Action Machine: Toward Person-Centric Action Recognition in Videos
文献类型：期刊论文
| 作者 | Zhu, Jiagang1,2 ; Zou, Wei1,2; Zhu, Zheng1,2; Xu, Liang3; Huang, Guan3
|
| 刊名 | IEEE SIGNAL PROCESSING LETTERS
 |
| 出版日期 | 2019-11-01 |
| 卷号 | 26期号:11页码:1633-1637 |
| 关键词 | Pose estimation Videos Two dimensional displays Heating systems Training Magnetic heads Head Video action recognition deep learning pose estimation |
| ISSN号 | 1070-9908 |
| DOI | 10.1109/LSP.2019.2942739 |
| 通讯作者 | Zou, Wei(wei.zou@ia.ac.cn) |
| 英文摘要 | Existing RGB and CNN-based methods in video action recognition mostly do not distinguish human body from the environment, thus easily overfit the scenes and objects of training sets. In this work, we present a conceptually simple, general and high-performance framework for action recognition in videos, aiming at person-centric modeling. The method, called Action Machine, is based on person bounding boxes for instance-level action analysis. It extends the Inflated 3D ConvNet (I3D) by adding a branch for human pose estimation and a 2D CNN for pose-based action recognition. Action Machine can benefit from the multi-task training of action recognition and pose estimation, the fusion of predictions from RGB images and poses. Experiments results are provided on trimmed video action datasets, NTU RGB+D, Northwestern UCLA Multiview Action3D, MSR Daily Activity3D. Action Machine achieves superior performance and generalizes well across datasets. |
| 资助项目 | National Key Research and Development Program of China[2017YFB1300104] ; National Natural Science Foundation of China[61773374] |
| WOS研究方向 | Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:000492999700003 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Key Research and Development Program of China ; National Natural Science Foundation of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/28874]  |
| 专题 | 精密感知与控制研究中心_精密感知与控制 |
| 通讯作者 | Zou, Wei |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100190, Peoples R China 3.Horozon Robot Co Ltd, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhu, Jiagang,Zou, Wei,Zhu, Zheng,et al. Action Machine: Toward Person-Centric Action Recognition in Videos[J]. IEEE SIGNAL PROCESSING LETTERS,2019,26(11):1633-1637. |
| APA | Zhu, Jiagang,Zou, Wei,Zhu, Zheng,Xu, Liang,&Huang, Guan.(2019).Action Machine: Toward Person-Centric Action Recognition in Videos.IEEE SIGNAL PROCESSING LETTERS,26(11),1633-1637. |
| MLA | Zhu, Jiagang,et al."Action Machine: Toward Person-Centric Action Recognition in Videos".IEEE SIGNAL PROCESSING LETTERS 26.11(2019):1633-1637. |
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。