中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Hedging Deep Features for Visual Tracking

文献类型：期刊论文

作者Qi, Yuankai6; Zhang, Shengping5; Qin, Lei4; Huang, Qingming3,4,6; Yao, Hongxun6; Lim, Jongwoo2; Yang, Ming-Hsuan1
刊名IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
出版日期2019-05-01
卷号41期号:5页码:1116-1130
关键词Visual tracking convolutional neural network adaptive hedge Siamese network
ISSN号0162-8828
DOI10.1109/TPAMI.2018.2828817
英文摘要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.
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
语种英语
WOS记录号WOS:000463607400007
出版者IEEE COMPUTER SOC
源URL[http://119.78.100.204/handle/2XEOYT63/4269]  
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.Univ Calif Merced, Sch Engn, Merced, CA 95344 USA
2.Hanyang Univ, Dept Comp Sci, Seoul 133791, South Korea
3.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing 100049, Peoples R China
4.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China
5.Harbin Inst Technol, Sch Comp Sci & Technol, Weihai 264209, Shandong, Peoples R China
6.Harbin Inst Technol, Sch Comp Sci & Technol, Harbin 150001, Heilongjiang, Peoples R China
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.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

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。