Part-aligned pose-guided recurrent network for action recognition

doi:10.1016/j.patcog.2019.03,010

	Part-aligned pose-guided recurrent network for action recognition
	Huang, Linjiang 1,2; Huang, Yan1,2 ; Ouyang, Wanli 4; Wang, Liang1,2,3
刊名	PATTERN RECOGNITION
	2019-08-01
卷号	92 页码:165-176
关键词	Action recognition Part alignment Auto-transformer attention
ISSN号	0031-3203
DOI	10.1016/j.patcog.2019.03,010
通讯作者	Wang, Liang(wangliang@nlpr.ia.ac.cn)
英文摘要	Action recognition using pose information has drawn much attention recently. However, most previous approaches treat human pose as a whole or just use pose to extract robust features. Actually, human body parts play an important role in action, and so modeling spatio-temporal information of body parts can effectively assist in classifying actions. In this paper, we propose a Part-aligned Pose-guided Recurrent Network ((PRN)-R-2) for action recognition. The model mainly consists of two modules, i.e., part alignment module and part pooling module, which are used for part representation learning and part-related feature fusion, respectively. The part-alignment module incorporates an auto-transformer attention, aiming to capture spatial configuration of body parts and predict pose attention maps. While the part pooling module exploits both symmetry and complementarity of body parts to produce fused body representation. The whole network is a recurrent network which can exploit the body representation and simultaneously model spatio-temporal evolutions of human body parts. Experiments on two publicly available benchmark datasets show the state-of-the-art performance and demonstrate the power of the two proposed modules. (C) 2019 Elsevier Ltd. All rights reserved.
资助项目	National Key Research and Development Program of China[2016YFB1001000] ; National Natural Science Foundation of China[61525306] ; National Natural Science Foundation of China[61633021] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[61420106015] ; National Natural Science Foundation of China[61806194] ; Capital Science and Technology Leading Talent Training Project[Z181100006318030] ; Beijing Science and Technology Project[Z181100008918010]
WOS关键词	REPRESENTATION ; HISTOGRAMS
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	ELSEVIER SCI LTD
WOS记录号	WOS:000468013000014
资助机构	National Key Research and Development Program of China ; National Natural Science Foundation of China ; Capital Science and Technology Leading Talent Training Project ; Beijing Science and Technology Project
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/24248]
专题	中国科学院自动化研究所
通讯作者	Wang, Liang
作者单位	1.Univ Chinese Acad Sci, Beijing, Peoples R China 2.NLPR, CRIPAC, Beijing, Peoples R China 3.Chinese Acad Sci CASIA, Inst Automat, Ctr Excellence Brain Sci & Intelligence Technol C, Beijing, Peoples R China 4.Univ Sydney, Sch Elect & Informat Engn, Sydney, NSW, Australia
推荐引用方式 GB/T 7714	Huang, Linjiang,Huang, Yan,Ouyang, Wanli,et al. Part-aligned pose-guided recurrent network for action recognition[J]. PATTERN RECOGNITION,2019,92:165-176.
APA	Huang, Linjiang,Huang, Yan,Ouyang, Wanli,&Wang, Liang.(2019).Part-aligned pose-guided recurrent network for action recognition.PATTERN RECOGNITION,92,165-176.
MLA	Huang, Linjiang,et al."Part-aligned pose-guided recurrent network for action recognition".PATTERN RECOGNITION 92(2019):165-176.