Learning robust representations using recurrent neural networks for skeleton based action classification and detection | |
Wang Hongsong(王洪松)1,2,3,4![]() | |
2017 | |
会议日期 | 10-14 July 2017 |
会议地点 | Hong Kong |
英文摘要 |
Recently, skeleton based action recognition gains more popularity due to affordable depth sensors and real-time skeleton estimation algorithms. Previous Recurrent Neural Networks (RNN) based approaches focus on modeling spatial configuration of skeletons and temporal evolution of body joints. There are certain intrinsic characteristics of the skeleton based actions. For example, the starting point may be varied, an action can be observed at arbitrary viewpoints and the skeletons are noisy. To this end, we present a novel end-to-end architecture based on RNN to learn robust representations from raw skeletons. The architecture includes three new layers, i.e., starting point transformation layer, viewpoint transformation layer and spatial dropout layer, which address the corresponding three problems, respectively. We apply the proposed method to two different tasks: action classification and detection. Experiments on two large-scale datasets (NTU RGB+D and PKU-MMD) show the superiority of our model. Specially, for action detection, our results are more than 33.4% higher the previous results. |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/19625] ![]() |
专题 | 自动化研究所_智能感知与计算研究中心 |
作者单位 | 1.Center for Research on Intelligent Perception and Computing (CRIPAC) 2.National Laboratory of Pattern Recognition (NLPR) 3.Institute of Automation, Chinese Academy of Sciences (CASIA) 4.University of Chinese Academy of Sciences (UCAS) |
推荐引用方式 GB/T 7714 | Wang Hongsong,Liang Wang. Learning robust representations using recurrent neural networks for skeleton based action classification and detection[C]. 见:. Hong Kong. 10-14 July 2017. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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