Holographic Feature Learning of Egocentric-Exocentric Videos for Multi-Domain Action Recognition

doi:10.1109/TMM.2021.3078882

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 多媒体计算与图形学团队

	Holographic Feature Learning of Egocentric-Exocentric Videos for Multi-Domain Action Recognition
	Huang, Yi 1,2,3; Yang, Xiaoshan 1,2,3; Gao, Junyun 1,2,3; Xu, Changsheng 1,2,3
刊名	IEEE TRANSACTIONS ON MULTIMEDIA
	2022
卷号	24 页码:2273-2286
关键词	Videos Feature extraction Visualization Task analysis Computational modeling Target recognition Prototypes Egocentric videos exocentric videos holographic feature multi-domain action recognition
ISSN号	1520-9210
DOI	10.1109/TMM.2021.3078882
通讯作者	Xu, Changsheng(csxu@nlpr.ia.ac.cn)
英文摘要	Though existing cross-domain action recognition methods successfully improve the performance on videos of one view (e.g., egocentric videos) by transferring the knowledge from videos of another view (e.g., exocentric videos), they have limitations in generality because the source and target domains need to be fixed aforehand. In this paper, we propose to solve a more practical task of multi-domain action recognition on egocentric-exocentric videos, which aims to learn a single model to recognize test videos from either egocentric perspective or exocentric perspective by transferring knowledge between two domains. Though previous cross-domain methods can also transfer knowledge from one domain to another one by learning view-invariant representations of two video domains, they are not suitable for the multi-domain action recognition task because they always suffer from the problem of losing view-specific visual information. As a solution to the multi-domain action recognition task, we propose to map a video from either egocentric perspective or exocentric perspective to a global feature space (we call it holographic feature space) that shares both view-invariant and view-specific visual knowledge of two views. Specially, we decompose the video feature into view-invariant component and view-specific component, where view-specific component is written into memory networks for saving view-specific visual knowledge. The final holographic feature combines view-invariant feature and view-specific features of two views based on the memory networks. We demonstrate the effectiveness of the proposed method with extensive experimental results on two public datasets. Moreover, the good performances under the semi-supervised setting show the generality of our model.
资助项目	National Key Research and Development Program of China[2018AAA0100604] ; National Natural Science Foundation of China[61720106006] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[62072455] ; National Natural Science Foundation of China[U1836220] ; National Natural Science Foundation of China[U1705262] ; National Natural Science Foundation of China[61872424] ; Key Research Program of Frontier Sciences of CAS[QYZDJ-SSW-JSC039] ; Beijing Natural Science Foundation[L201001]
WOS关键词	NETWORKS
WOS研究方向	Computer Science ; Telecommunications
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000793839600005
资助机构	National Key Research and Development Program of China ; National Natural Science Foundation of China ; Key Research Program of Frontier Sciences of CAS ; Beijing Natural Science Foundation
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/49458]
专题	自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
通讯作者	Xu, Changsheng
作者单位	1.Peng Cheng Lab, Shenzhen 518066, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Inst Automat, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Huang, Yi,Yang, Xiaoshan,Gao, Junyun,et al. Holographic Feature Learning of Egocentric-Exocentric Videos for Multi-Domain Action Recognition[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2022,24:2273-2286.
APA	Huang, Yi,Yang, Xiaoshan,Gao, Junyun,&Xu, Changsheng.(2022).Holographic Feature Learning of Egocentric-Exocentric Videos for Multi-Domain Action Recognition.IEEE TRANSACTIONS ON MULTIMEDIA,24,2273-2286.
MLA	Huang, Yi,et al."Holographic Feature Learning of Egocentric-Exocentric Videos for Multi-Domain Action Recognition".IEEE TRANSACTIONS ON MULTIMEDIA 24(2022):2273-2286.