SIA OpenIR  > 机器人学研究室
Structured and weighted multi-task low rank tracker
Fan BJ(范保杰)1; Li XM(李小毛)2; Cong Y(丛杨)3; Tang YD(唐延东)3
作者部门机器人学研究室
关键词Robust multi-subtask learning Structured and weighted low rank Group-sparsity regularization Normalized collaboration metric
发表期刊PATTERN RECOGNITION
ISSN0031-3203
2018
卷号81页码:528-544
收录类别SCI
WOS记录号WOS:000436350700039
产权排序3
摘要Low rank subspace and multi-task learning have been introduced into object tracking to pursuit the accurate representation. However, many existing methods regularize all rank components equally, and shrink with the same threshold. In addition, these methods ignore the discriminative and structured information among tasks during the tracking. In this paper, we propose an online discriminative multi-task tracker with structured and weighted low rank regularization (ODMT-SL). Specifically, the total tracking task is accomplished by the combination of multiple subtasks, and each subtask corresponds to the trace of the image patch from the tracked object. In order to improve the flexibility of multi-task tracker, the weighted nuclear norm is introduced to adaptively assign different tracking importance on different rank components of multiple tasks. The geometric structure relationship among and inside candidates (or training samples) are mined to learn the collaborate representation, according to the discriminative subspace and optimal classifier. They are simultaneously learned and updated by minimizing the developed tracking model. The best candidate is selected by jointly evaluating the normalized metric. The proposed tracker is empirically compared with the state-of-the-art trackers on a large set of public video sequences. Both quantitative and qualitative comparisons demonstrate that the proposed algorithm performs well in terms of effectiveness, accuracy and robustness. (C) 2018 Published by Elsevier Ltd.
语种英语
引用统计
被引频次:1[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.sia.cn/handle/173321/22426
专题机器人学研究室
通讯作者Fan BJ(范保杰); Li XM(李小毛)
作者单位1.Automation College, Nanjing University of Posts and Telecommunications, China
2.School of Mechatronic Engineering and Automation, Shanghai University, China
3.State Key Laboratory of Robotics, Chinese Academy of Sciences, China
推荐引用方式
GB/T 7714
Fan BJ,Li XM,Cong Y,et al. Structured and weighted multi-task low rank tracker[J]. PATTERN RECOGNITION,2018,81:528-544.
APA Fan BJ,Li XM,Cong Y,&Tang YD.(2018).Structured and weighted multi-task low rank tracker.PATTERN RECOGNITION,81,528-544.
MLA Fan BJ,et al."Structured and weighted multi-task low rank tracker".PATTERN RECOGNITION 81(2018):528-544.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Structured and weigh(4183KB)期刊论文出版稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Fan BJ(范保杰)]的文章
[Li XM(李小毛)]的文章
[Cong Y(丛杨)]的文章
百度学术
百度学术中相似的文章
[Fan BJ(范保杰)]的文章
[Li XM(李小毛)]的文章
[Cong Y(丛杨)]的文章
必应学术
必应学术中相似的文章
[Fan BJ(范保杰)]的文章
[Li XM(李小毛)]的文章
[Cong Y(丛杨)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Structured and weighted multi-task low rank tracker.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。