Knowledge Commons of Institute of Automation,CAS
Action Machine: Toward Person-Centric Action Recognition in Videos | |
Zhu, Jiagang1,2; Zou, Wei1,2; Zhu, Zheng1,2; Xu, Liang3; Huang, Guan3 | |
发表期刊 | IEEE SIGNAL PROCESSING LETTERS |
ISSN | 1070-9908 |
2019-11-01 | |
卷号 | 26期号:11页码:1633-1637 |
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. |
关键词 | Pose estimation Videos Two dimensional displays Heating systems Training Magnetic heads Head Video action recognition deep learning pose estimation |
DOI | 10.1109/LSP.2019.2942739 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Key Research and Development Program of China[2017YFB1300104] ; National Natural Science Foundation of China[61773374] ; National Natural Science Foundation of China[61773374] ; National Key Research and Development Program of China[2017YFB1300104] |
WOS研究方向 | Engineering |
WOS类目 | Engineering, Electrical & Electronic |
WOS记录号 | WOS:000492999700003 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
七大方向——子方向分类 | 图像视频处理与分析 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/28875 |
专题 | 中科院工业视觉智能装备工程实验室_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 |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
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. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Action Machine Towar(396KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论