Dual Graph Regularized Discriminative Multitask Tracker | |
Fan BJ(范保杰)1; Cong Y(丛杨)2![]() ![]() | |
Department | 机器人学研究室 |
Source Publication | IEEE Transactions on Multimedia
![]() |
ISSN | 1520-9210 |
2018 | |
Volume | 20Issue:9Pages:2303-2315 |
Indexed By | SCI ; EI |
EI Accession number | 20180704801535 |
WOS ID | WOS:000442358200006 |
Contribution Rank | 2 |
Funding Organization | China Postdoctoral Science Foundation ; Jiangsu Postdoctoral Science Foundation ; Foundation for the Talent of Nanjing University of Tele. and Com. ; National Nature Science Foundation ; Natural Science Foundation of Jiangsu Province |
Keyword | Multi-task Tracker Discriminative Low Rank Learning Geometric Structure Information Graph Regularization Collaborate Metric |
Abstract | Multi-task and low rank learning methods have attracted increasing attention for visual tracking. However, most trackers only focus on learning appearance subspace basis or the sparse low rankness of representation, thus do not make full use of the structure information among and inside target candidates (or samples). In this work, we propose a dual graph regularized discriminative low rank learning for multi-task tracker, which integrates the discriminative subspace and intrinsic geometric structures among tasks. By constructing double graphs regula- tions from two views of multi-task observation, the developed modal not only exploits the intrinsic relationship among tasks, and preserves the spatial layout structure among the local patches inside each candidate, but also learns the salient features of the target samples. This operation is benefit to having good target representation and improving the performance of the tracker. Moreover, our developed tracker is a collaborate multi- task tracking model, and learns the discriminative subspace with adaptive dimension and optimal classifier simultaneously. Then, a collaborate metric is developed to find the best candidate, which integrates both classification reliability and representation accu- racy. Encouraging experimental results on a large set of public video sequences justify that our tracker performs favourably against many other state-of-the-art trackers. |
Language | 英语 |
WOS Subject | Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications |
WOS Keyword | OBJECT TRACKING ; VISUAL TRACKING ; SPARSE REPRESENTATION ; LOW-RANK ; BENCHMARK |
WOS Research Area | Computer Science ; Telecommunications |
Funding Project | China Postdoctoral Science Foundation[2015M571785] ; China Postdoctoral Science Foundation[2016T90484] ; Jiangsu Postdoctoral Science Foundation[1402085C] ; Foundation for the Talent of Nanjing University of Tele. and Com.[NY215148] ; Foundation for the Talent of Nanjing University of Tele. and Com.[NY217061] ; National Nature Science Foundation[61722311] ; National Nature Science Foundation[U1613214] ; National Nature Science Foundation[51775284] ; Natural Science Foundation of Jiangsu Province[BK20151505] |
Citation statistics | |
Document Type | 期刊论文 |
Identifier | http://ir.sia.cn/handle/173321/21531 |
Collection | 机器人学研究室 |
Corresponding Author | Fan BJ(范保杰) |
Affiliation | 1.Nanjing University of Posts and Telecommunications, 12577 Nanjing China 210003 2.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, shenyang China |
Recommended Citation GB/T 7714 | Fan BJ,Cong Y,Tang YD. Dual Graph Regularized Discriminative Multitask Tracker[J]. IEEE Transactions on Multimedia,2018,20(9):2303-2315. |
APA | Fan BJ,Cong Y,&Tang YD.(2018).Dual Graph Regularized Discriminative Multitask Tracker.IEEE Transactions on Multimedia,20(9),2303-2315. |
MLA | Fan BJ,et al."Dual Graph Regularized Discriminative Multitask Tracker".IEEE Transactions on Multimedia 20.9(2018):2303-2315. |
Files in This Item: | ||||||
File Name/Size | DocType | Version | Access | License | ||
Dual Graph Regulariz(5057KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | View Application Full Text |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment