Multi-Domain and Multi-Task Learning for Human Action Recognition

doi:10.1109/TIP.2018.2872879

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	Multi-Domain and Multi-Task Learning for Human Action Recognition
	Xu, Ning 3; Zhang, Yong-Dong 1,2; Su, Yu-Ting 3; Nie, Wei-Zhi 3; Liu, An-An 3
刊名	IEEE TRANSACTIONS ON IMAGE PROCESSING
	2019-02-01
卷号	28 期号:2 页码:853-867
关键词	Domain-invariant Learning multi-task learning human action recognition
ISSN号	1057-7149
DOI	10.1109/TIP.2018.2872879
英文摘要	Domain-invariant (view-invariant and modality-invariant) feature representation is essential for human action recognition. Moreover, given a discriminative visual representation, it is critical to discover the latent correlations among multiple actions in order to facilitate action modeling. To address these problems, we propose a multi-domain and multi-task learning (MDMTL) method to: 1) extract domain-invariant information for multi-view and multi-modal action representation and 2) explore the relatedness among multiple action categories. Specifically, we present a sparse transfer learning-based method to co-embed multi-domain (multi-view and multi-modality) data into a single common space for discriminative feature learning. Additionally, visual feature learning is incorporated into the multi-task learning framework, with the Frobenius-norm regularization term and the sparse constraint term, for joint task modeling and task relatedness-induced feature learning. To the best of our knowledge, MDMTL is the first supervised framework to jointly realize domain-invariant feature learning and task modeling for multi-domain action recognition. Experiments conducted on the INRIA Xmas Motion Acquisition Sequences data set, the MSR Daily Activity 3D (DailyActivity3D) data set, and the Multi-modal & Multi-view & Interactive data set, which is the most recent and largest multi-view and multi-model action recognition data set, demonstrate the superiority of MDMTL over the state-of-the-art approaches.
资助项目	National Natural Science Foundation of China[61772359] ; National Natural Science Foundation of China[61472275] ; National Natural Science Foundation of China[61525206] ; National Natural Science Foundation of China[61872267] ; National Natural Science Foundation of China[61502337] ; National Key Research and Development Program of China[2017YFC0820600] ; National Defense Science and Technology Fund for Distinguished Young Scholars[2017-JCJQ-ZQ-022]
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000448501800002
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/3650]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Xu, Ning; Nie, Wei-Zhi; Liu, An-An
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Univ Sci & Technol China, Sch Informat Sci & Technol, Hefei 230026, Anhui, Peoples R China 3.Tianjin Univ, Sch Elect & Informat Engn, Tianjin 300072, Peoples R China
推荐引用方式 GB/T 7714	Xu, Ning,Zhang, Yong-Dong,Su, Yu-Ting,et al. Multi-Domain and Multi-Task Learning for Human Action Recognition[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2019,28(2):853-867.
APA	Xu, Ning,Zhang, Yong-Dong,Su, Yu-Ting,Nie, Wei-Zhi,&Liu, An-An.(2019).Multi-Domain and Multi-Task Learning for Human Action Recognition.IEEE TRANSACTIONS ON IMAGE PROCESSING,28(2),853-867.
MLA	Xu, Ning,et al."Multi-Domain and Multi-Task Learning for Human Action Recognition".IEEE TRANSACTIONS ON IMAGE PROCESSING 28.2(2019):853-867.