Efficient spatiotemporal context modeling for action recognition

doi:10.1016/j.neucom.2023.126289

CASIA OpenIR > 智能感知与计算研究中心

	Efficient spatiotemporal context modeling for action recognition
	Cao, Congqi1,3,4 ; Lu, Yue1 ; Zhang, Yifan2,5,6 ; Jiang, Dongmei 1; Zhang, Yanning 1
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
	2023-08-07
卷号	545 页码:13
通讯作者	Cao, Congqi(congqi.cao@nwpu.edu.cn)
摘要	Contextual information is essential in action recognition. However, local operations have difficulty in modeling two distant elements, and directly computing the dense relations between any two points brings huge computation and memory burden. Inspired by the recurrent 2D criss-cross attention (RCCA-2D) in image segmentation, we propose a recurrent 3D criss-cross attention (RCCA-3D) that factorizes the global relation map into sparse relation maps to model long-range spatiotemporal context with minor costs for video-based action recognition. Specifically, we first propose a 3D criss-cross attention (CCA-3D) module. Compared with the CCA-2D which only works in space, it can capture the spatiotemporal relationship between the points in the same line along the direction of width, height and time. However, only replacing the two CCA-2Ds in the RCCA-2D with our CCA-3Ds cannot model the spatiotemporal context in videos. Therefore, we further duplicate the CCA-3D with a recurrent mechanism to transmit the relation between the points in a line to a plane and finally to the whole spatiotemporal space. To make the RCCA-3D adaptive for action recognition, we propose a novel recurrent structure rather than directly extending the original 2D structure to 3D. In the experiments, we make a thorough analysis of different structures of RCCA-3D, verifying the proposed structure is more suitable for action recognition. We also compare our RCCA-3D with the non-local attention, showing that the RCCA-3D requires 25% fewer parameters and 30% fewer FLOPs with even higher accuracy. Finally, equipped with our RCCA-3D, 3 networks achieve better and leading performance on 5 RGB-based and skeleton-based datasets.
关键词	Action recognition Long -range context modeling Spatiotemporal feature map Attention module Relation
DOI	10.1016/j.neucom.2023.126289
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[U19B2037] ; National Natural Science Foundation of China[62273347] ; National Natural Science Foundation of China[61906155] ; National Key R&D Program of China[2020AAA0106900] ; Key R&D Project in Shaanxi Province[2023-YBGY-240] ; Young Talent Fund of Association for Science and Technology in Shaanxi, China[20220117]
项目资助者	National Natural Science Foundation of China ; National Key R&D Program of China ; Key R&D Project in Shaanxi Province ; Young Talent Fund of Association for Science and Technology in Shaanxi, China
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:001000901900001
出版者	ELSEVIER
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/53433
专题	智能感知与计算研究中心
通讯作者	Cao, Congqi
作者单位	1.Northwestern Polytech Univ, Sch Comp Sci, Xian, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China 3.Northwestern Polytech Univ, Natl Engn Lab Integrated Aerosp Ground Ocean Big D, Xian 710129, Peoples R China 4.Northwestern Polytech Univ, Sch Comp Sci, Shaanxi Prov Key Lab Speech & Image Informat Proc, Xian 710129, Peoples R China 5.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 6.Univ Chinese Acad Sci, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Cao, Congqi,Lu, Yue,Zhang, Yifan,et al. Efficient spatiotemporal context modeling for action recognition[J]. NEUROCOMPUTING,2023,545:13.
APA	Cao, Congqi,Lu, Yue,Zhang, Yifan,Jiang, Dongmei,&Zhang, Yanning.(2023).Efficient spatiotemporal context modeling for action recognition.NEUROCOMPUTING,545,13.
MLA	Cao, Congqi,et al."Efficient spatiotemporal context modeling for action recognition".NEUROCOMPUTING 545(2023):13.