Geometric Hypergraph Learning for Visual Tracking

doi:10.1109/TCYB.2016.2626275

	Geometric Hypergraph Learning for Visual Tracking
	Du, Dawei 1,2; Qi, Honggang 1,2; Wen, Longyin 3,4; Tian, Qi 5; Huang, Qingming 1,2,6; Lyu, Siwei 7
	2017-12-01
发表期刊	IEEE TRANSACTIONS ON CYBERNETICS
ISSN	2168-2267
卷号	47 期号:12 页码:4182-4195
摘要	Graph-based representation is widely used in visual tracking field by finding correct correspondences between target parts in different frames. However, most graph-based trackers consider pairwise geometric relations between local parts. They do not make full use of the target's intrinsic structure, thereby making the representation easily disturbed by errors in pairwise affinities when large deformation or occlusion occurs. In this paper, we propose a geometric hypergraph learning-based tracking method, which fully exploits high-order geometric relations among multiple correspondences of parts in different frames. Then visual tracking is formulated as the mode-seeking problem on the hypergraph in which vertices represent correspondence hypotheses and hyperedges describe high-order geometric relations among correspondences. Besides, a confidence-aware sampling method is developed to select representative vertices and hyperedges to construct the geometric hypergraph for more robustness and scalability. The experiments are carried out on three challenging datasets (VOT2014, OTB100, and Deform-SOT) to demonstrate that our method performs favorably against other existing trackers.
关键词	Confidence-aware sampling correspondence hypotheses deformation geometric hypergraph learning mode-seeking occlusion visual tracking
DOI	10.1109/TCYB.2016.2626275
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61620106009] ; National Natural Science Foundation of China[61332016] ; National Natural Science Foundation of China[61472388] ; National Natural Science Foundation of China[61429201] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-SYS013] ; ARO[W911NF-15-1-0290] ; Faculty Research Gift Awards by NEC Laboratories of America ; U.S. National Science Foundation Research Grant through Division of Computing and Communication Foundations[1319800] ; Blippar
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS记录号	WOS:000415727200015
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：26[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/6496
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Qi, Honggang; Huang, Qingming
作者单位	1.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Key Lab Big Data Min & Knowledge Management, Beijing 101408, Peoples R China 3.SUNY Albany, Albany, NY 12222 USA 4.GE Global Res, Niskayuna, NY 12309 USA 5.Univ Texas San Antonio, Dept Comp Sci, San Antonio, TX 78249 USA 6.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 7.SUNY Albany, Dept Comp Sci, Albany, NY 12222 USA
推荐引用方式 GB/T 7714	Du, Dawei,Qi, Honggang,Wen, Longyin,et al. Geometric Hypergraph Learning for Visual Tracking[J]. IEEE TRANSACTIONS ON CYBERNETICS,2017,47(12):4182-4195.
APA	Du, Dawei,Qi, Honggang,Wen, Longyin,Tian, Qi,Huang, Qingming,&Lyu, Siwei.(2017).Geometric Hypergraph Learning for Visual Tracking.IEEE TRANSACTIONS ON CYBERNETICS,47(12),4182-4195.
MLA	Du, Dawei,et al."Geometric Hypergraph Learning for Visual Tracking".IEEE TRANSACTIONS ON CYBERNETICS 47.12(2017):4182-4195.