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. 复杂系统认知与决策实验室
  5. 类脑芯片与系统研究
Skeleton-Based Action Recognition With Gated Convolutional Neural Networks

文献类型：期刊论文

作者Cao, Congqi2; Lan, Cuiling1; Zhang, Yifan2,3,4; Zeng, Wenjun1; Lu, Hanqing3,4; Zhang, Yanning
刊名IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
出版日期2019-11-01
卷号29期号:11页码:3247-3257
关键词Skeleton Logic gates Task analysis Recurrent neural networks Matrix converters Three-dimensional displays Convolutional neural networks Skeleton action recognition gated connection convolutional neural networks
ISSN号1051-8215
DOI10.1109/TCSVT.2018.2879913
通讯作者Cao, Congqi(congqi.cao@nwpu.edu.cn) ; Lan, Cuiling(culan@microsoft.com) ; Zhang, Yifan(yfzhang@nlpr.ia.ac.cn)
英文摘要For skeleton-based action recognition, most of the existing works used recurrent neural networks. Using convolutional neural networks (CNNs) is another attractive solution considering their advantages in parallelization, effectiveness in feature learning, and model base sufficiency. Besides these, skeleton data are low-dimensional features. It is natural to arrange a sequence of skeleton features chronologically into an image, which retains the original information. Therefore, we solve the sequence learning problem as an image classification task using CNNs. For better learning ability, we build a classification network with stacked residual blocks and having a special design called linear skip gated connection which can benefit information propagation across multiple residual blocks. When arranging the coordinates of body joints in one frame into a skeleton feature, we systematically investigate the performance of part-based, chain-based, and traversal-based orders. Furthermore, a fully convolutional permutation network is designed to learn an optimized order for data rearrangement. Without any bells and whistles, our proposed model achieves state-of-the-art performance on two challenging benchmark datasets, outperforming existing methods significantly.
资助项目Fundamental Research Funds for the Central Universities[31020180QD138]
WOS研究方向Engineering
语种英语
WOS记录号WOS:000494710600008
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构Fundamental Research Funds for the Central Universities
源URL[http://ir.ia.ac.cn/handle/173211/28838]  
专题类脑芯片与系统研究
通讯作者Cao, Congqi; Lan, Cuiling; Zhang, Yifan
作者单位1.Microsoft Res Asia, Beijing 100080, Peoples R China
2.Northwestern Polytech Univ, Sch Comp Sci, Xian 710129, Shaanxi, Peoples R China
3.Univ Chinese Acad Sci, Beijing 100190, Peoples R China
4.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Cao, Congqi,Lan, Cuiling,Zhang, Yifan,et al. Skeleton-Based Action Recognition With Gated Convolutional Neural Networks[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2019,29(11):3247-3257.
APA Cao, Congqi,Lan, Cuiling,Zhang, Yifan,Zeng, Wenjun,Lu, Hanqing,&Zhang, Yanning.(2019).Skeleton-Based Action Recognition With Gated Convolutional Neural Networks.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,29(11),3247-3257.
MLA Cao, Congqi,et al."Skeleton-Based Action Recognition With Gated Convolutional Neural Networks".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 29.11(2019):3247-3257.

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。