3106, articleTitle=null, refAbstract=null), Reference(id=1327018570590040667, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=48, rfOrder=48, authorNames=null, journalName=null, refType=null, unstructuredReference=Donahue J, Anne H L, Guadarrama S, et al. Long-term recurrent convolutional networks for visual recognition and description[C]//Proc of the 28th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2015: 2625−2634, articleTitle=null, refAbstract=null), Reference(id=1327018570673926748, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=49, rfOrder=49, authorNames=null, journalName=null, refType=null, unstructuredReference=Ghodrati A, Gavves E, Snoek C G M. Video time: Properties, encoders and evaluation[J]. arXiv preprint, arXiv: 1807.06980, 2018, articleTitle=null, refAbstract=null), Reference(id=1327018570745229917, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=50, rfOrder=50, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang Gao, Liu Zhuang, Van D M L, et al. Densely connected convolutional networks[C]//Proc of the 30th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 4700−4708, articleTitle=null, refAbstract=null), Reference(id=1327018570850087518, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=51, rfOrder=51, authorNames=null, journalName=null, refType=null, unstructuredReference=Shi Wuzhen, Liu Shaohui, Jiang Feng, et al. Video compressed sensing using a convolutional neural network[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2020, 31(2): 425−438, articleTitle=null, refAbstract=null), Reference(id=1327018570929779295, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=52, rfOrder=52, authorNames=null, journalName=null, refType=null, unstructuredReference=Song Xue, Xu Baohan, Jiang Yugang, et al. Predicting content similarity via multimodal modeling for video-in-video advertising[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2020, 31(2): 569−581, articleTitle=null, refAbstract=null), Reference(id=1327018571009471072, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=53, rfOrder=53, authorNames=null, journalName=null, refType=null, unstructuredReference=Simonyan K, Zisserman A. Two-stream convolutional networks for action recognition in videos[C/OL]//Proc of the 28th Advances in Neural Information Processing Systems. 2014[2024-01-19]. https://proceedings.neurips.cc/paper_files/paper/2014/hash/00ec53c4682d36f5c4359f4ae7bd7ba1-Abstract.html, articleTitle=null, refAbstract=null), Reference(id=1327018571097551457, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=54, rfOrder=54, authorNames=null, journalName=null, refType=null, unstructuredReference=Bilen H, Fernando B, Gavves E, et al. Action recognition with dynamic image networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 40(12): 2799−2813, articleTitle=null, refAbstract=null), Reference(id=1327018571152077410, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=55, rfOrder=55, authorNames=null, journalName=null, refType=null, unstructuredReference=Tran D, Bourdev L, Fergus R, et al. Learning spatiotemporal features with 3D convolutional networks[C]//Proc of the 28th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE. 2015: 4489−4497, articleTitle=null, refAbstract=null), Reference(id=1327018571214991971, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=56, rfOrder=56, authorNames=null, journalName=null, refType=null, unstructuredReference=Carreira J, Zisserman A. Quo vadis, action recognition? A new model and the kinetics dataset[C]//Proc of the 30th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 6299−6308, articleTitle=null, refAbstract=null), Reference(id=1327018571286295140, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=57, rfOrder=57, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Bolei, Andonian A, Oliva A, et al. Temporal relational reasoning in videos[C]//Proc of the 15th European Conf on Computer Vision. Berlin: Springer, 2018: 803−818, articleTitle=null, refAbstract=null), Reference(id=1327018571340821093, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=58, rfOrder=58, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Limin, Xiong Yuanjun, Wang, Zhe, et al. Temporal segment networks: Towards good practices for deep action recognition[C]//Proc of the 14th European Conf on Computer Vision. Berlin: Springer, 2016: 20−36, articleTitle=null, refAbstract=null), Reference(id=1327018571407929958, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=59, rfOrder=59, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Limin, Xiong Yuanjun, Wang Zhe, et al. Temporal segment networks for action recognition in videos[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 41(11): 2740−2755, articleTitle=null, refAbstract=null), Reference(id=1327018571466650215, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=60, rfOrder=60, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Xiaolong, Girshick R, Gupta A, et al. Non-local neural networks[C]//Proc of the 31st IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 7794−7803, articleTitle=null, refAbstract=null), Reference(id=1327018571537953384, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=61, rfOrder=61, authorNames=null, journalName=null, refType=null, unstructuredReference=Sigurdsson G A, Divvala S, Farhadi A, et al. Asynchronous temporal fields for action recognition[C]//Proc of the 30th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 585−594, articleTitle=null, refAbstract=null), Reference(id=1327018571596673641, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=62, rfOrder=62, authorNames=null, journalName=null, refType=null, unstructuredReference=Varol G, Ivan L, Cordelia S, et al. Long-term temporal convolutions for action recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 40(6): 1510−1517, articleTitle=null, refAbstract=null), Reference(id=1327018571655393898, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=63, rfOrder=63, authorNames=null, journalName=null, refType=null, unstructuredReference=Zoph B, Vasudevan V, Shlens J, et al. Learning transferable architectures for scalable image recognition[C]//Proc of the 31st IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 8697−8710, articleTitle=null, refAbstract=null), Reference(id=1327018571718308459, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=64, rfOrder=64, 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 31st IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 6848−6856, articleTitle=null, refAbstract=null), Reference(id=1327018571781223020, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=65, rfOrder=65, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Guihong, Duc H, Kartikeya B, et al. Zero-Shot neural architecture search: Challenges, solutions, and opportunities[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(12): 7618−7635, articleTitle=null, refAbstract=null), Reference(id=1327018571844137581, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=66, rfOrder=66, authorNames=null, journalName=null, refType=null, unstructuredReference=Haroon I, Amir R Z, Jiang Yugang, et al. The thumos challenge on action recognition for videos “in the wild”[J]. Computer Vision and Image Understanding, 2017, 155(1): 1−23, articleTitle=null, refAbstract=null), Reference(id=1327018571907052142, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=67, rfOrder=67, authorNames=null, journalName=null, refType=null, unstructuredReference=Girdhar R, Ramanan D, Gupta A, et al. ActionVLAD: Learning spatio-temporal aggregation for action classification[C]//Proc of the 30th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 971−980, articleTitle=null, refAbstract=null), Reference(id=1327018571982549615, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=68, rfOrder=68, authorNames=null, journalName=null, refType=null, unstructuredReference=Hussein N, Gavves E, Smeulders A W M. VideoGraph: Recognizing minutes-long human activities in videos[J]. arXiv preprint, arXiv: 1905.05143, 2019, articleTitle=null, refAbstract=null), Reference(id=1327018572045464176, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=69, rfOrder=69, authorNames=null, journalName=null, refType=null, unstructuredReference=Piergiovanni A, Angelova A, Toshev A, et al. Evolving space-time neural architectures for videos[C]//Proc of the 17th IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2019: 1793−1802, articleTitle=null, refAbstract=null), Reference(id=1327018572125155953, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=70, rfOrder=70, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Huijuan, Das A, Saenko K. R-C3D: Region convolutional 3D network for temporal activity detection[C]//Proc of the 30th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 5783−5792, articleTitle=null, refAbstract=null), Reference(id=1327018572196459122, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=71, rfOrder=71, authorNames=null, journalName=null, refType=null, unstructuredReference=Dai Xiyang, Singh B, Ng J Y H, et al. Tan: Temporal aggregation network for dense multi-label action recognition[C]//Proc of the 6th IEEE Winter Conf on Applications of Computer Vision. Piscataway, NJ: IEEE, 2019: 151−160, articleTitle=null, refAbstract=null), Reference(id=1327018572263567987, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=72, rfOrder=72, authorNames=null, journalName=null, refType=null, unstructuredReference=Piergiovanni A, Ryoo M S. Learning latent super-events to detect multiple activities in videos[C]//Proc of the 31st IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 5304−5313, articleTitle=null, refAbstract=null), Reference(id=1327018572334871156, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=73, rfOrder=73, authorNames=null, journalName=null, refType=null, unstructuredReference=Piergiovanni A, Ryoo M. Temporal Gaussian mixture layer for videos[C/OL]//Proc of the 36th Int Conf on Machine Learning. 2019[2023-12-16]. https://proceedings.mlr.press/v97/piergiovanni19a.html, articleTitle=null, refAbstract=null), Reference(id=1327018572397785717, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=74, rfOrder=74, authorNames=null, journalName=null, refType=null, unstructuredReference=Tirupattur P, Duarte K, Rawat Y S, et al. Modeling multi-label action dependencies for temporal action localization[C]//Proc of the 34th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 1460−1470, articleTitle=null, refAbstract=null), Reference(id=1327018572464894582, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=75, rfOrder=75, authorNames=null, journalName=null, refType=null, unstructuredReference=Dai R, Das S, Minciullo L, et al. Pdan: Pyramid dilated attention network for action detection[C]//Proc of the 8th IEEE/CVF Winter Conf on Applications of Computer Vision. Piscataway, NJ: IEEE, 2021: 2970−2979, articleTitle=null, refAbstract=null), Reference(id=1327018572624278136, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=76, rfOrder=76, authorNames=null, journalName=null, refType=null, unstructuredReference=Dai Rui, Das S, Bremond F. Ctrn: Class-temporal relational network for action detection[J]. arXiv preprint, arXiv: 2110.13473, 2021, articleTitle=null, refAbstract=null), Reference(id=1327018572703969913, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=77, rfOrder=77, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Yuankai, Su Xin, Salihu D, et al. Modeling action spatiotemporal relationships using graph-based class-level attention network for long-term action detection[C]//Proc of the 36th IEEE/RSJ Int Conf on Intelligent Robots and Systems (IROS). Piscataway, NJ: IEEE, 2023: 6719−6726, articleTitle=null, refAbstract=null), Reference(id=1327018572766884474, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=78, rfOrder=78, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Jiaming, Lin Kunyu, Li Haoxin, et al. Graph-based high-order relation modeling for long-term action recognition[C]//Proc of the 34th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 8984−8993, articleTitle=null, refAbstract=null), Reference(id=1327018572833993339, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=79, rfOrder=79, authorNames=null, journalName=null, refType=null, unstructuredReference=Guo Hongji, Wang Hanjing, Ji Qiang. Uncertainty-guided probabilistic transformer for complex action recognition[C]//Proc of the 35th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 20052−20061, articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1327018557881299421, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, xref=1, ext=[AuthorCompanyExt(id=1327018557893882334, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, companyId=1327018557881299421, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1Pengcheng Laboratory, Shenzhen, Guangdong 518000), AuthorCompanyExt(id=1327018557902270943, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, companyId=1327018557881299421, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1鹏城实验室 广东深圳 518000)]), AuthorCompany(id=1327018557965185504, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, xref=2, ext=[AuthorCompanyExt(id=1327018557973574113, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, companyId=1327018557965185504, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2DarkMatter AI Research, Guangzhou 511466), AuthorCompanyExt(id=1327018557981962722, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, companyId=1327018557965185504, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2暗物智能科技(广州)有限公司 广州 511466)]), AuthorCompany(id=1327018558074237411, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, xref=3, ext=[AuthorCompanyExt(id=1327018558078431716, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, companyId=1327018558074237411, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3School of Intelligent Engineering, Sun Yat-sen University, Shenzhen, Guangdong 518107), AuthorCompanyExt(id=1327018558086820325, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, companyId=1327018558074237411, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3中山大学智能工程学院 广东深圳 518107)]), AuthorCompany(id=1327018558145540582, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, xref=4, ext=[AuthorCompanyExt(id=1327018558153929191, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, companyId=1327018558145540582, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
4School of Information Science and Technology, University of Science and Technology of China, Hefei 230026), AuthorCompanyExt(id=1327018558162317800, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, companyId=1327018558145540582, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
4中国科学技术大学信息科学技术学院 合肥 230026)]), AuthorCompany(id=1327018558225232361, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, xref=5, ext=[AuthorCompanyExt(id=1327018558233620970, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, companyId=1327018558225232361, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
5School of Information Science and Technology, Northwest University, Xi’an 710127), AuthorCompanyExt(id=1327018558242009579, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, companyId=1327018558225232361, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
5西北大学信息科学与技术学院 西安 710127)])], figs=[ArticleFig(id=1327018561840722450, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=EN, label=Figure 1, caption=
A long video example of a complex action with four unit actions, figureFileSmall=FrH4neJ/dlfFuCxVPTbRsQ==, figureFileBig=ygJ31Zukv17h5XVueCZRKg==, tableContent=null), ArticleFig(id=1327018561895248403, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=CN, label=图1, caption=
一个包含4个单元动作的复杂动作的长视频示例, figureFileSmall=FrH4neJ/dlfFuCxVPTbRsQ==, figureFileBig=ygJ31Zukv17h5XVueCZRKg==, tableContent=null), ArticleFig(id=1327018562092380692, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=EN, label=Figure 2, caption=
Structure diagram of neural architecture search network based on cell network stacking, figureFileSmall=ek8lnYPRg4X/b09XMKiYUA==, figureFileBig=UfjQR6OowMkHlgeI+LhPPw==, tableContent=null), ArticleFig(id=1327018562159489557, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=CN, label=图2, caption=
基于单元网络堆叠的神经架构搜索网络结构图, figureFileSmall=ek8lnYPRg4X/b09XMKiYUA==, figureFileBig=UfjQR6OowMkHlgeI+LhPPw==, tableContent=null), ArticleFig(id=1327018562251764246, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=EN, label=Figure 3, caption=
Schematic diagram of search space and unit operations structure, figureFileSmall=8/BdS9Cz9nvHP/n17P9/NA==, figureFileBig=YVQO3sL5ixKZkrKWvNPo/w==, tableContent=null), ArticleFig(id=1327018562306290199, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=CN, label=图3, caption=
搜索空间和单元操作结构示意图, figureFileSmall=8/BdS9Cz9nvHP/n17P9/NA==, figureFileBig=YVQO3sL5ixKZkrKWvNPo/w==, tableContent=null), ArticleFig(id=1327018562381787672, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=EN, label=Figure 4, caption=
Network architecture of NAS-TC, figureFileSmall=zAqUDTGjC6bATiSiaOjFmA==, figureFileBig=MNNhUGllU2PtCraxoOxKpw==, tableContent=null), ArticleFig(id=1327018562444702233, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=CN, label=图4, caption=
NAS-TC 的网络架构, figureFileSmall=zAqUDTGjC6bATiSiaOjFmA==, figureFileBig=MNNhUGllU2PtCraxoOxKpw==, tableContent=null), ArticleFig(id=1327018562503422490, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=EN, label=Figure 5, caption=
Variation curve of model parameter quantity with increasing TC layers, figureFileSmall=JICyy8QDfOcAsQnymrJ4RA==, figureFileBig=yZk6bttyqX6T6HPLLaxq7g==, tableContent=null), ArticleFig(id=1327018562574725659, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=CN, label=图5, caption=
模型参数量随着 TC 层数增加的变化曲线, figureFileSmall=JICyy8QDfOcAsQnymrJ4RA==, figureFileBig=yZk6bttyqX6T6HPLLaxq7g==, tableContent=null), ArticleFig(id=1327018562646028828, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=EN, label=Figure 6, caption=
Structure comparison of temporal convolutional module and NAS-Temp, figureFileSmall=Q6E2moWNzyVZkkDHlc56iQ==, figureFileBig=M+FdDl18GbIH/zSs863MvA==, tableContent=null), ArticleFig(id=1327018562708943389, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=CN, label=图6, caption=
时间卷积模块和NAS-Temp的结构对比, figureFileSmall=Q6E2moWNzyVZkkDHlc56iQ==, figureFileBig=M+FdDl18GbIH/zSs863MvA==, tableContent=null), ArticleFig(id=1327018562813800990, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=EN, label=Table 1, caption=
Parameters of Candidate Operation Sets, figureFileSmall=null, figureFileBig=null, tableContent=
| 操作集 | 核大小 $ k $ | 膨胀率 $ d $ | 组数 $ g $ | 填充数 $ p $ |
|---|
| 注:“- ”表示不适用;括号里的数字分别是x, y, z轴上的值. |
| Identity | - | - | - | - |
| Zero | - | - | - | - |
| Avg pool 2 | (2,1,1) | - | - | (1,0,0) |
| Max pool 2 | (2,1,1) | (2,1,1) | - | (1,0,0) |
| DilConv $ k3 $ | (3,1,1) | 2 | $ C $ | (2,0,0) |
| DilConv_$ k $5 | (5,1,1) | 2 | $ C $ | (4,0,0) |
| SepConv $ k $3 | (3,1,1) | 1 | - | (1,0,0) |
| SepConv $ k $5 | (5,1,1) | 1 | - | (2,0,0) |
| SepConv $ k $7 | (7,1,1) | 1 | - | (3,0,0) |
), ArticleFig(id=1327018562918658591, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=CN, label=表1, caption=
候选操作集的参数
, figureFileSmall=null, figureFileBig=null, tableContent=
| 操作集 | 核大小 $ k $ | 膨胀率 $ d $ | 组数 $ g $ | 填充数 $ p $ |
|---|
| 注:“- ”表示不适用;括号里的数字分别是x, y, z轴上的值. |
| Identity | - | - | - | - |
| Zero | - | - | - | - |
| Avg pool 2 | (2,1,1) | - | - | (1,0,0) |
| Max pool 2 | (2,1,1) | (2,1,1) | - | (1,0,0) |
| DilConv $ k3 $ | (3,1,1) | 2 | $ C $ | (2,0,0) |
| DilConv_$ k $5 | (5,1,1) | 2 | $ C $ | (4,0,0) |
| SepConv $ k $3 | (3,1,1) | 1 | - | (1,0,0) |
| SepConv $ k $5 | (5,1,1) | 1 | - | (2,0,0) |
| SepConv $ k $7 | (7,1,1) | 1 | - | (3,0,0) |
), ArticleFig(id=1327018563031904800, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=EN, label=Table 2, caption=
Statistics of the Datasets, figureFileSmall=null, figureFileBig=null, tableContent=
| 数据集 | 视频数 | 总时长/h | 平均时长/min | 每个视频 的动作数 | 种类数 |
|---|
| Charades | 9848 | 82 | 0.5 | 6 | 157 |
| MultiTHUMOS | 400 | 30 | 4.5 | 11 | 65 |
| BreakfastActions | 1712 | 66 | 2.3 | 7 | 48 |
), ArticleFig(id=1327018563119985186, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=CN, label=表2, caption=
数据集的统计信息
, figureFileSmall=null, figureFileBig=null, tableContent=
| 数据集 | 视频数 | 总时长/h | 平均时长/min | 每个视频 的动作数 | 种类数 |
|---|
| Charades | 9848 | 82 | 0.5 | 6 | 157 |
| MultiTHUMOS | 400 | 30 | 4.5 | 11 | 65 |
| BreakfastActions | 1712 | 66 | 2.3 | 7 | 48 |
), ArticleFig(id=1327018563182899747, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=EN, label=Table 3, caption=
Performance Comparison of Models with Different Time Step Inputs, figureFileSmall=null, figureFileBig=null, tableContent=
| I3D | CNN_Steps ⇒ TC_Steps | Timeception[26] | | NAS-TC(本文) |
|---|
| 参数量 | mAP/% | | 参数量 | mAP/% |
|---|
| 注:括号内表示相对Timeception提升的数值;“↑”表示上升的百分点. |
| + 3 TC | 256 ⇒ 32 | 2.0×106 | 33.9 | | 1.5×106 | 34.5 (0.6 ↑) |
| + 3 TC | 512 ⇒ 64 | 2.0×106 | 35.5 | | 1.5×106 | 37.2 (1.7 ↑) |
| + 4 TC | 1 024 ⇒ 128 | 2.8×106 | 37.2 | | 2.0×106 | 39.3 (2.1 ↑) |
), ArticleFig(id=1327018563245814308, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=CN, label=表3, caption=
不同时间步长输入下模型的性能对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| I3D | CNN_Steps ⇒ TC_Steps | Timeception[26] | | NAS-TC(本文) |
|---|
| 参数量 | mAP/% | | 参数量 | mAP/% |
|---|
| 注:括号内表示相对Timeception提升的数值;“↑”表示上升的百分点. |
| + 3 TC | 256 ⇒ 32 | 2.0×106 | 33.9 | | 1.5×106 | 34.5 (0.6 ↑) |
| + 3 TC | 512 ⇒ 64 | 2.0×106 | 35.5 | | 1.5×106 | 37.2 (1.7 ↑) |
| + 4 TC | 1 024 ⇒ 128 | 2.8×106 | 37.2 | | 2.0×106 | 39.3 (2.1 ↑) |
), ArticleFig(id=1327018563333894693, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=EN, label=Table 4, caption=
Performance Comparison of Different Methods on Charades Dataset, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 数据模态 | mAP/% |
|---|
| 注:括号内表示相对于I3D+Timeception,I3D+NAS-TC获得的性能增益;“↑”表示上升的百分点. |
| R-C3D[70] | RGB + Flow | 12.7 |
| Two-stream[61] | RGB + Flow | 18.6 |
| Two-stream+LSTM[61] | RGB + Flow | 17.8 |
| ActionVLAD[67] | RGB + iDT | 21.0 |
| TemporalFields[61] | RGB + Flow | 22.4 |
| TemporalRelations[57] | RGB | 25.2 |
| ResNet-152[61] | RGB | 22.8 |
| ResNet-152+Timeception[26] | RGB | 31.6 |
| 3D ResNet-101[60] | RGB | 35.5 |
| I3D+TAN[71] | RGB + Flow | 17.6 |
| I3D+Super-events[72] | RGB + Flow | 19.4 |
| I3D+TGM[73] | RGB + Flow | 21.5 |
| I3D+MLAD[74] | RGB + Flow | 23.7 |
| I3D+PDAN[75] | RGB + Flow | 26.5 |
| I3D+CTRN[76] | RGB + Flow | 27.8 |
| I3D+GCAN[77] | RGB + Flow | 27.7 |
| I3D[56] | RGB | 32.9 |
| I3D+ActionVLAD[67] | RGB | 35.4 |
| I3D+Timeception[26] | RGB | 37.2 |
| I3D-NL[60] | RGB | 37.5 |
| I3D+VideoGraph[68] | RGB | 37.8 |
| I3D+EvaNet[69] | RGB | 38.1 |
| I3D+GHRM[78] | RGB | 38.3 |
| I3D+UGPT[79] | RGB | 38.8 |
| I3D+NAS-TC(本文) | RGB | 39.3 (2.1↑) |
), ArticleFig(id=1327018563417780774, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=CN, label=表4, caption=
在Charades数据集上不同方法的性能比较
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 数据模态 | mAP/% |
|---|
| 注:括号内表示相对于I3D+Timeception,I3D+NAS-TC获得的性能增益;“↑”表示上升的百分点. |
| R-C3D[70] | RGB + Flow | 12.7 |
| Two-stream[61] | RGB + Flow | 18.6 |
| Two-stream+LSTM[61] | RGB + Flow | 17.8 |
| ActionVLAD[67] | RGB + iDT | 21.0 |
| TemporalFields[61] | RGB + Flow | 22.4 |
| TemporalRelations[57] | RGB | 25.2 |
| ResNet-152[61] | RGB | 22.8 |
| ResNet-152+Timeception[26] | RGB | 31.6 |
| 3D ResNet-101[60] | RGB | 35.5 |
| I3D+TAN[71] | RGB + Flow | 17.6 |
| I3D+Super-events[72] | RGB + Flow | 19.4 |
| I3D+TGM[73] | RGB + Flow | 21.5 |
| I3D+MLAD[74] | RGB + Flow | 23.7 |
| I3D+PDAN[75] | RGB + Flow | 26.5 |
| I3D+CTRN[76] | RGB + Flow | 27.8 |
| I3D+GCAN[77] | RGB + Flow | 27.7 |
| I3D[56] | RGB | 32.9 |
| I3D+ActionVLAD[67] | RGB | 35.4 |
| I3D+Timeception[26] | RGB | 37.2 |
| I3D-NL[60] | RGB | 37.5 |
| I3D+VideoGraph[68] | RGB | 37.8 |
| I3D+EvaNet[69] | RGB | 38.1 |
| I3D+GHRM[78] | RGB | 38.3 |
| I3D+UGPT[79] | RGB | 38.8 |
| I3D+NAS-TC(本文) | RGB | 39.3 (2.1↑) |
), ArticleFig(id=1327018563489083943, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=EN, label=Table 5, caption=
Performance Comparison of Different Methods on MultiTHUMOS Dataset, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 核大小$ k $ | 膨胀率$ d $ | mAP/% |
|---|
| 注:“-”表示不适用;括号内表示相比I3D+Timeception,I3D+NAS-TC获得的性能增益;“↑”表示上升的百分点. |
| Two-stream[61] | - | - | 27.60 |
| Two-stream+LSTM[61] | - | - | 28.10 |
| Muti-LSTM[61] | - | - | 29.60 |
| I3D+super-events[72] | - | - | 36.40 |
| I3D+super-events+TGMs[73] | - | - | 46.40 |
| I3D[56] | - | - | 72.43 |
| I3D+Timeception[26] | 3 | 1 | 72.83 |
| I3D+Timeception[26] | 3 | 1,2,3 | 74.52 |
| I3D+Timeception[26] | 1,3,5,7 | 1 | 74.79 |
| I3D+NAS-TC(本文) | 3,5,7 | 1,2 | 76.83 (2.04 ↑) |
), ArticleFig(id=1327018563560387112, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=CN, label=表5, caption=
在 MultiTHUMOS 数据集上不同方法的性能比较
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 核大小$ k $ | 膨胀率$ d $ | mAP/% |
|---|
| 注:“-”表示不适用;括号内表示相比I3D+Timeception,I3D+NAS-TC获得的性能增益;“↑”表示上升的百分点. |
| Two-stream[61] | - | - | 27.60 |
| Two-stream+LSTM[61] | - | - | 28.10 |
| Muti-LSTM[61] | - | - | 29.60 |
| I3D+super-events[72] | - | - | 36.40 |
| I3D+super-events+TGMs[73] | - | - | 46.40 |
| I3D[56] | - | - | 72.43 |
| I3D+Timeception[26] | 3 | 1 | 72.83 |
| I3D+Timeception[26] | 3 | 1,2,3 | 74.52 |
| I3D+Timeception[26] | 1,3,5,7 | 1 | 74.79 |
| I3D+NAS-TC(本文) | 3,5,7 | 1,2 | 76.83 (2.04 ↑) |
), ArticleFig(id=1327018563640078889, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=EN, label=Table 6, caption=
Performance Comparison of Different Methods on BreakfastActions Dataset, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | Activities Acc/% | Actions mAP/% |
|---|
| 注:括号内表示相对于I3D+Timeception,I3D+NAS-TC获得的性能增益;“↑”表示上升的百分点. |
| ResNet-152[61] | 41.13 | 32.65 |
| ResNet-152+ActionVLAD[67] | 55.49 | 47.12 |
| ResNet-152+Timeception[26] | 57.75 | 48.47 |
| ResNet-152+VideoGraph[68] | 59.12 | 49.38 |
| I3D[56] | 58.61 | 47.05 |
| I3D+ActionVLAD[67] | 65.48 | 60.20 |
| I3D+Timeception[26] | 67.07 | 61.82 |
| I3D+VideoGraph[68] | 69.45 | 63.14 |
| I3D+NAS-TC(本文) | 71.89 (4.82 ↑) | 64.64 (2.82 ↑) |
), ArticleFig(id=1327018563711382058, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018554244837828, language=CN, label=表6, caption=
不同方法在 BreakfastActions数据集上的性能比较
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | Activities Acc/% | Actions mAP/% |
|---|
| 注:括号内表示相对于I3D+Timeception,I3D+NAS-TC获得的性能增益;“↑”表示上升的百分点. |
| ResNet-152[61] | 41.13 | 32.65 |
| ResNet-152+ActionVLAD[67] | 55.49 | 47.12 |
| ResNet-152+Timeception[26] | 57.75 | 48.47 |
| ResNet-152+VideoGraph[68] | 59.12 | 49.38 |
| I3D[56] | 58.61 | 47.05 |
| I3D+ActionVLAD[67] | 65.48 | 60.20 |
| I3D+Timeception[26] | 67.07 | 61.82 |
| I3D+VideoGraph[68] | 69.45 | 63.14 |
| I3D+NAS-TC(本文) | 71.89 (4.82 ↑) | 64.64 (2.82 ↑) |
)], 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/issn1000-1239.202440048, detailUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202440048, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/PDF/10.7544/issn1000-1239.202440048, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/PDF/10.7544/issn1000-1239.202440048, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1753977600000, fullTextJson=null, articleText=null, reference=null)