Skeleton-Based Action Recognition With Gated Convolutional Neural Networks

doi:10.1109/TCSVT.2018.2879913

	Skeleton-Based Action Recognition With Gated Convolutional Neural Networks
	Cao, Congqi 4; Lan, Cuiling 3; Zhang, Yifan 1,2,4; Zeng, Wenjun 3; Lu, Hanqing 1,2; Zhang, Yanning
刊名	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
	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
DOI	10.1109/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
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000494710600008
资助机构	Fundamental Research Funds for the Central Universities
内容类型	期刊论文
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.Univ Chinese Acad Sci, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China 3.Microsoft Res Asia, Beijing 100080, Peoples R China 4.Northwestern Polytech Univ, Sch Comp Sci, Xian 710129, Shaanxi, 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.