中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 智能感知与计算研究中心
Skeleton-based action recognition with hierarchical spatial reasoning and temporal stack learning network

文献类型：期刊论文

作者Si, Chenyang1,2,3; Jing, Ya1,2,3; Wang, Wei1,2,3; Wang, Liang1,2,3; Tan, Tieniu1,2,3
刊名PATTERN RECOGNITION
出版日期2020-11-01
卷号107页码:12
关键词Skeleton-based action recognition Hierarchical spatial reasoning Temporal stack learning Clip-based incremental loss
ISSN号0031-3203
DOI10.1016/j.patcog.2020.107511
通讯作者Wang, Wei(wangwei@nlpr.ia.ac.cn)
英文摘要Skeleton-based action recognition aims to recognize human actions by exploring the inherent characteristics from the given skeleton sequences and has attracted far more attention due to its great important potentials in practical applications. Previous methods have illustrated that learning discriminative spatial and temporal features from the skeleton sequences is a crucial factor to recognize human actions. Nevertheless, how to model spatio-temporal evolutions is still a challenging problem. In this work, we propose a novel model with hierarchical spatial reasoning and temporal stack learning network (HSR-TSL) to explore the discriminative spatial and temporal features for human action recognition, which consists of a hierarchical spatial reasoning network (HSRN) and a temporal stack learning network (TSLN). Specifically, the HSRN employs a hierarchical residual graph neural network to capture two-level spatial features: intra spatial information of each part and body-level structural information between each part. The TSLN models the detailed temporal dynamics of skeleton sequences by a composition of multiple skip-clip LSTMs. During training, we develop a clip-based incremental loss to effectively optimize the model. We perform extensive experiments on five challenging benchmarks to verify the effectiveness of each component of our model. The comparison results illustrate that our approach significantly boosts the performances for skeleton-based action recognition. (C) 2020 Elsevier Ltd. All rights reserved.
资助项目National Key Research and Development Program of China[2016YFB1001000] ; National Natural Science Foundation of China[61420106015] ; National Natural Science Foundation of China[61976214] ; National Natural Science Foundation of China[61721004] ; Shandong Provincial Key Research and Development Program (Major Scientific and Technological Innovation Project)[2019JZZY010119]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000552866000052
出版者ELSEVIER SCI LTD
资助机构National Key Research and Development Program of China ; National Natural Science Foundation of China ; Shandong Provincial Key Research and Development Program (Major Scientific and Technological Innovation Project)
源URL[http://ir.ia.ac.cn/handle/173211/40283]  
专题自动化研究所_智能感知与计算研究中心
通讯作者Wang, Wei
作者单位1.Univ Chinese Acad Sci UCAS, Beijing, Peoples R China
2.Natl Lab Pattern Recognit NLPR, Ctr Res Intelligent Percept & Comp CRIPAC, Beijing, Peoples R China
3.Chinese Acad Sci CASIA, Inst Automat, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Si, Chenyang,Jing, Ya,Wang, Wei,et al. Skeleton-based action recognition with hierarchical spatial reasoning and temporal stack learning network[J]. PATTERN RECOGNITION,2020,107:12.
APA Si, Chenyang,Jing, Ya,Wang, Wei,Wang, Liang,&Tan, Tieniu.(2020).Skeleton-based action recognition with hierarchical spatial reasoning and temporal stack learning network.PATTERN RECOGNITION,107,12.
MLA Si, Chenyang,et al."Skeleton-based action recognition with hierarchical spatial reasoning and temporal stack learning network".PATTERN RECOGNITION 107(2020):12.

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。