Modeling Temporal Interactions with Interval Temporal Bayesian Networks for Complex Activity Recognition

	Modeling Temporal Interactions with Interval Temporal Bayesian Networks for Complex Activity Recognition
	Zhang, Yongmian 1; Zhang, Yifan2,3 ; Swears, Eran 4; Larios, Natalia 4; Wang, Ziheng 4; Ji, Qiang 4
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
	2013-10-01
卷号	35 期号:10 页码:2468-2483
文章类型	Article
摘要	Complex activities typically consist of multiple primitive events happening in parallel or sequentially over a period of time. Understanding such activities requires recognizing not only each individual event but, more importantly, capturing their spatiotemporal dependencies over different time intervals. Most of the current graphical model-based approaches have several limitations. First, time-sliced graphical models such as hidden Markov models (HMMs) and dynamic Bayesian networks are typically based on points of time and they hence can only capture three temporal relations: precedes, follows, and equals. Second, HMMs are probabilistic finite-state machines that grow exponentially as the number of parallel events increases. Third, other approaches such as syntactic and description-based methods, while rich in modeling temporal relationships, do not have the expressive power to capture uncertainties. To address these issues, we introduce the interval temporal Bayesian network (ITBN), a novel graphical model that combines the Bayesian Network with the interval algebra to explicitly model the temporal dependencies over time intervals. Advanced machine learning methods are introduced to learn the ITBN model structure and parameters. Experimental results show that by reasoning with spatiotemporal dependencies, the proposed model leads to a significantly improved performance when modeling and recognizing complex activities involving both parallel and sequential events.
关键词	Activity Recognition Temporal Reasoning Bayesian Networks Interval Temporal Bayesian Networks
WOS标题词	Science & Technology ; Technology
关键词[WOS]	EVENT RECOGNITION ; REPRESENTATION ; TRACKING ; VIDEO ; KNOWLEDGE ; FRAMEWORK
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000323175200012
引用统计	被引频次：53[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/173211/3354
专题	紫东太初大模型研究中心_图像与视频分析
作者单位	1.Konica Minolta Lab USA Inc, IT Res Div, San Mateo, CA 94403 USA 2.Rensselaer Polytech Inst, Dept Elect Comp & Syst Engn, Troy, NY 12180 USA 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 4.Rensselaer Polytech Inst, Dept Elect Comp & Syst Engn, Troy, NY 12180 USA
推荐引用方式 GB/T 7714	Zhang, Yongmian,Zhang, Yifan,Swears, Eran,et al. Modeling Temporal Interactions with Interval Temporal Bayesian Networks for Complex Activity Recognition[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2013,35(10):2468-2483.
APA	Zhang, Yongmian,Zhang, Yifan,Swears, Eran,Larios, Natalia,Wang, Ziheng,&Ji, Qiang.(2013).Modeling Temporal Interactions with Interval Temporal Bayesian Networks for Complex Activity Recognition.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,35(10),2468-2483.
MLA	Zhang, Yongmian,et al."Modeling Temporal Interactions with Interval Temporal Bayesian Networks for Complex Activity Recognition".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 35.10(2013):2468-2483.