CASIA OpenIR  > 精密感知与控制研究中心  > 人工智能与机器学习
Discriminative Reverse Sparse Tracking via Weighted Multitask Learning
Yang, Yehui; Hu, Wenrui; Zhang, Wensheng; Zhang, Tianzhu; Xie, Yuan; Wensheng Zhang
Source PublicationIEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
2017-05-01
Volume27Issue:5Pages:1031-1042
SubtypeArticle
AbstractMultitask learning has shown great potentiality for visual tracking under a particle filter framework. However, the recent multitask trackers, which exploit the similarity between all candidates by imposing group sparsity on the candidate representations, have a limitation in robustness due to the diverse sampling of candidates. To deal with this issue, we propose a discriminative reverse sparse tracker via weighted multitask learning. Our positive and negative templates are retained from the target observations and the background, respectively. Here, the templates are reversely represented via the candidates, and the representation of each positive template is viewed as a single task. Compared with existing multitask trackers, the proposed algorithm has the following advantages. First, we regularize the target representations with the similar to 2,1-norm to exploit the similarity shared by the positive templates, which is reasonable because of the target appearance consistency in the tracking process. Second, the valuable prior relationship between the candidates and the templates is introduced into the representation model by a weighted multitask learning scheme. Third, both target information and background information are integrated to generate discriminative scores for enhancing the proposed tracker. The experimental results on challenging sequences show that the proposed algorithm is effective and performs favorably against 12 state-of-the-art trackers.
KeywordSparse Representation Visual Tracking Weighted Multitask Learning
WOS HeadingsScience & Technology ; Technology
DOI10.1109/TCSVT.2015.2513699
WOS KeywordROBUST VISUAL TRACKING ; OBJECT TRACKING ; FACE RECOGNITION ; REPRESENTATION
Indexed BySCI
Language英语
Funding OrganizationNational Natural Science Foundation of China(61402480 ; National High Technology Research and Development Program of China(2013AA01A607) ; 6150051467 ; U1135005)
WOS Research AreaEngineering
WOS SubjectEngineering, Electrical & Electronic
WOS IDWOS:000400907500008
Citation statistics
Cited Times:3[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/12256
Collection精密感知与控制研究中心_人工智能与机器学习
Corresponding AuthorWensheng Zhang
AffiliationChinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Yang, Yehui,Hu, Wenrui,Zhang, Wensheng,et al. Discriminative Reverse Sparse Tracking via Weighted Multitask Learning[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2017,27(5):1031-1042.
APA Yang, Yehui,Hu, Wenrui,Zhang, Wensheng,Zhang, Tianzhu,Xie, Yuan,&Wensheng Zhang.(2017).Discriminative Reverse Sparse Tracking via Weighted Multitask Learning.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,27(5),1031-1042.
MLA Yang, Yehui,et al."Discriminative Reverse Sparse Tracking via Weighted Multitask Learning".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 27.5(2017):1031-1042.
Files in This Item: Download All
File Name/Size DocType Version Access License
07368895.pdf(2761KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yang, Yehui]'s Articles
[Hu, Wenrui]'s Articles
[Zhang, Wensheng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yang, Yehui]'s Articles
[Hu, Wenrui]'s Articles
[Zhang, Wensheng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yang, Yehui]'s Articles
[Hu, Wenrui]'s Articles
[Zhang, Wensheng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 07368895.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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