Progressive Relation Learning for Group Activity Recognition | |
Guyue, Hu1,3; Bo, Cui1,3; Yuan, He1,3; Shan, Yu1,2,3 | |
2020 | |
会议名称 | IEEE Conference on Computer Vision and Pattern Recognition |
页码 | 977-986 |
会议日期 | JUN 14-19, 2020 |
会议地点 | ELECTR NETWORK |
摘要 | Group activities usually involve spatiotemporal dynamics among many interactive individuals, while only a few participants at several key frames essentially define the activity. Therefore, effectively modeling the group-relevant and suppressing the irrelevant actions (and interactions) are vital for group activity recognition. In this paper, we propose a novel method based on deep reinforcement learning to progressively refine the low-level features and high-level relations of group activities. Firstly, we construct a semantic relation graph (SRG) to explicitly model the relations among persons. Then, two agents adopting policy according to two Markov decision processes are applied to progressively refine the SRG. Specifically, one featured-istilling (FD) agent in the discrete action space refines the low-level spatiotemporal features by distilling the most informative frames. Another relation-gating (RG) agent in continuous action space adjusts the high-level semantic graph to pay more attention to group-relevant relations. The SRG, FD agent, and RG agent are optimized alternately to mutually boost the performance of each other. Extensive experiments on two widely used benchmarks demonstrate the effectiveness and superiority of the proposed approach. |
DOI | 10.1109/CVPR42600.2020.00106 |
语种 | 英语 |
七大方向——子方向分类 | 脑网络分析 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44319 |
专题 | 脑图谱与类脑智能实验室_脑网络组研究 |
通讯作者 | Guyue, Hu |
作者单位 | 1.Chinese Acad Sci CASIA, Natl Lab Pattern Recognit, Brainnetome Ctr, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing, Peoples R China |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Guyue, Hu,Bo, Cui,Yuan, He,et al. Progressive Relation Learning for Group Activity Recognition[C],2020:977-986. |
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 | ||
[CVPR2020] Progressi(1706KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
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