Deep Spatial and Temporal Network for Robust Visual Object Tracking

doi:10.1109/TIP.2019.2942502

	Deep Spatial and Temporal Network for Robust Visual Object Tracking
	Teng, Zhu 1; Xing, Junliang2 ; Wang, Qiang 2; Zhang, Baopeng 1; Fan, Jianping 3
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
	2020
卷号	29 页码:1762-1775
通讯作者	Xing, Junliang(jlxing@nlpr.ia.ac.cn)
摘要	There are two key components that can be leveraged for visual tracking: (a) object appearances; and (b) object motions. Many existing techniques have recently employed deep learning to enhance visual tracking due to its superior representation power and strong learning ability, where most of them employed object appearances but few of them exploited object motions. In this work, a deep spatial and temporal network (DSTN) is developed for visual tracking by explicitly exploiting both the object representations from each frame and their dynamics along multiple frames in a video, such that it can seamlessly integrate the object appearances with their motions to produce compact object appearances and capture their temporal variations effectively. Our DSTN method, which is deployed into a tracking pipeline in a coarse-to-fine form, can perceive the subtle differences on spatial and temporal variations of the target (object being tracked), and thus it benefits from both off-line training and online fine-tuning. We have also conducted our experiments over four largest tracking benchmarks, including OTB-2013, OTB-2015, VOT2015, and VOT2017, and our experimental results have demonstrated that our DSTN method can achieve competitive performance as compared with the state-of-the-art techniques. The source code, trained models, and all the experimental results of this work will be made public available to facilitate further studies on this problem.
关键词	Target tracking Visualization Biological system modeling Correlation Training Benchmark testing Visual tracking deep network spatial-temporal LSTM
DOI	10.1109/TIP.2019.2942502
收录类别	SCI
语种	英语
资助项目	Natural Science Foundation of China[61972027] ; Natural Science Foundation of China[61672519] ; Natural Science Foundation of China[61872035] ; Fundamental Research Funds for the Central Universities of China[2019JBM022] ; Natural Science Foundation of China[61972027] ; Natural Science Foundation of China[61672519] ; Natural Science Foundation of China[61872035] ; Fundamental Research Funds for the Central Universities of China[2019JBM022]
项目资助者	Natural Science Foundation of China ; Fundamental Research Funds for the Central Universities of China
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000501324900008
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类	图像视频处理与分析
引用统计	被引频次：13[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/29340
专题	复杂系统认知与决策实验室_智能系统与工程
通讯作者	Xing, Junliang
作者单位	1.Beijing Jiaotong Univ, Sch Comp & Informat Technol, Beijing 100044, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Univ North Carolina Charlotte, Dept Comp Sci, Charlotte, NC 28223 USA
通讯作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Teng, Zhu,Xing, Junliang,Wang, Qiang,et al. Deep Spatial and Temporal Network for Robust Visual Object Tracking[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2020,29:1762-1775.
APA	Teng, Zhu,Xing, Junliang,Wang, Qiang,Zhang, Baopeng,&Fan, Jianping.(2020).Deep Spatial and Temporal Network for Robust Visual Object Tracking.IEEE TRANSACTIONS ON IMAGE PROCESSING,29,1762-1775.
MLA	Teng, Zhu,et al."Deep Spatial and Temporal Network for Robust Visual Object Tracking".IEEE TRANSACTIONS ON IMAGE PROCESSING 29(2020):1762-1775.