中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Richly Activated Graph Convolutional Network for Action Recognition with Incomplete Skeletons

文献类型:会议论文

作者Song, Yi-Fan1,2,3; Zhang, Zhang1,2,3; Wang, Liang1,2,3
出版日期2019-09
会议日期2019.09.22 -- 2019.09.25
会议地点Taipei, Taiwan, China
关键词Action Recognition Skeleton Data Graph Convolutional Network Activation Maps Occlusion
DOI10.1109/ICIP.2019.8802917
英文摘要

Current methods for skeleton-based human action recognition usually work with completely observed skeletons. However, in real scenarios, it is prone to capture incomplete and noisy skeletons, which will deteriorate the performance of traditional models. To enhance the robustness of action recognition models to incomplete skeletons, we propose a multi-stream graph convolutional network (GCN) for exploring sufficient discriminative features distributed over all skeleton joints. Here, each stream of the network is only responsible for learning features from currently unactivated joints, which are distinguished by the class activation maps (CAM) obtained by preceding streams, so that the activated joints of the proposed method are obviously more than traditional methods. Thus, the proposed method is termed richly activated GCN (RA-GCN), where the richly discovered features will improve the robustness of the model. Compared to the state-of-the-art methods, the RA-GCN achieves comparable performance on the NTU RGB+D dataset. Moreover, on a synthetic occlusion dataset, the performance deterioration can be alleviated by the RA-GCN significantly.

语种英语
URL标识查看原文
源URL[http://ir.ia.ac.cn/handle/173211/44957]  
专题自动化研究所_智能感知与计算研究中心
通讯作者Song, Yi-Fan
作者单位1.Center for Research on Intelligent Perception and Computing (CRIPAC)
2.Institute of Automation, Chinese Academy of Sciences (CASIA)
3.School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS)
推荐引用方式
GB/T 7714
Song, Yi-Fan,Zhang, Zhang,Wang, Liang. Richly Activated Graph Convolutional Network for Action Recognition with Incomplete Skeletons[C]. 见:. Taipei, Taiwan, China. 2019.09.22 -- 2019.09.25.

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。