SIA OpenIR  > 机器人学研究室
Active Trace: A Sparse Spatiotemporal Representation for Videos
Han Z(韩志); Shen GP(沈贵萍); Yu SQ(余思泉); Ding ND(丁乃达); Tian JD(田建东); Tang YD(唐延东)
Department机器人学研究室
Source PublicationIEEE Access
ISSN2169-3536
2017
Volume5Pages:22433-22442
Indexed BySCI ; EI
EI Accession number20174404325460
WOS IDWOS:000414737100001
Contribution Rank1
Funding OrganizationNational Natural Science Foundation of China under Grant 61773367 and Grant 61303168
KeywordActive Trace Video Modeling Sparse Representation Tracking Action Template
AbstractThis paper proposes a sparse video representation with a deformable spatiotemporal template feature, named as active trace template. An active trace is the motion track of an active spatial feature which moves in a certain velocity. To accommodate geometric variations of the spatial feature and motion variations of the temporal track, the atomic spatial feature in each video frame is capable to slightly shift its location and other attributes within certain ranges to best represent the salient trackable structure. The representation quality is quantified by a spatiotemporal score. It is computed through a new proposed spatiotemporal hierarchical architecture of summax maps. Based on the score, a small number of best active trace templates are selected from all the trace candidates to depict the video sketch. The experiments demonstrate that for natural videos, the proposed model is able to provide an intuitive and sparse representation which matches human vision as well as reveals the spatiotemporal correspondence along consecutive frames, even in challenging situations such as occlusion. Furthermore, it shows the potential on dealing with high level vision tasks by moving object detection and segmentation, and action template learning and representation. OAPA
Language英语
WOS HeadingsScience & Technology ; Technology
WOS SubjectComputer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS KeywordOBJECT TRACKING ; VISUAL TRACKING ; MODEL
WOS Research AreaComputer Science ; Engineering ; Telecommunications
Citation statistics
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/21110
Collection机器人学研究室
Corresponding AuthorHan Z(韩志)
AffiliationState Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China
Recommended Citation
GB/T 7714
Han Z,Shen GP,Yu SQ,et al. Active Trace: A Sparse Spatiotemporal Representation for Videos[J]. IEEE Access,2017,5:22433-22442.
APA Han Z,Shen GP,Yu SQ,Ding ND,Tian JD,&Tang YD.(2017).Active Trace: A Sparse Spatiotemporal Representation for Videos.IEEE Access,5,22433-22442.
MLA Han Z,et al."Active Trace: A Sparse Spatiotemporal Representation for Videos".IEEE Access 5(2017):22433-22442.
Files in This Item: Download All
File Name/Size DocType Version Access License
Active Trace_ A Spar(6522KB)期刊论文作者接受稿开放获取ODC PDDLView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Han Z(韩志)]'s Articles
[Shen GP(沈贵萍)]'s Articles
[Yu SQ(余思泉)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Han Z(韩志)]'s Articles
[Shen GP(沈贵萍)]'s Articles
[Yu SQ(余思泉)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Han Z(韩志)]'s Articles
[Shen GP(沈贵萍)]'s Articles
[Yu SQ(余思泉)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Active Trace_ A Sparse Spatiotemporal Representation for Videos.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.