CASIA OpenIR  > 智能感知与计算研究中心
Learning robust representations using recurrent neural networks for skeleton based action classification and detection
Wang Hongsong(王洪松)1,2,3,4; Liang Wang(王亮)1,2,3,4
2017
会议名称IEEE International Conference on Multimedia & Expo(ICME) Workshops
会议日期10-14 July 2017
会议地点Hong Kong
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.
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/19625
专题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],2017.
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
LEARNING ROBUST REPR(473KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Wang Hongsong(王洪松)]的文章
[Liang Wang(王亮)]的文章
百度学术
百度学术中相似的文章
[Wang Hongsong(王洪松)]的文章
[Liang Wang(王亮)]的文章
必应学术
必应学术中相似的文章
[Wang Hongsong(王洪松)]的文章
[Liang Wang(王亮)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: LEARNING ROBUST REPRESENTATIONS USING RECURRENT NEURAL NETWORKS FOR SKELETON BASED ACTION CLASSIFICATION A ND DETECTION.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。