CASIA OpenIR  > 智能感知与计算
Part-aligned pose-guided recurrent network for action recognition
Huang, Linjiang1,2; Huang, Yan1,2; Ouyang, Wanli4; Wang, Liang1,2,3
Source PublicationPATTERN RECOGNITION
ISSN0031-3203
2019-08-01
Volume92Issue:1Pages:165-176
Abstract

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 (P2RN) 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.

KeywordAction recognition Part alignment Auto-transformer attention
DOI10.1016/j.patcog.2019.03,010
WOS KeywordAction Recognition ; Human Pose ; Part Alignment
Indexed BySCI
Language英语
Funding ProjectBeijing Science and Technology Project[Z181100008918010] ; Capital Science and Technology Leading Talent Training Project[Z181100006318030] ; National Natural Science Foundation of China[61806194] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[61420106015] ; National Natural Science Foundation of China[61633021] ; National Natural Science Foundation of China[61525306] ; National Key Research and Development Program of China[2016YFB1001000] ; 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[61420106015] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[61806194] ; Capital Science and Technology Leading Talent Training Project[Z181100006318030] ; Beijing Science and Technology Project[Z181100008918010]
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS IDWOS:000468013000014
PublisherELSEVIER SCI LTD
Citation statistics
Cited Times:7[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/24249
Collection智能感知与计算
Corresponding AuthorWang, Liang
Affiliation1.University of Chinese Academy of Sciences
2.Center for Research on Intelligent Perception and Computing, National Laboratory of Pattern Recognition
3.Center for Excellence in Brain Science and Intelligence Technology, Institute of Automation, Chinese Academy of Sciences
4.University of Sydney
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
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(1):165-176.
APA Huang, Linjiang,Huang, Yan,Ouyang, Wanli,&Wang, Liang.(2019).Part-aligned pose-guided recurrent network for action recognition.PATTERN RECOGNITION,92(1),165-176.
MLA Huang, Linjiang,et al."Part-aligned pose-guided recurrent network for action recognition".PATTERN RECOGNITION 92.1(2019):165-176.
Files in This Item: Download All
File Name/Size DocType Version Access License
Part-aligned pose-gu(2555KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Huang, Linjiang]'s Articles
[Huang, Yan]'s Articles
[Ouyang, Wanli]'s Articles
Baidu academic
Similar articles in Baidu academic
[Huang, Linjiang]'s Articles
[Huang, Yan]'s Articles
[Ouyang, Wanli]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Huang, Linjiang]'s Articles
[Huang, Yan]'s Articles
[Ouyang, Wanli]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Part-aligned pose-guided recurrent network for action recognition.pdf
Format: Adobe PDF
This file does not support browsing at this time
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.