Global Instance Tracking: Locating Target More Like Humans

doi:10.1109/TPAMI.2022.3153312

	Global Instance Tracking: Locating Target More Like Humans
	Hu, Shiyu1,2 ; Zhao, Xin2,5 ; Huang, Lianghua2 ; Huang, Kaiqi2,3,4,5,6
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN	0162-8828
	2023
卷号	45 期号:1 页码:576-592
通讯作者	Zhao, Xin(xzhao@nlpr.ia.ac.cn)
摘要	Target tracking, the essential ability of the human visual system, has been simulated by computer vision tasks. However, existing trackers perform well in austere experimental environments but fail in challenges like occlusion and fast motion. The massive gap indicates that researches only measure tracking performance rather than intelligence. How to scientifically judge the intelligence level of trackers? Distinct from decision-making problems, lacking three requirements (a challenging task, a fair environment, and a scientific evaluation procedure) makes it strenuous to answer the question. In this article, we first propose the global instance tracking (GIT) task, which is supposed to search an arbitrary user-specified instance in a video without any assumptions about camera or motion consistency, to model the human visual tracking ability. Whereafter, we construct a high-quality and large-scale benchmark VideoCube to create a challenging environment. Finally, we design a scientific evaluation procedure using human capabilities as the baseline to judge tracking intelligence. Additionally, we provide an online platform with toolkit and an updated leaderboard. Although the experimental results indicate a definite gap between trackers and humans, we expect to take a step forward to generate authentic human-like trackers. The database, toolkit, evaluation server, and baseline results are available at http://videocube.aitestunion.com.
关键词	Global instance tracking single object tracking benchmark dataset performance evaluation human tracking ability
DOI	10.1109/TPAMI.2022.3153312
关键词[WOS]	OBJECT TRACKING
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[61876181] ; Projects of Chinese Academy of Science[QYZDB-SSW-JSC006] ; Strategic Priority Research Program of Chinese Academy of Sciences[XDA27000000] ; Youth Innovation Promotion Association CAS
项目资助者	National Natural Science Foundation of China ; Projects of Chinese Academy of Science ; Strategic Priority Research Program of Chinese Academy of Sciences ; Youth Innovation Promotion Association CAS
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000899419900035
出版者	IEEE COMPUTER SOC
引用统计	被引频次：2[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/173211/51097
专题	复杂系统认知与决策实验室
通讯作者	Zhao, Xin
作者单位	1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Syst & Engn, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Ctr Res Intelligent Syst & Engn, Beijing 100190, Peoples R China 4.Chinese Acad Sci, Inst Automation, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 5.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 6.CAS Ctr Excellence Brain Sci & Intelligence Techno, Beijing 100190, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Hu, Shiyu,Zhao, Xin,Huang, Lianghua,et al. Global Instance Tracking: Locating Target More Like Humans[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2023,45(1):576-592.
APA	Hu, Shiyu,Zhao, Xin,Huang, Lianghua,&Huang, Kaiqi.(2023).Global Instance Tracking: Locating Target More Like Humans.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,45(1),576-592.
MLA	Hu, Shiyu,et al."Global Instance Tracking: Locating Target More Like Humans".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 45.1(2023):576-592.

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
GIT.pdf（15055KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载