Richly Activated Graph Convolutional Network for Robust Skeleton-Based Action Recognition | |
Song, Yi-Fan1![]() ![]() ![]() | |
发表期刊 | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
![]() |
ISSN | 1051-8215 |
2021-05-01 | |
卷号 | 31期号:5页码:1915-1925 |
摘要 | Current methods for skeleton-based human action recognition usually work with complete skeletons. However, in real scenarios, it is inevitable to capture incomplete or noisy skeletons, which could significantly deteriorate the performance of current methods when some informative joints are occluded or disturbed. To improve the robustness of action recognition models, a multi-stream graph convolutional network (GCN) is proposed to explore sufficient discriminative features spreading over all skeleton joints, so that the distributed redundant representation reduces the sensitivity of the action models to non-standard skeletons. Concretely, the backbone GCN is extended by a series of ordered streams which is responsible for learning discriminative features from the joints less activated by preceding streams. Here, the activation degrees of skeleton joints of each GCN stream are measured by the class activation maps (CAM), and only the information from the unactivated joints will be passed to the next stream, by which rich features over all active joints are obtained. Thus, the proposed method is termed richly activated GCN (RA-GCN). Compared to the state-of-the-art (SOTA) methods, the RA-GCN achieves comparable performance on the standard NTU RGB+D 60 and 120 datasets. More crucially, on the synthetic occlusion and jittering datasets, the performance deterioration due to the occluded and disturbed joints can be significantly alleviated by utilizing the proposed RA-GCN. |
关键词 | Skeleton Robustness Noise measurement Three-dimensional displays Degradation Standards Feature extraction Action recognition skeleton activation map graph convolutional network occlusion jittering |
DOI | 10.1109/TCSVT.2020.3015051 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Key Research and Development Program of China[2016YFB1001002] ; National Natural Science Foundation of China[61525306] ; National Natural Science Foundation of China[61633021] ; National Natural Science Foundation of China[61721004] ; Shandong Provincial Key Research and Development Program (Major Scientific and Technological Innovation Project)[2019JZZY010119] ; Artificial Intelligence Research, Chinese Academy of Sciences (CAS-AIR)[2019-001] |
项目资助者 | National Key Research and Development Program of China ; National Natural Science Foundation of China ; Shandong Provincial Key Research and Development Program (Major Scientific and Technological Innovation Project) ; Artificial Intelligence Research, Chinese Academy of Sciences (CAS-AIR) |
WOS研究方向 | Engineering |
WOS类目 | Engineering, Electrical & Electronic |
WOS记录号 | WOS:000647394100019 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
七大方向——子方向分类 | 机器学习 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44643 |
专题 | 模式识别实验室 |
通讯作者 | Zhang, Zhang |
作者单位 | 1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 3.Shandong Univ Sci & Technol, Coll Elect Engn & Automat, Qingdao 266590, Peoples R China |
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 | Song, Yi-Fan,Zhang, Zhang,Shan, Caifeng,et al. Richly Activated Graph Convolutional Network for Robust Skeleton-Based Action Recognition[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2021,31(5):1915-1925. |
APA | Song, Yi-Fan,Zhang, Zhang,Shan, Caifeng,&Wang, Liang.(2021).Richly Activated Graph Convolutional Network for Robust Skeleton-Based Action Recognition.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,31(5),1915-1925. |
MLA | Song, Yi-Fan,et al."Richly Activated Graph Convolutional Network for Robust Skeleton-Based Action Recognition".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 31.5(2021):1915-1925. |
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 | ||
RA-GCNv2.pdf(3381KB) | 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