Article(id=1329455949573633019, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1329455653363495339, articleNumber=null, orderNo=null, doi=10.7544/issn1000-1239.202220698, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1659888000000, receivedDateStr=2022-08-08, revisedDate=1678636800000, revisedDateStr=2023-03-13, acceptedDate=null, acceptedDateStr=null, onlineDate=1794896598475, onlineDateStr=2026-11-17, pubDate=1706803200000, pubDateStr=2024-02-02, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794896598475, onlineIssueDateStr=2026-11-17, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794896598475, creator=13701087609, updateTime=1794896598475, updator=13701087609, issue=Issue{id=1329455653363495339, tenantId=1146029695717560320, journalId=1324759914146529478, year='2024', volume='61', issue='2', pageStart='273', pageEnd='538', issueExtLink='null', onlineDate='null', pubDate='1706803200000', pubDateStr='2024-02-02', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794896527853, creator='13701087609', updateTime=1794896527853, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext=null, issueFiles=null, downloadFileDto=null}, startPage=460, endPage=469, ext={EN=ArticleExt(id=1329455949984674812, articleId=1329455949573633019, tenantId=1146029695717560320, journalId=1324759914146529478, language=EN, title=Mixing Tokens from Target and Search Regions for Visual Object Tracking, columnId=1329455694815802127, journalTitle=Journal of Computer Research and Development, columnName=Artificial Intelligence and Pattern Recognition, runingTitle=null, highlight=null, articleAbstract=

There are three problems about feature extraction and fusion in the current mainstream tracking framework based on Transformer: 1. The two modules of feature extraction and fusion are used separately, which is easy to produce sub-optimal model training results. 2. Computational complexity of $ O\left({N}^{2}\right) $ using self-attention reduces tracking efficiency. 3. The target template selection strategy is simple and is difficult to adapt to the drastic changes in the target appearance during the tracking process. We propose a novel Transformer tracking framework using fast Fourier transform mixing target tokens and search region tokens. For problem 1, an efficient end-to-end approach is proposed to extract and fuse features for unified learning to obtain optimal model; For problem 2, the fast Fourier transform is used to achieve complete information interaction between the target tokens and search region tokens. The computational complexity of this operation is $ O\left(N\mathrm{l}\mathrm{o}\mathrm{g}\left(N\right)\right) $, which greatly improves the tracing efficiency. For problem 3, a template memory storage mechanism based on quality assessment is proposed, which can quickly adapt to the drastic changes in target appearance. Compared with the current state-of-the-art algorithms on three datasets LaSOT, OTB100 and UAV123, our tracker achieves better performance in both efficiency and accuracy.

, authors=Wanli Xue1, Zhibin Zhang1, Shenglei Pei2, *, Kaihua Zhang3, Shengyong Chen1, authorsList=Wanli Xue, Zhibin Zhang, Shenglei Pei, Kaihua Zhang, Shengyong Chen, authorCompany=null, correspAuthors=Shenglei Pei, authorNote=

born in 1986. PhD, associate professor, master supervisor. Member of CCF and CSIG. His main research interests include visual tracking, sign language recognition, and image stitching

born in 1996. PhD candidate. His main research interests include visual object tracking and deep learning

born in 1980. PhD, professor, master supervisor. His main research interests include machine learning, data mining, and intelligent decision system

born in 1983. PhD, professor. His main research interests include video object segmentation and visual object tracking

born in 1973. PhD, professor. His main research interests include computer vision and machine learning

, correspAuthorsNote=null, copyrightStatement=Copyright © 2024 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=1329455953520472086, articleId=1329455949573633019, tenantId=1146029695717560320, journalId=1324759914146529478, language=CN, title=混合目标与搜索区域令牌的视觉目标跟踪, columnId=1329455694975185681, journalTitle=计算机研究与发展, columnName=人工智能和模式识别, runingTitle=null, highlight=null, articleAbstract=

当前基于Transformer的主流跟踪框架在特征提取及融合方面存在3个问题:1)分开进行特征提取与融合,易产生次优模型训练结果;2)使用计算复杂度为$ O\left({N}^{2}\right) $的自注意力机制会降低跟踪算法效率;3)简单的目标模板选取策略难以自适应跟踪过程中目标表观的剧烈变化. 为此,利用快速傅里叶变换对目标与搜索区域的令牌进行有效混合,提出一种新颖的基于Transformer的视觉目标跟踪方案. 针对问题1提出一种高效端到端方式将特征提取与融合进行统一学习以获得最优模型. 针对问题2采用快速傅里叶变换实现目标与搜索区域令牌之间的完全信息交互,该操作计算复杂度为$ O\left(N\mathrm{l}\mathrm{o}\mathrm{g}\left(N\right)\right) $,有助于提升跟踪效率. 针对问题3提出一种基于跟踪质量评估的目标模板记忆存储机制以快速自适应目标表观的剧烈变化. 在3个标准数据集LaSOT,OTB100,UAV123上,所提方法与当前最优方法相比在效率和精度上均取得更好表现.

, authors=薛万利1, 张智彬1, 裴生雷2, *, 张开华3, 陈胜勇1, authorsList=薛万利, 张智彬, 裴生雷, 张开华, 陈胜勇, authorCompany=null, correspAuthors=裴生雷, authorNote=

1986年生. 博士,副教授,硕士生导师. CCF与CSIG会员. 主要研究方向为目标跟踪、手语识别和图像拼接

1996年生. 博士研究生. 主要研究方向为视觉目标跟踪、深度学习

1980年生. 博士,教授,硕士生导师. 主要研究方向为机器学习、数据挖掘、智能决策系统

1983年生. 博士,教授. 主要研究方向为视频目标分割、视觉目标跟踪

1973年生. 博士,教授. 主要研究方向计算机视觉、机器学习

, correspAuthorsNote=
裴生雷()
, copyrightStatement=版权所有 © 2024 计算机研究与发展编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=tGkKHQGJHNvQdN+Ym6jY2g==, magXml=TzWNE05Qf59QyUvdYbhp6g==, pdfUrl=null, pdf=hVfiOJIAnuhoUTGS8lYSLA==, pdfFileSize=3609731, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=x3AznxKdZIgPqGVIAfb+Lw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=hVQX8/i6Y4oCnpHJyMb1KQ==, mapNumber=null, fund=null)}, authors=[Author(id=1329455954556465185, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=xuewanli@email.tjut.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329455954619379747, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, authorId=1329455954556465185, language=EN, stringName=Wanli Xue, firstName=Wanli, middleName=null, lastName=Xue, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Computer Science and Engineering, Tianjin University of Technology, Tianjin 300384, bio={"content":"

born in 1986. PhD, associate professor, master supervisor. Member of CCF and CSIG. His main research interests include visual tracking, sign language recognition, and image stitching

"}, bioImg=null, bioContent=

born in 1986. PhD, associate professor, master supervisor. Member of CCF and CSIG. His main research interests include visual tracking, sign language recognition, and image stitching

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329455954694877220, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, authorId=1329455954556465185, language=CN, stringName=薛万利, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1天津理工大学计算机科学与工程学院 天津 300384, bio={"img":"gXoQwvQt6H8oP4/VH4FrKw==","content":"

1986年生. 博士,副教授,硕士生导师. CCF与CSIG会员. 主要研究方向为目标跟踪、手语识别和图像拼接

"}, bioImg=gXoQwvQt6H8oP4/VH4FrKw==, bioContent=

1986年生. 博士,副教授,硕士生导师. CCF与CSIG会员. 主要研究方向为目标跟踪、手语识别和图像拼接

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329455953893765143, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, xref=1, ext=[AuthorCompanyExt(id=1329455953910542360, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, companyId=1329455953893765143, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science and Engineering, Tianjin University of Technology, Tianjin 300384), AuthorCompanyExt(id=1329455953923125273, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, companyId=1329455953893765143, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1天津理工大学计算机科学与工程学院 天津 300384)])]), Author(id=1329455954770374694, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, 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=1329455954845872168, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, authorId=1329455954770374694, language=EN, stringName=Zhibin Zhang, firstName=Zhibin, middleName=null, lastName=Zhang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Computer Science and Engineering, Tianjin University of Technology, Tianjin 300384, bio={"content":"

born in 1996. PhD candidate. His main research interests include visual object tracking and deep learning

"}, bioImg=null, bioContent=

born in 1996. PhD candidate. His main research interests include visual object tracking and deep learning

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329455955043004457, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, authorId=1329455954770374694, language=CN, stringName=张智彬, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1天津理工大学计算机科学与工程学院 天津 300384, bio={"img":"rKtriTHucvh6SqfbzYvekg==","content":"

1996年生. 博士研究生. 主要研究方向为视觉目标跟踪、深度学习

"}, bioImg=rKtriTHucvh6SqfbzYvekg==, bioContent=

1996年生. 博士研究生. 主要研究方向为视觉目标跟踪、深度学习

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329455953893765143, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, xref=1, ext=[AuthorCompanyExt(id=1329455953910542360, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, companyId=1329455953893765143, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science and Engineering, Tianjin University of Technology, Tianjin 300384), AuthorCompanyExt(id=1329455953923125273, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, companyId=1329455953893765143, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1天津理工大学计算机科学与工程学院 天津 300384)])]), Author(id=1329455955122696235, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=peishenglei@126.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1329455955189805101, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, authorId=1329455955122696235, language=EN, stringName=Shenglei Pei, firstName=Shenglei, middleName=null, lastName=Pei, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2College of Physics and Electronic Information Engineering, Qinghai Minzu University, Xining 810007, bio={"content":"

born in 1980. PhD, professor, master supervisor. His main research interests include machine learning, data mining, and intelligent decision system

"}, bioImg=null, bioContent=

born in 1980. PhD, professor, master supervisor. His main research interests include machine learning, data mining, and intelligent decision system

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329455955256913966, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, authorId=1329455955122696235, language=CN, stringName=裴生雷, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2青海民族大学物理与电子信息工程学院 西宁 810007, bio={"img":"RWSp4KIQEGPoVTp1uU5vxA==","content":"

1980年生. 博士,教授,硕士生导师. 主要研究方向为机器学习、数据挖掘、智能决策系统

"}, bioImg=RWSp4KIQEGPoVTp1uU5vxA==, bioContent=

1980年生. 博士,教授,硕士生导师. 主要研究方向为机器学习、数据挖掘、智能决策系统

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329455954178977818, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, xref=2, ext=[AuthorCompanyExt(id=1329455954183172123, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, companyId=1329455954178977818, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2College of Physics and Electronic Information Engineering, Qinghai Minzu University, Xining 810007), AuthorCompanyExt(id=1329455954195755036, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, companyId=1329455954178977818, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2青海民族大学物理与电子信息工程学院 西宁 810007)])]), Author(id=1329455955336605744, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, 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=1329455955416297522, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, authorId=1329455955336605744, language=EN, stringName=Kaihua Zhang, firstName=Kaihua, middleName=null, lastName=Zhang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3School of Computer Science, Nanjing University of Information Science & Technology, Nanjing 130012, bio={"content":"

born in 1983. PhD, professor. His main research interests include video object segmentation and visual object tracking

"}, bioImg=null, bioContent=

born in 1983. PhD, professor. His main research interests include video object segmentation and visual object tracking

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329455955529543731, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, authorId=1329455955336605744, language=CN, stringName=张开华, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3南京信息工程大学计算机学院 南京 130012, bio={"img":"bbVrQEwa3MQ4lWxO3nmZfQ==","content":"

1983年生. 博士,教授. 主要研究方向为视频目标分割、视觉目标跟踪

"}, bioImg=bbVrQEwa3MQ4lWxO3nmZfQ==, bioContent=

1983年生. 博士,教授. 主要研究方向为视频目标分割、视觉目标跟踪

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329455954447413277, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, xref=3, ext=[AuthorCompanyExt(id=1329455954455801886, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, companyId=1329455954447413277, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3School of Computer Science, Nanjing University of Information Science & Technology, Nanjing 130012), AuthorCompanyExt(id=1329455954464190495, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, companyId=1329455954447413277, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3南京信息工程大学计算机学院 南京 130012)])]), Author(id=1329455955596652597, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329455955667955767, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, authorId=1329455955596652597, language=EN, stringName=Shengyong Chen, firstName=Shengyong, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Computer Science and Engineering, Tianjin University of Technology, Tianjin 300384, bio={"content":"

born in 1973. PhD, professor. His main research interests include computer vision and machine learning

"}, bioImg=null, bioContent=

born in 1973. PhD, professor. His main research interests include computer vision and machine learning

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329455955810562104, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, authorId=1329455955596652597, language=CN, stringName=陈胜勇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1天津理工大学计算机科学与工程学院 天津 300384, bio={"img":"YOGCLw/AjskWxHKlqERRRQ==","content":"

1973年生. 博士,教授. 主要研究方向计算机视觉、机器学习

"}, bioImg=YOGCLw/AjskWxHKlqERRRQ==, bioContent=

1973年生. 博士,教授. 主要研究方向计算机视觉、机器学习

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329455953893765143, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, xref=1, ext=[AuthorCompanyExt(id=1329455953910542360, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, companyId=1329455953893765143, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science and Engineering, Tianjin University of Technology, Tianjin 300384), AuthorCompanyExt(id=1329455953923125273, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, companyId=1329455953893765143, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1天津理工大学计算机科学与工程学院 天津 300384)])])], keywords=[Keyword(id=1329455956020277305, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=EN, orderNo=1, keyword=Transformer), Keyword(id=1329455956141912122, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=EN, orderNo=2, keyword=fast Fourier transform), Keyword(id=1329455956284518460, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=EN, orderNo=3, keyword=feature extraction), Keyword(id=1329455956406153277, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=EN, orderNo=4, keyword=feature fusion), Keyword(id=1329455956494233662, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=EN, orderNo=5, keyword=object tracking), Keyword(id=1329455956611674175, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=CN, orderNo=1, keyword=Transformer), Keyword(id=1329455956695560256, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=CN, orderNo=2, keyword=快速傅里叶变换), Keyword(id=1329455956771057729, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=CN, orderNo=3, keyword=特征提取), Keyword(id=1329455956859138115, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=CN, orderNo=4, keyword=特征融合), Keyword(id=1329455956947218500, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=CN, orderNo=5, keyword=目标跟踪)], refs=[Reference(id=1329455960575291483, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, 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=李玺,查宇飞,张天柱,等. 深度学习的目标跟踪算法综述[J]. 中国图象图形学报,2019,24(12):2057−2080, articleTitle=null, refAbstract=null), Reference(id=1329455960642400348, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Xi, Cha Yufei, Zhang Tianzhu, et al. Survey of visual object tracking algorithms based on deep learning[J]. Journal of Image and Graphics, 2019, 24(12): 2057−2080 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329455960709509213, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=柳培忠,汪鸿翔,骆炎民,等. 一种结合时空上下文的在线卷积网络跟踪算法[J]. 计算机研究与发展,2018,55(12):2785−2793, articleTitle=null, refAbstract=null), Reference(id=1329455960772423774, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Peizhong, Wang Hongxiang, Luo Yanmin, et al. Visual tracking algorithm based on adaptive spatial regularization[J]. Journal of Computer Research and Development, 2018, 55(12): 2785−2793 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329455960847921247, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=Rao Yongming, Zhao Wenliang, Zhu Zheng, et al. Global filter networks for image classification[C] //Proc of the 35th Advances in Neural Information Processing Systems. Cambridge, MA: MIT, 2021: 980−993, articleTitle=null, refAbstract=null), Reference(id=1329455960940195936, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Zhipeng, Peng Houwen. Deeper and wider Siamese networks for real-time visual tracking[C] //Proc of the 32nd IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 4591−4600, articleTitle=null, refAbstract=null), Reference(id=1329455961007304801, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Bo, Wu Wei, Wang Qiang, et al. Evolution of Siamese visual tracking with very deep networks[C] //Proc of the 32nd IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 16−20, articleTitle=null, refAbstract=null), Reference(id=1329455961128939618, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Bo, Yan Junjie, Wu Wei, et al. High performance visual tracking with Siamese region proposal network[C] //Proc of the 31st IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 8971−8980, articleTitle=null, refAbstract=null), Reference(id=1329455961187659875, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=Bertinetto L, Valmadre J, Henriques J F, et al. Fully-convolutional siamese networks for object tracking[C] //Proc of the 14th European Conf on Computer Vision. Berlin: Springer, 2016: 850−865, articleTitle=null, refAbstract=null), Reference(id=1329455961263157348, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Bhat G, Danelljan M, Gool L V, et al. Learning discriminative model prediction for tracking[C] //Proc of the 17th IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2019: 6182−6191, articleTitle=null, refAbstract=null), Reference(id=1329455961321877605, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=Danelljan M, Gool L V, Timofte R. Probabilistic regression for visual tracking[C] //Proc of the 33rd IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2020: 7183−7192, articleTitle=null, refAbstract=null), Reference(id=1329455961380597862, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Danelljan M, Bhat G, Khan F S, et al. Atom: Accurate tracking by overlap maximization[C] //Proc of the 32nd IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 4660−4669, articleTitle=null, refAbstract=null), Reference(id=1329455961447706727, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=Yan Bin, Peng Houwen, Fu Jianlong, et al. Learning spatio-temporal transformer for visual tracking[C] //Proc of the 18th IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2021: 10448-10457, articleTitle=null, refAbstract=null), Reference(id=1329455961510621288, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Xin, Yan Bin, Zhu Jiawen, et al. Transformer tracking[C] //Proc of the 34th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 8126−8135, articleTitle=null, refAbstract=null), Reference(id=1329455961581924457, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Ning, Zhou Wengang, Wang Jie, et al. Transformer meets tracker: Exploiting temporal context for robust visual tracking[C] //Proc of the 34th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 1571−1580, articleTitle=null, refAbstract=null), Reference(id=1329455961644839018, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin Liting, Fan Heng, Xu Yong, et al. SwinTrack: A simple and strong baseline for transformer tracking[J]. arXiv preprint, arXiv: 2112. 00995, 2021, articleTitle=null, refAbstract=null), Reference(id=1329455961711947883, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Cui Yutao, Cheng Jiang, Wang Liming, et al. Mixformer: End-to-end tracking with iterative mixed attention[C] //Proc of the 35th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 13608−13618, articleTitle=null, refAbstract=null), Reference(id=1329455961774862444, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Tolstikhin I, Houlsby N, Kolesnikov A, et al. MLP-mixer: An all-MLP architecture for vision[J]. arXiv preprint, arXiv: 2105. 01601, 2021, articleTitle=null, refAbstract=null), Reference(id=1329455961837777005, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Touvron H, Bojanowski P, Caron M, et al. ResMLP: Feedforward networks for image classification with data-efficient training[J]. arXiv preprint, arXiv: 2105. 03404, 2021, articleTitle=null, refAbstract=null), Reference(id=1329455961896497262, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Fan Heng, Lin Liting, Yang Fan, et al. LaSOT: A high-quality benchmark for large-scale single object tracking[C] //Proc of the 32nd IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 5374−5383, articleTitle=null, refAbstract=null), Reference(id=1329455961980383343, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Yi, Lim J, Yang Ming-Hsuan. Online object tracking: A benchmark[C] //Proc of the 26th IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2013: 2411−2418, articleTitle=null, refAbstract=null), Reference(id=1329455962068463728, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Mueller M, Smith N, Ghanem B. A benchmark and simulator for UAV tracking[C] //Proc of the 14th European Conf on Computer Vision. Berlin: Springer, 2016: 445−461, articleTitle=null, refAbstract=null), Reference(id=1329455962164932721, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=Guo Qing, Feng Wei, Zhou Ce, et al. Learning dynamic siamese network for visual object tracking[C] //Proc of the 16th IEEE Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2017: 1763−1771, articleTitle=null, refAbstract=null), Reference(id=1329455962236235890, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Ze, Lin Yutong, Cao Yue, et al. Swin Transformer: hierarchical vision transformer using shifted windows[C] // Proc of the 18th IEEE Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2021: 10012−10022, articleTitle=null, refAbstract=null), Reference(id=1329455962320121971, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16x16 words: Transformers for image recognition at scale[J]. arXiv preprint, arXiv: 2010. 11929, 2020, articleTitle=null, refAbstract=null), Reference(id=1329455962404008052, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Haiping, Xiao Bin, Codella N, et al. CVT: Introducing convolutions to vision transformers[C] // Proc of the 18th IEEE Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2021: 22-31, articleTitle=null, refAbstract=null), Reference(id=1329455962466922613, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Deep residual learning for image recognition[C] //Proc of the 29th IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2016: 770−778, articleTitle=null, refAbstract=null), Reference(id=1329455962534031478, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Mayer C, Danelljan M, Bhat G, et al. Transforming model prediction for tracking[J]. arXiv preprint, arXiv: 2203. 11192, 2022, articleTitle=null, refAbstract=null), Reference(id=1329455962605334647, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Hanxiao, Dai Zihang, So D, et al. Pay attention to MLPs[C] //Proc of the 35th Advances in Neural Information Processing Systems. Cambridge, MA: MIT, 2021: 9204−9215, articleTitle=null, refAbstract=null), Reference(id=1329455962668249208, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Bolme D S, Beveridge J R, Draper B A, et al. Visual object tracking using adaptive correlation filters[C] //Proc of the 23rd IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2010: 2544−2550, articleTitle=null, refAbstract=null), Reference(id=1329455962739552377, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Mengmeng, Liu Yong, Huang Zeyi. Large margin object tracking with circulant feature maps[C] //Proc of the 30th IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 4021−4029, articleTitle=null, refAbstract=null), Reference(id=1329455962819244154, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang Lianghua, Zhao Xin, Huang Kaiqi. GOT-10k: A large high-diversity benchmark for generic object tracking in the wild[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 43(5): 1562−1577, articleTitle=null, refAbstract=null), Reference(id=1329455962882158715, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Muller M, Bibi A, Giancola S, et al. TrackingNet: A large-scale dataset and benchmark for object tracking in the wild[C] //Proc of the 15th European Conf on Computer Vision. Berlin: Springer, 2018: 300−317, articleTitle=null, refAbstract=null), Reference(id=1329455962945073276, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Kingma D P, Jimmy B. Adam: A method for stochastic optimization[J]. arXiv preprint, arXiv: 1412. 6980, 2014, articleTitle=null, refAbstract=null), Reference(id=1329455963003793533, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=Yan Bin, Zhang Xinyu, Wang Dong, et al. Alpha-Refine: Boosting tracking performance by precise bounding box estimation[C] //Proc of the 34th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 5289−5298, articleTitle=null, refAbstract=null), Reference(id=1329455963083485310, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=Voigtlaender P, Luiten J, Torr P H S, et al. SiamR-CNN: Visual tracking by re-detection[C] //Proc of the 33rd IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2020: 6578−6588, articleTitle=null, refAbstract=null), Reference(id=1329455963154788479, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=Guo Dongyan, Shao Yanyan, Cui Ying, et al. Graph attention tracking[C] //Proc of the 34th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 9543−9552, articleTitle=null, refAbstract=null), Reference(id=1329455964794761344, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Zedu, Zhong Bineng, Li Guorong, et al. Siamese box adaptive network for visual tracking[C] //Proc of the 33rd IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2020: 6668−6677, articleTitle=null, refAbstract=null), Reference(id=1329455964866064513, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=Danelljan M, Bhat G, Shahbaz K F, et al. ECO: Efficient convolution operators for tracking[C] //Proc of the 30th IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 6638−6646, articleTitle=null, refAbstract=null), Reference(id=1329455964941561986, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=38, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=Nam H, Han B. Learning multi-domain convolutional neural networks for visual tracking[C] //Proc of the 29th IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2016: 4293−4302, articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1329455953893765143, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, xref=1, ext=[AuthorCompanyExt(id=1329455953910542360, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, companyId=1329455953893765143, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science and Engineering, Tianjin University of Technology, Tianjin 300384), AuthorCompanyExt(id=1329455953923125273, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, companyId=1329455953893765143, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1天津理工大学计算机科学与工程学院 天津 300384)]), AuthorCompany(id=1329455954178977818, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, xref=2, ext=[AuthorCompanyExt(id=1329455954183172123, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, companyId=1329455954178977818, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2College of Physics and Electronic Information Engineering, Qinghai Minzu University, Xining 810007), AuthorCompanyExt(id=1329455954195755036, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, companyId=1329455954178977818, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2青海民族大学物理与电子信息工程学院 西宁 810007)]), AuthorCompany(id=1329455954447413277, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, xref=3, ext=[AuthorCompanyExt(id=1329455954455801886, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, companyId=1329455954447413277, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3School of Computer Science, Nanjing University of Information Science & Technology, Nanjing 130012), AuthorCompanyExt(id=1329455954464190495, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, companyId=1329455954447413277, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3南京信息工程大学计算机学院 南京 130012)])], figs=[ArticleFig(id=1329455957085630533, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=EN, label=Figure 1, caption=The tracking algorithm framework proposed in our paper, figureFileSmall=CS4HJp6ej2VrJA8uCDLjsA==, figureFileBig=x3AznxKdZIgPqGVIAfb+Lw==, tableContent=null), ArticleFig(id=1329455957211459654, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=CN, label=图1, caption=本文所提跟踪算法框架, figureFileSmall=CS4HJp6ej2VrJA8uCDLjsA==, figureFileBig=x3AznxKdZIgPqGVIAfb+Lw==, tableContent=null), ArticleFig(id=1329455957404397639, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=EN, label=Figure 2, caption=Structure diagram of FFT tokens fusion network, figureFileSmall=VVedZ1sYIV2rp1iv8npAVA==, figureFileBig=QiAr94ckO/0WhOnmWy85tw==, tableContent=null), ArticleFig(id=1329455957467312200, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=CN, label=图2, caption=FFT令牌融合网络结构图, figureFileSmall=VVedZ1sYIV2rp1iv8npAVA==, figureFileBig=QiAr94ckO/0WhOnmWy85tw==, tableContent=null), ArticleFig(id=1329455957538615369, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=EN, label=Figure 3, caption=Visualization of template memory storage algorithm based on quality assessment, figureFileSmall=C0BjxXUv4wbSRj88+VVhmA==, figureFileBig=QSuh4B1AohB5z3jMJw3rwQ==, tableContent=null), ArticleFig(id=1329455957618307146, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=CN, label=图3, caption=基于质量评估的模板记忆存储算法的可视化, figureFileSmall=C0BjxXUv4wbSRj88+VVhmA==, figureFileBig=QSuh4B1AohB5z3jMJw3rwQ==, tableContent=null), ArticleFig(id=1329455957685416011, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=EN, label=Figure 4, caption=Comparison of success ratio and precision plot in our algorithm and other state-of-the-art algorithms on LaSOT dataset, figureFileSmall=361DXSvl5T/Tt1NItU457w==, figureFileBig=tJP1Ocm49ZcUSaZp5fRmYA==, tableContent=null), ArticleFig(id=1329455957760913484, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=CN, label=图4, caption=本文算法与其他最先进算法在LaSOT数据集上的成功率指标与精度图比较, figureFileSmall=361DXSvl5T/Tt1NItU457w==, figureFileBig=tJP1Ocm49ZcUSaZp5fRmYA==, tableContent=null), ArticleFig(id=1329455957840605261, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=EN, label=Figure 5, caption=Score comparison of the indictors in success ratio and precision plot for different challenges on LaSOT dataset, figureFileSmall=VpOdevTENcxM2zBmitmjFA==, figureFileBig=22lutZfb0+rOVtgT3Thefg==, tableContent=null), ArticleFig(id=1329455957924491342, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=CN, label=图5, caption=LaSOT数据集上不同挑战的成功率指标和精度图指标得分比较, figureFileSmall=VpOdevTENcxM2zBmitmjFA==, figureFileBig=22lutZfb0+rOVtgT3Thefg==, tableContent=null), ArticleFig(id=1329455958050320463, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=EN, label=Figure 6, caption=Comparison of the success ratio and precision plot in our algorithm and other state-of-the-art algorithms on OTB100 dataset, figureFileSmall=FWEJz1csfnGDrxd2qSwECA==, figureFileBig=cTLWufQJ37kvCErIUCSQrg==, tableContent=null), ArticleFig(id=1329455958117429328, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=CN, label=图6, caption=本文算法与其他最先进算法在OTB100数据集上的成功率与精度图比较, figureFileSmall=FWEJz1csfnGDrxd2qSwECA==, figureFileBig=cTLWufQJ37kvCErIUCSQrg==, tableContent=null), ArticleFig(id=1329455958171955281, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=EN, label=Figure 7, caption=Tracking results of bird-17 video sequence in LaSOT dataset, figureFileSmall=cgg5vEOmXUsut7nHBSlSfg==, figureFileBig=2Y/kzE6VY9cmqbG+btzfCg==, tableContent=null), ArticleFig(id=1329455958251647058, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=CN, label=图7, caption=LaSOT数据集中bird-17视频序列中的跟踪结果, figureFileSmall=cgg5vEOmXUsut7nHBSlSfg==, figureFileBig=2Y/kzE6VY9cmqbG+btzfCg==, tableContent=null), ArticleFig(id=1329455958314561619, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=EN, label=Figure 8, caption=Tracking results of bicycle-18 video sequence in LaSOT dataset, figureFileSmall=Ynt60brdxeM+35budCJuvg==, figureFileBig=M8xaNGC6KlSOcE1g6JhHXQ==, tableContent=null), ArticleFig(id=1329455958377476180, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=CN, label=图8, caption=LaSOT数据集中bicycle-18视频序列中的跟踪结果, figureFileSmall=Ynt60brdxeM+35budCJuvg==, figureFileBig=M8xaNGC6KlSOcE1g6JhHXQ==, tableContent=null), ArticleFig(id=1329455958440390741, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=EN, label=Table 1, caption=

Comparison of Our Algorithm and Other State-of-the-art Algorithms on UAV123 Dataset

, figureFileSmall=null, figureFileBig=null, tableContent=
算法AUC精度图
本文算法0.7020.877
TransT0.6910.864
PrDiMP0.6900.867
TrDiMP0.6800.852
DiMP0.6620.838
SiamBAN0.6500.820
SiamR-CNN0.6490.834
SiamGAT0.6460.843
SiamRPN++0.6100.803
), ArticleFig(id=1329455958524276822, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=CN, label=表1, caption=

本文算法与其他先进算法在UAV123数据集上的比较

, figureFileSmall=null, figureFileBig=null, tableContent=
算法AUC精度图
本文算法0.7020.877
TransT0.6910.864
PrDiMP0.6900.867
TrDiMP0.6800.852
DiMP0.6620.838
SiamBAN0.6500.820
SiamR-CNN0.6490.834
SiamGAT0.6460.843
SiamRPN++0.6100.803
), ArticleFig(id=1329455958603968599, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=EN, label=Table 2, caption=

Results of the Ablation Experiments of Our Proposed algorithm on LaSOT Dataset

, figureFileSmall=null, figureFileBig=null, tableContent=
模型变体基于CNN
的融合
基于FFT
的融合
记忆存
储机制
成功率精度图平均跟踪
速度/fps
变体1√0.6480.68423
变体2√0.6610.70941
变体3√√0.6670.72334
), ArticleFig(id=1329455960264912984, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=CN, label=表2, caption=

在LaSOT数据集上本文算法的消融实验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
模型变体基于CNN
的融合
基于FFT
的融合
记忆存
储机制
成功率精度图平均跟踪
速度/fps
变体1√0.6480.68423
变体2√0.6610.70941
变体3√√0.6670.72334
), ArticleFig(id=1329455960386547801, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=EN, label=Table 3, caption=

Comparative Experimental Results of Reasoning Speed on LaSOT Dataset

, figureFileSmall=null, figureFileBig=null, tableContent=
方法出处成功率精度图平均跟踪速度/fps
TrDiMPCVPR210.6400.66626
MixformerCVPR220.6920.74725
本文算法0.6670.72334
), ArticleFig(id=1329455960462045274, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, language=CN, label=表3, caption=

LaSOT数据集上推理速度的对比实验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
方法出处成功率精度图平均跟踪速度/fps
TrDiMPCVPR210.6400.66626
MixformerCVPR220.6920.74725
本文算法0.6670.72334
)], 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/issn1000-1239.202220698, detailUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202220698, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/PDF/10.7544/issn1000-1239.202220698, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/PDF/10.7544/issn1000-1239.202220698, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1706803200000, fullTextJson=null, articleText=null, reference=null)
收藏切换
混合目标与搜索区域令牌的视觉目标跟踪
薛万利 1 , 张智彬 1 , 裴生雷 2, * , 张开华 3 , 陈胜勇 1
计算机研究与发展 | 人工智能和模式识别 2024,61(2): 460-469
收起
收藏切换
计算机研究与发展 |人工智能和模式识别 2024 , 61 (2) : 460 -469
混合目标与搜索区域令牌的视觉目标跟踪
全屏
[Author(id=1329455954556465185, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=xuewanli@email.tjut.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329455954619379747, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, authorId=1329455954556465185, language=EN, stringName=Wanli Xue, firstName=Wanli, middleName=null, lastName=Xue, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Computer Science and Engineering, Tianjin University of Technology, Tianjin 300384, bio={"content":"

born in 1986. PhD, associate professor, master supervisor. Member of CCF and CSIG. His main research interests include visual tracking, sign language recognition, and image stitching

"}, bioImg=null, bioContent=

born in 1986. PhD, associate professor, master supervisor. Member of CCF and CSIG. His main research interests include visual tracking, sign language recognition, and image stitching

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329455954694877220, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, authorId=1329455954556465185, language=CN, stringName=薛万利, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1天津理工大学计算机科学与工程学院 天津 300384, bio={"img":"gXoQwvQt6H8oP4/VH4FrKw==","content":"

1986年生. 博士,副教授,硕士生导师. CCF与CSIG会员. 主要研究方向为目标跟踪、手语识别和图像拼接

"}, bioImg=gXoQwvQt6H8oP4/VH4FrKw==, bioContent=

1986年生. 博士,副教授,硕士生导师. CCF与CSIG会员. 主要研究方向为目标跟踪、手语识别和图像拼接

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329455953893765143, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, xref=1, ext=[AuthorCompanyExt(id=1329455953910542360, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, companyId=1329455953893765143, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science and Engineering, Tianjin University of Technology, Tianjin 300384), AuthorCompanyExt(id=1329455953923125273, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, companyId=1329455953893765143, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1天津理工大学计算机科学与工程学院 天津 300384)])]), Author(id=1329455954770374694, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, 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=1329455954845872168, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, authorId=1329455954770374694, language=EN, stringName=Zhibin Zhang, firstName=Zhibin, middleName=null, lastName=Zhang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Computer Science and Engineering, Tianjin University of Technology, Tianjin 300384, bio={"content":"

born in 1996. PhD candidate. His main research interests include visual object tracking and deep learning

"}, bioImg=null, bioContent=

born in 1996. PhD candidate. His main research interests include visual object tracking and deep learning

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329455955043004457, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, authorId=1329455954770374694, language=CN, stringName=张智彬, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1天津理工大学计算机科学与工程学院 天津 300384, bio={"img":"rKtriTHucvh6SqfbzYvekg==","content":"

1996年生. 博士研究生. 主要研究方向为视觉目标跟踪、深度学习

"}, bioImg=rKtriTHucvh6SqfbzYvekg==, bioContent=

1996年生. 博士研究生. 主要研究方向为视觉目标跟踪、深度学习

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329455953893765143, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, xref=1, ext=[AuthorCompanyExt(id=1329455953910542360, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, companyId=1329455953893765143, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science and Engineering, Tianjin University of Technology, Tianjin 300384), AuthorCompanyExt(id=1329455953923125273, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, companyId=1329455953893765143, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1天津理工大学计算机科学与工程学院 天津 300384)])]), Author(id=1329455955122696235, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=peishenglei@126.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1329455955189805101, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, authorId=1329455955122696235, language=EN, stringName=Shenglei Pei, firstName=Shenglei, middleName=null, lastName=Pei, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2College of Physics and Electronic Information Engineering, Qinghai Minzu University, Xining 810007, bio={"content":"

born in 1980. PhD, professor, master supervisor. His main research interests include machine learning, data mining, and intelligent decision system

"}, bioImg=null, bioContent=

born in 1980. PhD, professor, master supervisor. His main research interests include machine learning, data mining, and intelligent decision system

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329455955256913966, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, authorId=1329455955122696235, language=CN, stringName=裴生雷, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2青海民族大学物理与电子信息工程学院 西宁 810007, bio={"img":"RWSp4KIQEGPoVTp1uU5vxA==","content":"

1980年生. 博士,教授,硕士生导师. 主要研究方向为机器学习、数据挖掘、智能决策系统

"}, bioImg=RWSp4KIQEGPoVTp1uU5vxA==, bioContent=

1980年生. 博士,教授,硕士生导师. 主要研究方向为机器学习、数据挖掘、智能决策系统

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329455954178977818, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, xref=2, ext=[AuthorCompanyExt(id=1329455954183172123, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, companyId=1329455954178977818, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2College of Physics and Electronic Information Engineering, Qinghai Minzu University, Xining 810007), AuthorCompanyExt(id=1329455954195755036, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, companyId=1329455954178977818, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2青海民族大学物理与电子信息工程学院 西宁 810007)])]), Author(id=1329455955336605744, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, 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=1329455955416297522, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, authorId=1329455955336605744, language=EN, stringName=Kaihua Zhang, firstName=Kaihua, middleName=null, lastName=Zhang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3School of Computer Science, Nanjing University of Information Science & Technology, Nanjing 130012, bio={"content":"

born in 1983. PhD, professor. His main research interests include video object segmentation and visual object tracking

"}, bioImg=null, bioContent=

born in 1983. PhD, professor. His main research interests include video object segmentation and visual object tracking

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329455955529543731, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, authorId=1329455955336605744, language=CN, stringName=张开华, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3南京信息工程大学计算机学院 南京 130012, bio={"img":"bbVrQEwa3MQ4lWxO3nmZfQ==","content":"

1983年生. 博士,教授. 主要研究方向为视频目标分割、视觉目标跟踪

"}, bioImg=bbVrQEwa3MQ4lWxO3nmZfQ==, bioContent=

1983年生. 博士,教授. 主要研究方向为视频目标分割、视觉目标跟踪

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329455954447413277, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, xref=3, ext=[AuthorCompanyExt(id=1329455954455801886, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, companyId=1329455954447413277, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3School of Computer Science, Nanjing University of Information Science & Technology, Nanjing 130012), AuthorCompanyExt(id=1329455954464190495, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, companyId=1329455954447413277, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3南京信息工程大学计算机学院 南京 130012)])]), Author(id=1329455955596652597, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329455955667955767, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, authorId=1329455955596652597, language=EN, stringName=Shengyong Chen, firstName=Shengyong, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Computer Science and Engineering, Tianjin University of Technology, Tianjin 300384, bio={"content":"

born in 1973. PhD, professor. His main research interests include computer vision and machine learning

"}, bioImg=null, bioContent=

born in 1973. PhD, professor. His main research interests include computer vision and machine learning

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329455955810562104, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, authorId=1329455955596652597, language=CN, stringName=陈胜勇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1天津理工大学计算机科学与工程学院 天津 300384, bio={"img":"YOGCLw/AjskWxHKlqERRRQ==","content":"

1973年生. 博士,教授. 主要研究方向计算机视觉、机器学习

"}, bioImg=YOGCLw/AjskWxHKlqERRRQ==, bioContent=

1973年生. 博士,教授. 主要研究方向计算机视觉、机器学习

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329455953893765143, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, xref=1, ext=[AuthorCompanyExt(id=1329455953910542360, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, companyId=1329455953893765143, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science and Engineering, Tianjin University of Technology, Tianjin 300384), AuthorCompanyExt(id=1329455953923125273, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329455949573633019, companyId=1329455953893765143, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1天津理工大学计算机科学与工程学院 天津 300384)])])]
薛万利1 , 张智彬1, 裴生雷2, * , 张开华3, 陈胜勇1
作者信息
  • 1天津理工大学计算机科学与工程学院 天津 300384
  • 2青海民族大学物理与电子信息工程学院 西宁 810007
  • 3南京信息工程大学计算机学院 南京 130012
通讯作者:
裴生雷()
作者简介:

1986年生. 博士,副教授,硕士生导师. CCF与CSIG会员. 主要研究方向为目标跟踪、手语识别和图像拼接

1996年生. 博士研究生. 主要研究方向为视觉目标跟踪、深度学习

1980年生. 博士,教授,硕士生导师. 主要研究方向为机器学习、数据挖掘、智能决策系统

1983年生. 博士,教授. 主要研究方向为视频目标分割、视觉目标跟踪

1973年生. 博士,教授. 主要研究方向计算机视觉、机器学习

Mixing Tokens from Target and Search Regions for Visual Object Tracking
Wanli Xue1 , Zhibin Zhang1, Shenglei Pei2, * , Kaihua Zhang3, Shengyong Chen1
Affiliations
  • 1School of Computer Science and Engineering, Tianjin University of Technology, Tianjin 300384
  • 2College of Physics and Electronic Information Engineering, Qinghai Minzu University, Xining 810007
  • 3School of Computer Science, Nanjing University of Information Science & Technology, Nanjing 130012
  • born in 1986. PhD, associate professor, master supervisor. Member of CCF and CSIG. His main research interests include visual tracking, sign language recognition, and image stitching

    born in 1996. PhD candidate. His main research interests include visual object tracking and deep learning

    born in 1980. PhD, professor, master supervisor. His main research interests include machine learning, data mining, and intelligent decision system

    born in 1983. PhD, professor. His main research interests include video object segmentation and visual object tracking

    born in 1973. PhD, professor. His main research interests include computer vision and machine learning

出版时间: 2024-02-02 doi: 10.7544/issn1000-1239.202220698
文章导航
收藏切换

当前基于Transformer的主流跟踪框架在特征提取及融合方面存在3个问题:1)分开进行特征提取与融合,易产生次优模型训练结果;2)使用计算复杂度为$ O\left({N}^{2}\right) $的自注意力机制会降低跟踪算法效率;3)简单的目标模板选取策略难以自适应跟踪过程中目标表观的剧烈变化. 为此,利用快速傅里叶变换对目标与搜索区域的令牌进行有效混合,提出一种新颖的基于Transformer的视觉目标跟踪方案. 针对问题1提出一种高效端到端方式将特征提取与融合进行统一学习以获得最优模型. 针对问题2采用快速傅里叶变换实现目标与搜索区域令牌之间的完全信息交互,该操作计算复杂度为$ O\left(N\mathrm{l}\mathrm{o}\mathrm{g}\left(N\right)\right) $,有助于提升跟踪效率. 针对问题3提出一种基于跟踪质量评估的目标模板记忆存储机制以快速自适应目标表观的剧烈变化. 在3个标准数据集LaSOT,OTB100,UAV123上,所提方法与当前最优方法相比在效率和精度上均取得更好表现.

Transformer  /  快速傅里叶变换  /  特征提取  /  特征融合  /  目标跟踪

There are three problems about feature extraction and fusion in the current mainstream tracking framework based on Transformer: 1. The two modules of feature extraction and fusion are used separately, which is easy to produce sub-optimal model training results. 2. Computational complexity of $ O\left({N}^{2}\right) $ using self-attention reduces tracking efficiency. 3. The target template selection strategy is simple and is difficult to adapt to the drastic changes in the target appearance during the tracking process. We propose a novel Transformer tracking framework using fast Fourier transform mixing target tokens and search region tokens. For problem 1, an efficient end-to-end approach is proposed to extract and fuse features for unified learning to obtain optimal model; For problem 2, the fast Fourier transform is used to achieve complete information interaction between the target tokens and search region tokens. The computational complexity of this operation is $ O\left(N\mathrm{l}\mathrm{o}\mathrm{g}\left(N\right)\right) $, which greatly improves the tracing efficiency. For problem 3, a template memory storage mechanism based on quality assessment is proposed, which can quickly adapt to the drastic changes in target appearance. Compared with the current state-of-the-art algorithms on three datasets LaSOT, OTB100 and UAV123, our tracker achieves better performance in both efficiency and accuracy.

Transformer  /  fast Fourier transform  /  feature extraction  /  feature fusion  /  object tracking
薛万利, 张智彬, 裴生雷, 张开华, 陈胜勇. 混合目标与搜索区域令牌的视觉目标跟踪. 计算机研究与发展, 2024 , 61 (2) : 460 -469 . DOI: 10.7544/issn1000-1239.202220698
Wanli Xue, Zhibin Zhang, Shenglei Pei, Kaihua Zhang, Shengyong Chen. Mixing Tokens from Target and Search Regions for Visual Object Tracking[J]. Journal of Computer Research and Development, 2024 , 61 (2) : 460 -469 . DOI: 10.7544/issn1000-1239.202220698
视觉目标跟踪是计算机视觉的重要研究方向[1]. 其研究任务是在视频序列首帧中给定任意目标,并在后续视频序列中持续预测目标位置. 目标跟踪被广泛应用于无人驾驶、智能视频监控、人机交互等领域[2]. 如何设计简单、高效的通用视觉目标跟踪方法是一个亟需解决的难题. 尤其在真实复杂场景中,目标表观受光照影响、尺寸变化、严重遮挡等挑战,会产生持续的剧烈变化,从而影响跟踪结果.
近些年,基于卷积神经网络(convolutional neural network, CNN)的目标跟踪获得广泛关注. 然而受限于感受野规模,CNN更多用于处理目标在时间域或空间域的局部特征,未能有效捕获目标特征之间的长期依赖关系[3]. 当前基于CNN的主流跟踪框架主要包括:基于孪生网络(siamese network)[4-7]的目标跟踪和基于在线学习判别式模型[8-10]的目标跟踪. 这些方法在获取图像局部特征时表现优异,但在复杂场景中,如目标被频繁遮挡或出现剧烈形变时,则不能很好地建模特征的全局上下文关系.
此外,基于Transformer的跟踪方案通过引入全局自注意力(self-attention)机制获取特征间长期依赖关系[11-13]. 在此类方案中,多数跟踪方法采用CNN作为主干网络对图像进行特征提取,随后利用Transformer设计编码器和解码器. 文献[14-15]专注简化跟踪步骤,将Transformer作为特征提取器并直接输出预测位置. 然而,此类跟踪方案中起核心作用的自注意力机制,由于其计算复杂度为$ O\left({N}^{2}\right) $,使得其随图像大小增加导致计算量陡增,并直接影响目标跟踪效率.
为了降低计算量,一些研究采用视觉多层感知器(multi-layer perceptron,MLP)来构建主干网络[16-17]. 这些研究使用MLP层代替Transformer中的自注意力层,并在时域进行令牌(token)间信息交互,所谓令牌即目标和搜索区域对应的样本被切分成若干个不重叠的图像块. 令牌间的信息交互进一步简化时域信息的融合操作. MLP的引入降低了计算复杂度,但是在训练和测试中随着令牌数量增加,会显著加大MLP计算量,同样会影响目标跟踪效率.
受全局滤波网络设计启发[3],本文提出利用快速傅里叶变换(fast Fourier transform, FFT)对令牌进行高效融合,以降低视觉MLP模型在令牌数量增加时产生的计算开销. 首先,利用FFT将令牌时域特征转变为频域特征. 随后,在频域空间中捕获目标当前信息及其历史信息与搜索区域信息间的长程依赖关系. 最后,利用快速傅里叶逆变换(inverse FFT, IFFT)将频域特征转换回时域特征. 上述FFT,IFFT运算步骤使得所提跟踪方法,能够以较低的对数复杂度在频域空间快速学习目标在时空维度上的交互关系. 此外,为了更好地自适应目标在跟踪过程中的表观变化,提出一种基于质量评估的目标模板记忆存储机制. 该机制根据当前跟踪状态动态更新记忆存储器中稳定的历史目标信息,用于学习适应目标变化的外观模型,有助于在搜索区域内准确匹配目标.
本文的主要贡献有3点:
1) 提出一种快速获取令牌间长程依赖关系的跟踪算法. 特征提取与融合以端到端的形式进行学习,同时在频域空间以更小的计算复杂度建模目标令牌与搜索区域令牌间的交互关系.
2) 提出一种基于质量评估的目标模板记忆存储机制,动态自适应地捕捉目标在视频序列中的稳定变化过程,提供高质量的长期历史目标信息.
3) 所提跟踪方法在3个公共跟踪数据集LaSOT[18],OTB100[19],UAV123[20]上获得优秀评价.
目标跟踪框架通常可以被划分为3部分:1)提取图像特征的主干网络;2)目标与搜索区域特征融合模块;3)生成预测位置模块. 多数跟踪方法[5-9]将CNN作为主干网络. 其中,基于孪生网络的跟踪框架以端到端方式进行训练.SiamFC[7]采用全卷积孪生网络提取目标特征,跟踪过程中不进行目标模板更新.DSiam[21]基于孪生网络以正则化线性回归模型动态更新目标模板.SiamRPN[6]利用孪生网络提取目标与搜索区域特征,同时结合目标检测研究中的区域推荐网络对目标位置进行精准定位.SiamRPN++[5]在训练过程中辅以位置均衡策略缓解CNN在训练过程中存在的位置偏见问题. 此外,一些基于在线学习的判别式目标跟踪模型也取得优异性能.DiMP[8]采用端到端网络模型离线学习目标与背景间的差异,同时在线更新目标模板.PrDiMP[9]基于DiMP[8]将概率回归用于端到端训练,在测试阶段对搜索区域生成关于目标状态的条件概率密度来捕获目标. 基于CNN的目标跟踪在训练时容易造成归纳偏置.
当前Transformer网络被广泛用于各项视觉任务中,如目标分类及检测[22-24]. Transformer中的自注意力机制将每个输入元素与其他元素进行相关性计算. 在视觉跟踪研究中,TrDiMP[13]使用Transformer增强目标上下文信息,在编码器中通过自注意力机制增强目标模板特征,利用解码器融合上下文模板进行目标定位. TransT[12]提出一种基于多头注意力机制的特征融合网络,融合后特征分别输入目标分类器及边界回归器. Stark[11]则利用ResNet[25]作为主干网络提取目标特征,以Transformer编码器和解码器进行端到端训练. SwinTrack[14]借鉴Swin Transformer[22],采用完全基于注意力机制的Transformer进行特征提取及融合. ToMP[26]同样是一种完全基于Transformer的跟踪算法,使用一个并行的2阶段跟踪器来回归目标边界. Mixformer[15]提出一种同时混合注意力模块用于特征提取及融合. 基于Transformer的目标跟踪方法虽然取得出色性能,但是随着搜索区域增大,其计算复杂度也将呈2次方增加,从而影响目标跟踪效率.
MLP-mixer[16]采用MLP代替Transformer中的自注意力机制进行令牌混合.ResMLP[17]基于MLP-mixer,利用仿射变换代替归一化进行加速处理.gMLP[27]使用空间门控单元在空间维度上给令牌重新加权. 上述MLP混合令牌的研究同样存在计算量增加问题,即随着输入令牌数量增多其时间复杂度会以2次方增加,并且MLP通常存在固定空间权重很难扩展到高分辨率图像的情形.
图1展示了基于FFT的目标与搜索区域间令牌高效混合的目标跟踪框架,该框架为端到端方式. 首先,初始目标模板大小设置为$ {{H}_{\mathrm{t}}\times W}_{\mathrm{t}}\times 3 $,记忆存储器中存储的历史目标模板的帧数设置为$ T $,搜索目标区域的大小为$ {H}_{\mathrm{s}}\times {W}_{\mathrm{s}}\times 3 $. 之后,将记忆存储器内所有目标样本和搜索区域对应图像样本,切分成不重叠的、规格为$ \tau \times \tau \times 3 $的图像块,这些图像块称为令牌. 将这些令牌拼接起来,组成1维令牌序列. 该序列包含目标信息与搜索区域信息. 下面分2步进行模型的离线训练.
1) 针对预测目标框分支进行训练. 为了高效学习目标与搜索区域令牌间的长程依赖关系,采用3阶段网络设计进行令牌间混合. 在阶段1中,使用线性嵌入层将原始令牌投影为维度为$ C $的令牌特征,再将这些令牌特征输入至线性嵌入层和包含2个FFT的令牌混合网络层. 在阶段2中,为了扩大模型的感受野,通过线性合并层来减少令牌数量,并将其输出特征维度设置为$ 2C $,这一过程由线性合并层和3个FFT的令牌混合网络层组成. 在阶段3中,继续进行线性合并,同时经过6个FFT令牌混合网络层,此时输出的特征维度设置为$ 4C $. 将在频域空间中获得的融合令牌信息进行IFFT运算,将频域特征重新转换为时域特征,并输入由3个Conv-BN-ReLU网络组成的预测头网络估计目标位置.
2) 对跟踪质量评估分支进行离线训练,受Stark[11]启发,跟踪质量评估分支由一个3层MLP网络组成,用于评价当前跟踪质量,以决定是否将当前跟踪结果更新到记忆存储器中.
下面将详细介绍基于FFT的令牌混合网络和基于跟踪质量评估的目标模板动态记忆存储机制.
如图1所示,提出的基于FFT令牌混合网络层将特征提取与融合进行集成. 具体地,先利用图像分块操作将原始的2维目标模板和搜索区域样本转化为$ N $个不重叠的$ \tau \times \tau \times 3 $大小的令牌. 经过裁剪等预处理后,得到一组特征矩阵$ {{\boldsymbol P}}=\left({\boldsymbol{p}}_{0},{\boldsymbol{p}}_{1},…,{\boldsymbol{p}}_{N-1}\right), {\boldsymbol{p}_{i}}\in {\mathbb{R}}^{3{\tau }^{2}},i\in [0,N-1] $. 之后,将$ {{\boldsymbol P}} $输入至FFT令牌混合网络,在频域空间快速获得目标特征的多尺度交互及搜索区域与目标之间的有效交互. 其中,FFT令牌融合网络层的结构如图2所示,对于第$ i $个令牌先将其映射成$ C $维向量:
$ {\boldsymbol{x}}_{i}={\omega }_{0}{\boldsymbol{p}_{i}}+{\boldsymbol{b}_{0}},i\in \left[0,N-1\right] \text{,} $
其中${\boldsymbol{\omega}}_{0}\in {\mathbb{R}}^{3{\tau }^{2}\times C} $为每个令牌首层可学习权重,$ {\boldsymbol{b}_{0}} $为首层权重位移参数向量,$ N $为输入令牌个数.
FFT令牌融合网络层的输入特征为$ \boldsymbol{X}={(\boldsymbol{x}}_{0},{\boldsymbol{x}}_{1},…, {\boldsymbol{x}}_{N-1})\in {\mathbb{R}}^{C\times N} $,其中$ C $为输出通道数. 然后采用式(2)将输入的时域特征转换为频域特征$ \boldsymbol{X}' $:
$ {\boldsymbol{X}}'=F\left(\boldsymbol{X}\right)\in {\mathbb{C}}^{H\times W\times N} \text{,} $
其中,FFT函数为$ F\left(\cdot\right) $用于获得输入特征的频域表达,$ W $为输入图像的宽,$ H $为输入图像的高.
FFT令牌混合网络层利用可学习的滤波器$ \boldsymbol{K}\in {\mathbb{C}}^{H\times W\times N} $学习$ {\boldsymbol{X}}^{'}$的频域特征$ {\boldsymbol{X}}^{''} $:
$ {\boldsymbol{X}}^{''}=\boldsymbol{K}\odot{\boldsymbol{X}}^{'} \text{,} $
其中$ \odot $为$ \boldsymbol{K} $中每一个元素与$ {\boldsymbol{X}}^{'} $对应位置元素间相乘[3].
最后,根据式(4)将频域特征$ {\boldsymbol{X}}^{''} $转换为时域特征$ {\boldsymbol{X}}^{{*}} $,并更新令牌进入下一层特征融合模块.
$ {\boldsymbol{X}}^{{*}}={F}^{-1}\left({\boldsymbol{X}}^{''}\right) , $
其中$ {F}^{-1}\left(\cdot\right) $为IFFT,用于将频域特征转化为时域特征.
参照Stark[11],本文采用一个3层Conv-BN-ReLU预测头网络来估计目标位置. 具体地,估计过程被建模为预测边界框的左上角和右下角坐标的概率值图,并回归概率值图分布获得预测目标的最终坐标. 不同于Stark的预测头网络高度依赖编码器和解码器,本文所提预测头网络由3个简单的全卷积网络组成. 离线训练预测头位置分支的损失$ {L}_{\mathrm{l}\mathrm{o}\mathrm{c}} $由$ {L}_{1} $损失和$ {L}_{\mathrm{g}\mathrm{i}\mathrm{o}\mathrm{u}} $损失组成,具体定义为:
$ {L}_{\mathrm{l}\mathrm{o}\mathrm{c}}=\alpha {L}_{1}\left({B}_{i},{B}_{\mathrm{p}\mathrm{r}\mathrm{e}\mathrm{d}}\right)+\beta {L}_{\mathrm{g}\mathrm{i}\mathrm{o}\mathrm{u}}\left({B}_{i},{B}_{\mathrm{p}\mathrm{r}\mathrm{e}\mathrm{d}}\right) \text{,} $
其中$ \alpha $为$ {L}_{1} $损失的权重系数,设置$ \alpha=5 $;$ \beta $为$ {L}_{\mathrm{g}\mathrm{i}\mathrm{o}\mathrm{u}} $的权重系数,设置$ \beta=2 $. $ {B}_{i} $为第$ i $帧搜索区域的真实标签,$ {B}_{\mathrm{p}\mathrm{r}\mathrm{e}\mathrm{d}} $为预测头网络输入预测的目标位置.
为了提升跟踪速度的同时规避跟踪过程中引入的累计误差,多数跟踪算法仅采用第1帧目标模板进行匹配. 然而在跟踪过程中目标表观通常会出现剧烈变化,此时固定目标模板的跟踪方法容易产生漂移. 部分算法采用跟踪响应图的统计特性来预测当前跟踪质量,如使用峰旁比[28]、平均峰值相关能量[29]等. 然而基于上述统计数值判断跟踪质量的做法在经历长期不稳定的跟踪后,容易导致不准确的评分结果.
如果跟踪算法可以及时预先获取当前跟踪质量,并将高质量跟踪结果放入记忆存储器中,则能够有效捕获目标在时序上的稳定表观信息变化,为目标与搜索区域的令牌混合提供有效依据.
因此,在预测头网络中添加了一个用于预测当前跟踪质量的分支. 该分支的输入为令牌融合网络层最终输出的令牌时域特征,输出为2个经过softmax函数处理过后的数值$ {S}_{i0} $与$ {S}_{i1} $. 其中$ {S}_{i0} $代表第$ i $帧输出的预测目标位置不是目标,$ {S}_{i1} $表示当前预测结果是目标.当$ {S}_{i1}{ > S}_{i0} $时,表示当前跟踪质量良好,可以将当前跟踪结果更新到记忆存储器中,此时设置$ {{\epsilon}_{i}}=1 $;当$ {S}_{i1}\le {S}_{i0} $时,表示当前跟踪质量较弱,不适宜将跟踪结果更新至记忆存储器,同时设置$ {\epsilon}_{i}=0 $.$ {\epsilon}_{i} $表示预测当前跟踪质量评估结果. 离线训练跟踪质量评价分支使用二值交叉熵损失评估,具体定义为:
$ {L}_{\mathrm{C}\mathrm{E}}={l}_{i}\mathrm{l}\mathrm{b}\left({\epsilon}_{i}\right)+\left(1-{l}_{i}\right)\mathrm{l}\mathrm{b}\left(1-{\epsilon}_{i}\right), $
其中$ {l}_{i} $为第$ i $帧样本真实的标签,当$ {l}_{i}=1 $时表示当前搜索区域包含真实目标,当$ {l}_{i}=0 $时表示当前搜索区域不包含搜索目标.
记忆存储器$ M $定义为长度$ T $的队列,更新间隔设为$ {T}_{\mathrm{I}\mathrm{N}\mathrm{R}} $. 对应的更新策略如算法1所示,当第$ i $帧的质量评估为跟踪状态良好时,即$ {\epsilon}_{i}=1 $且符合提取间隔,则将当前跟踪结果加入记忆存储队列$ M $. 若记忆存储队列$ M $的长度超过$ T $,则选择删除$ M $队列中首个元素$ {M}_{0} $. 当跟踪失败或者跟踪质量较低时,所提基于跟踪质量评估的目标记忆存储机制,能够有效缓解目标模板产生误差带来的消极影响.
该机制的可视化展示如图3所示. 第1帧给定初始目标,并将其存入记忆存储器中. 记忆存储器的长度$ T $设置为5,根据跟踪质量评价结果,动态地将可靠的目标模板存入$ M $中. 第200帧时,目标被完全遮挡,此时质量评估较差,不进行更新存储操作. 至此,$ M $中的目标模板分别来自第90帧、第100帧、第110帧、第120帧、第130帧的跟踪结果. 在第260帧时目标重新出现,此时质量评估良好,所以当前$ M $存储的目标模板调整为第120帧、第130帧、第240帧、第250帧、第260帧的跟踪结果.
算法1. 基于跟踪质量评估的目标模板记忆存储.
输入:$ {I}_{0} $为第1帧的目标模板区域,
$ {I}_{i} $为第$ i $帧跟踪结果区域,
$ {\epsilon}_{i} $为第$ i $帧跟踪质量评估结果,
$ M $为记忆存储器队列,
$ T $为记忆存储器长度,
$ {L}_{\mathrm{V}\mathrm{I}\mathrm{D}} $为视频序列长度,
$ {T}_{\mathrm{I}\mathrm{N}\mathrm{R}} $为更新间隔;
输出:$ M $为更新后的记忆存储器.
① $ M=\varnothing $;
② while len($ M $)<$ T $
③ $ M\leftarrow M\cup \left\{{I}_{0}\right\}; $
④ for $ i=1,2,\cdots {,L}_{\mathrm{V}\mathrm{I}\mathrm{D}} $
⑤   if $ ({\epsilon}_{i} $==1$ ) $ and $ ( $mod$ (i,{T}_{\mathrm{I}\mathrm{N}\mathrm{R}}) $==0)
⑥    $ M\leftarrow M\cup \left\{{I}_{i}\right\}; $
⑦   end if
⑧   if len$ \left(M\right) $<$ T $
⑨    $ M\leftarrow M\mathrm{r}\mathrm{e}\mathrm{m}\mathrm{o}\mathrm{v}\mathrm{e}{M}_{0}; $
⑩   end if
⑪ end for
目标模板大小为$ {{H}_{\mathrm{t}}\times W}_{\mathrm{t}}\times 3 $,搜索区域的大小为$ {{H}_{\mathrm{s}}\times W}_{\mathrm{s}}\times 3 $. 设置$ {H}_{\mathrm{t}} $,$ {W}_{\mathrm{t}} $两者值均为128;$ {H}_{\mathrm{s}} $,$ {W}_{\mathrm{s}} $两者值均为384.记忆存储器长度$ T=5 $. 记忆器更新模板的间隔$ {T}_{\mathrm{I}\mathrm{N}\mathrm{R}}=10 $. 图像分块操作中块大小$ \tau =4 $. 训练数据集为LaSOT[18],GOT-10k[30],TrackingNet[31].
考虑到定位和分类的联合学习可能导致2个任务存在次优解 [11]. 因此,借鉴Stark[11]和Mixformer[15]的训练方式,分2步训练特征融合模型. 首先,进行300批次的预测目标位置分支训练,采用Adam[32]损失优化器将学习率设置为$ 1\mathrm{E}-4 $;其次,进行100批次的预测当前跟踪质量的分支训练,学习率设置为$ 1\mathrm{E}-5 $. 软件环境为Ubuntu20.04,Python3.6,Torch1.10.3,Cuda11.3.硬件环境为NVIDIA RTX3090 24 GB.
在LaSOT[18],OTB100[19],UAV123[20]数据集上验证本文方法的有效性. 评价指标为成功率(success ratio)和精度图(precision plot),其中成功率使用成功率曲线下面积(area under curve, AUC)作为排序依据.
LaSOT[18]数据集包含1400个视频序列,共计70类目标. 其中1120个视频用于训练,280个视频用于测试. 视频序列平均长度2400帧. 数据集包含视野外等14种挑战.图4显示本文算法与TrDiMP[13],TransT[12],Alpha-Refine[33],SiamR-CNN[34],PrDiMP[9],DiMP[8],SiamGAT[35],SiamBAN[36] 8种优秀算法比较结果. 结果表明本文算法在成功率和精度图中均处于领先水平. 精度图方面比TransT高3.3%,成功率比Alpha-Refine高0.8%.图5展示本文算法与5种先进算法在不同挑战下的实验结果,可以看出本文算法在多数挑战中均表现优异.
OTB100[19]数据集包含100个视频序列,涉及快速运动等11种挑战.图6展示本文算法与TransT[12],SiamRPN++[5],SiamBAN[36],PrDiMP[9],DiMP[8],ECO[37],MDNet[38],ATOM[10]的比较结果. 本文方法取得最高的成功率值和精度图值,分别比SiamRPN++ 提升0.2%和0.5%.
UAV123[20]数据集由123个无人机低空拍摄的视频序列构成. 小目标和频繁遮挡是该数据集的独特挑战. 表1显示本文算法与TrDiMP[13],TransT[12], SiamR-CNN[34],SiamGAT[35],SiamBAN[36],PrDiMP[9],DiMP[8],SiamRPN++[5]的比较结果. 本文算法在成功率和精度图评价指标上均排名第一.
本节用可视化展示本文算法与6种优秀算法在旋转、快速移动、尺寸变换及遮挡等挑战下的表现.
图7展示LaSOT[18]数据集中bird-17视频序列的跟踪结果. 该视频序列具备快速移动、视野外等挑战. 目标在148~156帧快速向左移动至视野外,导致Alpha-Refine[33]和TrDiMP[13]发生跟踪漂移. 在第184帧中目标再次回归视野内,只有本文算法可以准确跟踪目标. 由于目标同时发生快速移动、运动模糊、旋转等挑战,其他算法均跟踪失败. 而本文算法拥有记忆存储器中的稳定目标模板,可以增强跟踪器对目标表观的自适应能力,并且在搜索目标时可快速计算目标模板和搜索区域之间的匹配关系,因此可以高效、稳健地跟踪目标.
图8展示LaSOT[18]数据集中bicycle-18视频序列的跟踪结果. 在此视频中目标受遮挡、旋转等挑战影响. 第344~400帧目标被岩石遮挡,导致TransT[12]和SiamGAT[35]丢失目标. 第437~517帧目标发生剧烈旋转,SiamGAT,TransT,PrDiMP[9]均无法快速应对剧烈旋转引起的外观突变而发生漂移. 本文算法则依托令牌混合方案快速对目标与搜索区域特征进行交互,有效地获取更加稳健的时空特征,最终成功跟踪目标.
本节验证本文算法中基于FFT的令牌混合网络和基于跟踪质量评估的目标模板动态记忆存储机制的有效性. 表2展示不同变体在LaSOT[18]测试集上的成功率和精度图得分.
首先,探讨基于FFT的令牌混合网络的有效性.表2中变体1采用基于CNN融合目标与搜索区域令牌的方法,并且仅利用第1帧初始目标区域作为目标模板. 变体2采用FFT融合方法,同样仅采用第1帧初始目标区域作为目标模板进行匹配. 结果显示,基于FFT的融合方法比基于CNN的融合方法的成功率和精度图分别高1.3%和2.5%. 基于传统CNN的融合方式在训练时只能学习特征间的局部依赖关系,无法获取全局长程依赖,且利用CNN训练模型存在较大的归纳偏置. 为了更加充分融合目标与搜索区域间的信息同时建立两者间的长程依赖关系,本文提出利用FFT进行令牌间的高效融合. 可以观察到在平均跟踪速度上变体2比变体1提升近1倍,结果证实基于FFT令牌混合网络的有效性.
其次,变体3在变体2的基础上增加了基于质量评估的目标模板动态记忆存储机制,用于获得更新稳定的目标模板信息,从而自适应目标表观变化. 由于记忆存储机制增加了目标模板数量,所以对平均跟踪速度上有一定影响. 变体3在测试时的平均跟踪速度比变体2降低了7 fps,但变体3在成功率和精度图上,分别比变体2高出0.6%和1.4%. 结果显示基于跟踪质量评估的目标模板动态记忆存储机制有效.
此外,为了进一步验证本文方法具备高效的特征提取与融合能力. 在LaSOT数据集上将本文方法与基于1阶段训练的Mixformer[15]和基于2阶段训练的TrDiMP[13]进行对比,结果如表3所示. 与采用2阶段训练的TrDiMP[13]相比,本文方法的成功率和精度图分别提升2.7%和5.7%,同时平均跟踪速度比TrDiMP[13]快8 fps.与基于1阶段训练的Mixformer[15]相比,虽然成功率和精度图降低2.5%和2.4%,但是推理速度比Mixformer[15]高9 fps.实验结果表明本文方法在准确率和推理速度间的平衡能力更好,同时34 fps的平均跟踪速度达到跟踪实时性[11]要求(>30 fps).
本文提出了一种端到端的基于傅里叶变换的高效混合目标与搜索区域令牌的视觉目标跟踪方法. 该方法将特征提取与融合相结合,利用傅里叶变换将令牌的时域特征转换为频域特征,以便快速学习搜索区域与目标模板之间的长程依赖关系. 为了捕获目标在时序上的外观变化,提出了一种基于跟踪质量评估的目标模板动态记忆存储机制,确保更新目标外观模板的合理性. 广泛的实验结果验证了所提方法的有效性.
作者贡献声明:薛万利提出论文整体思路并负责撰写与修改论文;张智彬负责算法设计与实验并撰写论文;裴生雷负责算法设计及论文审核;张开华负责论文修改;陈胜勇参与了论文思路的讨论及审核.

参考文献 引证文献
排序方式:
1
李玺,查宇飞,张天柱,等. 深度学习的目标跟踪算法综述[J]. 中国图象图形学报,2019,24(12):2057−2080
Li Xi, Cha Yufei, Zhang Tianzhu, et al. Survey of visual object tracking algorithms based on deep learning[J]. Journal of Image and Graphics, 2019, 24(12): 2057−2080 (in Chinese)
2
柳培忠,汪鸿翔,骆炎民,等. 一种结合时空上下文的在线卷积网络跟踪算法[J]. 计算机研究与发展,2018,55(12):2785−2793
Liu Peizhong, Wang Hongxiang, Luo Yanmin, et al. Visual tracking algorithm based on adaptive spatial regularization[J]. Journal of Computer Research and Development, 2018, 55(12): 2785−2793 (in Chinese)
3
Rao Yongming, Zhao Wenliang, Zhu Zheng, et al. Global filter networks for image classification[C] //Proc of the 35th Advances in Neural Information Processing Systems. Cambridge, MA: MIT, 2021: 980−993
4
Zhang Zhipeng, Peng Houwen. Deeper and wider Siamese networks for real-time visual tracking[C] //Proc of the 32nd IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 4591−4600
5
Li Bo, Wu Wei, Wang Qiang, et al. Evolution of Siamese visual tracking with very deep networks[C] //Proc of the 32nd IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 16−20
6
Li Bo, Yan Junjie, Wu Wei, et al. High performance visual tracking with Siamese region proposal network[C] //Proc of the 31st IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 8971−8980
7
Bertinetto L, Valmadre J, Henriques J F, et al. Fully-convolutional siamese networks for object tracking[C] //Proc of the 14th European Conf on Computer Vision. Berlin: Springer, 2016: 850−865
8
Bhat G, Danelljan M, Gool L V, et al. Learning discriminative model prediction for tracking[C] //Proc of the 17th IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2019: 6182−6191
9
Danelljan M, Gool L V, Timofte R. Probabilistic regression for visual tracking[C] //Proc of the 33rd IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2020: 7183−7192
10
Danelljan M, Bhat G, Khan F S, et al. Atom: Accurate tracking by overlap maximization[C] //Proc of the 32nd IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 4660−4669
11
Yan Bin, Peng Houwen, Fu Jianlong, et al. Learning spatio-temporal transformer for visual tracking[C] //Proc of the 18th IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2021: 10448-10457
12
Chen Xin, Yan Bin, Zhu Jiawen, et al. Transformer tracking[C] //Proc of the 34th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 8126−8135
13
Wang Ning, Zhou Wengang, Wang Jie, et al. Transformer meets tracker: Exploiting temporal context for robust visual tracking[C] //Proc of the 34th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 1571−1580
14
Lin Liting, Fan Heng, Xu Yong, et al. SwinTrack: A simple and strong baseline for transformer tracking[J]. arXiv preprint, arXiv: 2112. 00995, 2021
15
Cui Yutao, Cheng Jiang, Wang Liming, et al. Mixformer: End-to-end tracking with iterative mixed attention[C] //Proc of the 35th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 13608−13618
16
Tolstikhin I, Houlsby N, Kolesnikov A, et al. MLP-mixer: An all-MLP architecture for vision[J]. arXiv preprint, arXiv: 2105. 01601, 2021
17
Touvron H, Bojanowski P, Caron M, et al. ResMLP: Feedforward networks for image classification with data-efficient training[J]. arXiv preprint, arXiv: 2105. 03404, 2021
18
Fan Heng, Lin Liting, Yang Fan, et al. LaSOT: A high-quality benchmark for large-scale single object tracking[C] //Proc of the 32nd IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 5374−5383
19
Wu Yi, Lim J, Yang Ming-Hsuan. Online object tracking: A benchmark[C] //Proc of the 26th IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2013: 2411−2418
20
Mueller M, Smith N, Ghanem B. A benchmark and simulator for UAV tracking[C] //Proc of the 14th European Conf on Computer Vision. Berlin: Springer, 2016: 445−461
21
Guo Qing, Feng Wei, Zhou Ce, et al. Learning dynamic siamese network for visual object tracking[C] //Proc of the 16th IEEE Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2017: 1763−1771
22
Liu Ze, Lin Yutong, Cao Yue, et al. Swin Transformer: hierarchical vision transformer using shifted windows[C] // Proc of the 18th IEEE Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2021: 10012−10022
23
Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16x16 words: Transformers for image recognition at scale[J]. arXiv preprint, arXiv: 2010. 11929, 2020
24
Wu Haiping, Xiao Bin, Codella N, et al. CVT: Introducing convolutions to vision transformers[C] // Proc of the 18th IEEE Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2021: 22-31
25
He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Deep residual learning for image recognition[C] //Proc of the 29th IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2016: 770−778
26
Mayer C, Danelljan M, Bhat G, et al. Transforming model prediction for tracking[J]. arXiv preprint, arXiv: 2203. 11192, 2022
27
Liu Hanxiao, Dai Zihang, So D, et al. Pay attention to MLPs[C] //Proc of the 35th Advances in Neural Information Processing Systems. Cambridge, MA: MIT, 2021: 9204−9215
28
Bolme D S, Beveridge J R, Draper B A, et al. Visual object tracking using adaptive correlation filters[C] //Proc of the 23rd IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2010: 2544−2550
29
Wang Mengmeng, Liu Yong, Huang Zeyi. Large margin object tracking with circulant feature maps[C] //Proc of the 30th IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 4021−4029
30
Huang Lianghua, Zhao Xin, Huang Kaiqi. GOT-10k: A large high-diversity benchmark for generic object tracking in the wild[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 43(5): 1562−1577
31
Muller M, Bibi A, Giancola S, et al. TrackingNet: A large-scale dataset and benchmark for object tracking in the wild[C] //Proc of the 15th European Conf on Computer Vision. Berlin: Springer, 2018: 300−317
32
Kingma D P, Jimmy B. Adam: A method for stochastic optimization[J]. arXiv preprint, arXiv: 1412. 6980, 2014
33
Yan Bin, Zhang Xinyu, Wang Dong, et al. Alpha-Refine: Boosting tracking performance by precise bounding box estimation[C] //Proc of the 34th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 5289−5298
34
Voigtlaender P, Luiten J, Torr P H S, et al. SiamR-CNN: Visual tracking by re-detection[C] //Proc of the 33rd IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2020: 6578−6588
35
Guo Dongyan, Shao Yanyan, Cui Ying, et al. Graph attention tracking[C] //Proc of the 34th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 9543−9552
36
Chen Zedu, Zhong Bineng, Li Guorong, et al. Siamese box adaptive network for visual tracking[C] //Proc of the 33rd IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2020: 6668−6677
37
Danelljan M, Bhat G, Shahbaz K F, et al. ECO: Efficient convolution operators for tracking[C] //Proc of the 30th IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 6638−6646
38
Nam H, Han B. Learning multi-domain convolutional neural networks for visual tracking[C] //Proc of the 29th IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2016: 4293−4302
2024年第61卷第2期
75
36
0
引用本文
BibTeX
文章信息
doi: 10.7544/issn1000-1239.202220698
  • 接收时间:2022-08-08
  • 首发时间:2026-11-17
  • 出版时间:2024-02-02
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2022-08-08
  • 修回日期:2023-03-13
基金
作者信息
    1天津理工大学计算机科学与工程学院 天津 300384
    2青海民族大学物理与电子信息工程学院 西宁 810007
    3南京信息工程大学计算机学院 南京 130012

通讯作者:

裴生雷()
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/10.7544/issn1000-1239.202220698
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏