Learning Human Actions by Combining Global Dynamics and Local Appearance

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 视频内容安全团队

	Learning Human Actions by Combining Global Dynamics and Local Appearance
	Luo, Guan1 ; Yang, Shuang1 ; Tian, Guodong 1; Yuan, Chunfeng1 ; Hu, Weiming1 ; Maybank, Stephen J.2
刊名	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
	2014-12-01
卷号	36 期号:12 页码:2466-2482
关键词	Action recognition linear dynamical system local spatio-temporal feature non-vector descriptor distance learning
英文摘要	In this paper, we address the problem of human action recognition through combining global temporal dynamics and local visual spatio-temporal appearance features. For this purpose, in the global temporal dimension, we propose to model the motion dynamics with robust linear dynamical systems (LDSs) and use the model parameters as motion descriptors. Since LDSs live in a non-euclidean space and the descriptors are in non-vector form, we propose a shift invariant subspace angles based distance to measure the similarity between LDSs. In the local visual dimension, we construct curved spatio-temporal cuboids along the trajectories of densely sampled feature points and describe them using histograms of oriented gradients (HOG). The distance between motion sequences is computed with the Chi-Squared histogram distance in the bag-of-words framework. Finally we perform classification using the maximum margin distance learning method by combining the global dynamic distances and the local visual distances. We evaluate our approach for action recognition on five short clips data sets, namely Weizmann, KTH, UCF sports, Hollywood2 and UCF50, as well as three long continuous data sets, namely VIRAT, ADL and CRIM13. We show competitive results as compared with current state-of-the-art methods.
WOS标题词	Science & Technology ; Technology
类目[WOS]	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
研究领域[WOS]	Computer Science ; Engineering
关键词[WOS]	HUMAN ACTION CATEGORIES ; BINET-CAUCHY KERNELS ; TIME INTEREST POINTS ; ACTION RECOGNITION ; HUMAN MOTION ; SUBSPACE IDENTIFICATION ; TEXTURE RECOGNITION ; MODELS ; CLASSIFICATION ; SYSTEMS
收录类别	SCI
语种	英语
WOS记录号	WOS:000344988000011
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/3273]
专题	自动化研究所_模式识别国家重点实验室_视频内容安全团队
作者单位	1.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China 2.Univ London Birkbeck Coll, Dept Comp Sci & Informat Syst, London WC1E 7HX, England
推荐引用方式 GB/T 7714	Luo, Guan,Yang, Shuang,Tian, Guodong,et al. Learning Human Actions by Combining Global Dynamics and Local Appearance[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2014,36(12):2466-2482.
APA	Luo, Guan,Yang, Shuang,Tian, Guodong,Yuan, Chunfeng,Hu, Weiming,&Maybank, Stephen J..(2014).Learning Human Actions by Combining Global Dynamics and Local Appearance.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,36(12),2466-2482.
MLA	Luo, Guan,et al."Learning Human Actions by Combining Global Dynamics and Local Appearance".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 36.12(2014):2466-2482.