Hedging Deep Features for Visual Tracking

doi:10.1109/TPAMI.2018.2828817

	Hedging Deep Features for Visual Tracking
	Qi, Yuankai 1; Zhang, Shengping 2; Qin, Lei 3; Huang, Qingming 1,3,4; Yao, Hongxun 1; Lim, Jongwoo 5; Yang, Ming-Hsuan 6
	2019-05-01
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN	0162-8828
卷号	41 期号:5 页码:1116-1130
摘要	Convolutional Neural Networks (CNNs) have been applied to visual tracking with demonstrated success in recent years. Most CNN-based trackers utilize hierarchical features extracted from a certain layer to represent the target. However, features from a certain layer are not always effective for distinguishing the target object from the backgrounds especially in the presence of complicated interfering factors (e.g., heavy occlusion, background clutter, illumination variation, and shape deformation). In this work, we propose a CNN-based tracking algorithm which hedges deep features from different CNN layers to better distinguish target objects and background clutters. Correlation filters are applied to feature maps of each CNN layer to construct a weak tracker, and all weak trackers are hedged into a strong one. For robust visual tracking, we propose a hedge method to adaptively determine weights of weak classifiers by considering both the difference between the historical as well as instantaneous performance, and the difference among all weak trackers over time. In addition, we design a Siamese network to define the loss of each weak tracker for the proposed hedge method. Extensive experiments on large benchmark datasets demonstrate the effectiveness of the proposed algorithm against the state-of-the-art tracking methods.
关键词	Visual tracking convolutional neural network adaptive hedge Siamese network
DOI	10.1109/TPAMI.2018.2828817
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[U1636214] ; National Natural Science Foundation of China[61650202] ; National Natural Science Foundation of China[61672188] ; National Natural Science Foundation of China[61572465] ; National Natural Science Foundation of China[61390510] ; National Natural Science Foundation of China[61732007] ; National Natural Science Foundation of China[61472103] ; National Natural Science Foundation of China[61772158] ; National Natural Science Foundation of China[U1711265] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-SYS013] ; NRF - Ministry of Science, ICT Korea[NRF-2017R1A2B4011928] ; NRF - Ministry of Science, ICT Korea[NRF-2017M3C4A7069369] ; NSF CAREER[1149783] ; Young Excellent Talent Program of Harbin Institute of Technology
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000463607400007
出版者	IEEE COMPUTER SOC
引用统计	被引频次：54[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/2XEOYT63/4270
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhang, Shengping; Huang, Qingming
作者单位	1.Harbin Inst Technol, Sch Comp Sci & Technol, Harbin 150001, Heilongjiang, Peoples R China 2.Harbin Inst Technol, Sch Comp Sci & Technol, Weihai 264209, Shandong, Peoples R China 3.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China 4.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing 100049, Peoples R China 5.Hanyang Univ, Dept Comp Sci, Seoul 133791, South Korea 6.Univ Calif Merced, Sch Engn, Merced, CA 95344 USA
推荐引用方式 GB/T 7714	Qi, Yuankai,Zhang, Shengping,Qin, Lei,et al. Hedging Deep Features for Visual Tracking[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2019,41(5):1116-1130.
APA	Qi, Yuankai.,Zhang, Shengping.,Qin, Lei.,Huang, Qingming.,Yao, Hongxun.,...&Yang, Ming-Hsuan.(2019).Hedging Deep Features for Visual Tracking.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,41(5),1116-1130.
MLA	Qi, Yuankai,et al."Hedging Deep Features for Visual Tracking".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 41.5(2019):1116-1130.