Richly Activated Graph Convolutional Network for Action Recognition with Incomplete Skeletons | |
Song, Yi-Fan1,2,3; Zhang, Zhang1,2,3; Wang, Liang1,2,3 | |
2019-09 | |
会议名称 | International Conference on Image Processing |
会议日期 | 2019.09.22 -- 2019.09.25 |
会议地点 | Taipei, Taiwan, China |
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. |
关键词 | Action Recognition Skeleton Data Graph Convolutional Network Activation Maps Occlusion |
DOI | 10.1109/ICIP.2019.8802917 |
URL | 查看原文 |
语种 | 英语 |
七大方向——子方向分类 | 目标检测、跟踪与识别 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44957 |
专题 | 模式识别实验室 |
通讯作者 | Song, Yi-Fan |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS) 2.Institute of Automation, Chinese Academy of Sciences (CASIA) 3.Center for Research on Intelligent Perception and Computing (CRIPAC) |
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 | Song, Yi-Fan,Zhang, Zhang,Wang, Liang. Richly Activated Graph Convolutional Network for Action Recognition with Incomplete Skeletons[C],2019. |
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-GCNv1.pdf(1048KB) | 会议论文 | 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