中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Learning Content and Style: Joint Action Recognition and Person Identification from Human Skeletons

文献类型:期刊论文

作者Wang Hongsong(王洪松)1,2,3,4; Wang Liang(王亮)1,2,3,4
刊名Pattern Recognition
出版日期2018
期号81页码:23-35
关键词Content And Style Action Recognition Person Identification From Motions Skeleton Transformation Multi-task Rnn
英文摘要
Humans are able to simultaneously identify a person and recognize his or her action based on biological motions. Previous work usually treats action recognition and person identification from motions as two separate tasks with different objectives. In this paper, we present an end-to-end framework to perform these two tasks together. Inspired by the recent success of deep recurrent neural networks (RNN) for skeleton based action recognition, we propose a new pipeline to recognize both actions and persons from skeletons extracted by RGBD sensors. The structure includes two subnets and is end-to-end trainable. The former is skeleton transformation, which accommodates viewpoint changes and noise. The latter is multi-task RNN for joint learning and various architectures are explored including a novel architecture that learns the joint probability between the two output variables. Experiments on 3D action recognition benchmark datasets demonstrate the benefits of multi-task learning and our method dramatically outperforms existing state-of-the-art in action recognition.
源URL[http://ir.ia.ac.cn/handle/173211/21037]  
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,Wang Liang. Learning Content and Style: Joint Action Recognition and Person Identification from Human Skeletons[J]. Pattern Recognition,2018(81):23-35.
APA Wang Hongsong,&Wang Liang.(2018).Learning Content and Style: Joint Action Recognition and Person Identification from Human Skeletons.Pattern Recognition(81),23-35.
MLA Wang Hongsong,et al."Learning Content and Style: Joint Action Recognition and Person Identification from Human Skeletons".Pattern Recognition .81(2018):23-35.

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。