Joint spatial-temporal attention for action recognition
文献类型：期刊论文
| 作者 | Yu, Tingzhao1,2 ; Guo, Chaoxu1,2; Wang, Lingfeng1; Gu, Huxiang1; Xiang, Shiming1; Pan, Chunhong1
|
| 刊名 | PATTERN RECOGNITION LETTERS
 |
| 出版日期 | 2018-09-01 |
| 卷号 | 112页码:226-233 |
| 关键词 | Action Recognition Spatial-temporal Attention Two-stage |
| ISSN号 | 0167-8655 |
| DOI | 10.1016/j.patrec.2018.07.034 |
| 文献子类 | Article |
| 英文摘要 | 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. |
| WOS关键词 | REPRESENTATION |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:000443950800033 |
| 出版者 | ELSEVIER SCIENCE BV |
| 资助机构 | National Natural Science Foundation of China(61773377 ; 61573352 ; 91646207 ; 91438105) |
| 源URL | [http://ir.ia.ac.cn/handle/173211/27906]  |
| 专题 | 自动化研究所_模式识别国家重点实验室_遥感图像处理团队 |
| 通讯作者 | Yu, Tingzhao |
| 作者单位 | 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 |
| 推荐引用方式 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. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。