Institutional Repository of Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Joint spatial-temporal attention for action recognition | |
Yu, Tingzhao1,2![]() ![]() ![]() ![]() ![]() ![]() | |
Source Publication | PATTERN RECOGNITION LETTERS
![]() |
ISSN | 0167-8655 |
2018-09-01 | |
Volume | 112Pages:226-233 |
Subtype | Article |
Abstract | In this paper, we propose a novel high-level action representation using joint spatial-temporal attention model, with application to video-based human action recognition. Specifically, to extract robust motion representations of videos, a new spatial attention module based on 3D convolution is proposed, which can pay attention to the salient parts of the spatial areas. For better dealing with long-duration videos, a new bidirectional LSTM based temporal attention module is introduced, which aims to focus on the key video cubes instead of the key video frames of a given video. The spatial-temporal attention network can be jointly trained via a two-stage strategy, which enables us to simultaneously explore the correlation both in spatial and temporal domain. Experimental results on benchmark action recognition datasets demonstrate the effectiveness of our network. (c) 2018 Elsevier B.V. All rights reserved. |
Keyword | Action Recognition Spatial-temporal Attention Two-stage |
WOS Headings | Science & Technology ; Technology |
DOI | 10.1016/j.patrec.2018.07.034 |
WOS Keyword | REPRESENTATION |
Indexed By | SCI |
Language | 英语 |
Funding Organization | National Natural Science Foundation of China(61773377 ; 61573352 ; 91646207 ; 91438105) |
WOS Research Area | Computer Science |
WOS Subject | Computer Science, Artificial Intelligence |
WOS ID | WOS:000443950800033 |
Publisher | ELSEVIER SCIENCE BV |
Citation statistics | |
Document Type | 期刊论文 |
Identifier | http://ir.ia.ac.cn/handle/173211/27907 |
Collection | 模式识别国家重点实验室_先进时空数据分析与学习 |
Corresponding Author | Yu, Tingzhao |
Affiliation | 1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing 101408, Peoples R China |
First Author Affilication | Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China |
Corresponding Author Affilication | Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China |
Recommended Citation GB/T 7714 | Yu, Tingzhao,Guo, Chaoxu,Wang, Lingfeng,et al. Joint spatial-temporal attention for action recognition[J]. PATTERN RECOGNITION LETTERS,2018,112:226-233. |
APA | Yu, Tingzhao,Guo, Chaoxu,Wang, Lingfeng,Gu, Huxiang,Xiang, Shiming,&Pan, Chunhong.(2018).Joint spatial-temporal attention for action recognition.PATTERN RECOGNITION LETTERS,112,226-233. |
MLA | Yu, Tingzhao,et al."Joint spatial-temporal attention for action recognition".PATTERN RECOGNITION LETTERS 112(2018):226-233. |
Files in This Item: | There are no files associated with this item. |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment