Graph convolutional network with structure pooling and joint-wise channel attention for action recognition

doi:10.1016/j.patcog.2020.107321

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 视频内容安全

	Graph convolutional network with structure pooling and joint-wise channel attention for action recognition
	Chen, Yuxin1 ; Ma, Gaoqun 2; Yuan, Chunfeng1 ; Li, Bing1 ; Zhang, Hui 5; Wang, Fangshi 2; Hu, Weiming1,3,4
发表期刊	PATTERN RECOGNITION
ISSN	0031-3203
	2020-07-01
卷号	103 页码:12
通讯作者	Yuan, Chunfeng(cfyuan@nlpr.ia.ac.cn) ; Li, Bing(bli@nlpr.ia.ac.cn)
摘要	Recently, graph convolutional networks (GCNs) have achieved state-of-the-art results for skeleton based action recognition by expanding convolutional neural networks (CNNs) to graphs. However, due to the lack of effective feature aggregation method, e.g. max pooling in CNN, existing GCN-based methods only learn local information among adjacent joints and are hard to obtain high-level interaction features, such as interactions between five parts of human body. Moreover, subtle differences of confusing actions often hide in specific channels of key joints' features, this kind of discriminative information is rarely exploited in previous methods. In this paper, we propose a novel graph convolutional network with structure based graph pooling (SGP) scheme and joint-wise channel attention UCA) modules. The SGP scheme pools the human skeleton graph according to the prior knowledge of human body's typology. This pooling scheme not only leads to more global representations but also reduces the amount of parameters and computation cost. The JCA module learns to selectively focus on discriminative joints of skeleton and pays different levels of attention to different channels. This novel attention mechanism enhance the model's ability to classify confusing actions. We evaluate our SGP scheme and JCA module on three most challenging skeleton based action recognition datasets: NTU-RGB+D, Kinetics-M, and SYSU-3D. Our method outperforms the state-of-art methods on three benchmarks. (C) 2020 Elsevier Ltd. All rights reserved.
关键词	Graph convolutional network Structure graph pooling Joint-wise channel attention
DOI	10.1016/j.patcog.2020.107321
收录类别	SCI
语种	英语
资助项目	National Key RD Plan[2017YFB1-002801] ; National Key RD Plan[2016QY01W0106] ; Natural Science Foundation of China[U1803119] ; Natural Science Foundation of China[U1736106] ; Natural Science Foundation of China[61751212] ; Natural Science Foundation of China[61721004] ; Natural Science Foundation of China[61972397] ; Natural Science Foundation of China[61772225] ; NSFC-General Technology Collaborative Fund for Basic Research[U1636218] ; Key Research Program of Frontier Sciences, CAS[YZDJSSW-JSC040] ; Beijing Natural Science Foundation[JQ18018] ; Beijing Natural Science Foundation[L172051] ; Beijing Natural Science Foundation[L182058] ; CAS External Cooperation Key Project ; Youth Innovation Promotion Association, CAS
项目资助者	National Key RD Plan ; Natural Science Foundation of China ; NSFC-General Technology Collaborative Fund for Basic Research ; Key Research Program of Frontier Sciences, CAS ; Beijing Natural Science Foundation ; CAS External Cooperation Key Project ; Youth Innovation Promotion Association, CAS
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000530845000048
出版者	ELSEVIER SCI LTD
七大方向——子方向分类	图像视频处理与分析
引用统计	被引频次：44[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/39473
专题	多模态人工智能系统全国重点实验室_视频内容安全
通讯作者	Yuan, Chunfeng; Li, Bing
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Beijing Jiaotong Univ, Sch Software Engn, Beijing 100044, Peoples R China 3.CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing 100190, Peoples R China 4.Univ Chinese Acad Sci, Beijing 100190, Peoples R China 5.Chinese Acad Sci, Inst Informat Engn, Beijing 100093, Peoples R China
第一作者单位	模式识别国家重点实验室
通讯作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Chen, Yuxin,Ma, Gaoqun,Yuan, Chunfeng,et al. Graph convolutional network with structure pooling and joint-wise channel attention for action recognition[J]. PATTERN RECOGNITION,2020,103:12.
APA	Chen, Yuxin.,Ma, Gaoqun.,Yuan, Chunfeng.,Li, Bing.,Zhang, Hui.,...&Hu, Weiming.(2020).Graph convolutional network with structure pooling and joint-wise channel attention for action recognition.PATTERN RECOGNITION,103,12.
MLA	Chen, Yuxin,et al."Graph convolutional network with structure pooling and joint-wise channel attention for action recognition".PATTERN RECOGNITION 103(2020):12.