FERLrTc: 2D+3D facial expression recognition via low-rank tensor completion

doi:10.1016/j.sigpro.2019.03.015

	FERLrTc: 2D+3D facial expression recognition via low-rank tensor completion
	Fu, Yunfang 1,2,3; Ruan, Qiuqi 1,3; Luo, Ziyan 4; Jin, Yi 1,3; An, Gaoyun 1,3; Wan, Jun5
刊名	SIGNAL PROCESSING
	2019-08-01
卷号	161 页码:74-88
关键词	Tensor Tucker decomposition 2D+3D Facial expression recognition Tensor low-rank representation Tensor completion Multi-modality
ISSN号	0165-1684
DOI	10.1016/j.sigpro.2019.03.015
通讯作者	Fu, Yunfang(fu_yunfang@126.com)
英文摘要	In this paper, a 4D tensor model is firstly constructed to explore efficient structural information and correlations from multi-modal data (both 2D and 3D face data). As the dimensionality of the generated 4D tensor is high, a tensor dimensionality reduction technique is in need. Since many real-world high-order data often reside in a low dimensional subspace, Tucker decomposition as a powerful technique is utilized to capture multilinear low-rank structure and to extract useful information from the generated 4D tensor data. Our goal is to use Tucker decomposition to obtain a set of core tensors with smaller sizes and factor matrices which are projected into the 4D tensor data for classification prediction. To characterize the involved similarities of the 4D tensor, the low-rank and sparse representation is built in terms of the low-rank structure of factor matrices and the sparsity of the core tensor in the Tucker decomposition of the generated 4D tensor. A tensor completion (TC) framework is embedded to recover the missing information in the 4D tensor modeling process. Thus, a novel tensor dimensionality reduction approach for 2D+3D facial expression recognition via low-rank tensor completion (FERLrTC) is proposed to solve the factor matrices in a majorization-minimization manner by using a rank reduction strategy. Numerical experiments are conducted with a full implementation on the BU-3DFE and Bosphorus databases and synthetic data to illustrate the effectiveness of the proposed approach. (C) 2019 Elsevier B.V. All rights reserved.
资助项目	National Natural Science Foundation of China[61471032] ; National Natural Science Foundation of China[11771038] ; National Natural Science Foundation of China[11431002] ; National Natural Science Foundation of China[61403024] ; National Natural Science Foundation of China[61472030] ; National Natural Science Foundation of China[61772067] ; National Natural Science Foundation of China[61502491] ; Program for Innovative Research Team in University of Ministry of Education of China[IRT201206] ; Program for New Century Excellent Talents in University[NCET-12-0768] ; Fundamental Research Funds for the Central Universities[2017JBZ108]
WOS关键词	FEATURE-SELECTION ; 3-D FACE ; 3D ; DECOMPOSITIONS
WOS研究方向	Engineering
语种	英语
出版者	ELSEVIER SCIENCE BV
WOS记录号	WOS:000466258200007
资助机构	National Natural Science Foundation of China ; Program for Innovative Research Team in University of Ministry of Education of China ; Program for New Century Excellent Talents in University ; Fundamental Research Funds for the Central Universities
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/24597]
专题	中国科学院自动化研究所
通讯作者	Fu, Yunfang
作者单位	1.Beijing Jiaotong Univ, Inst Informat Sci, Beijing 100044, Peoples R China 2.Shijiazhuang Univ, Sch Comp Sci & Engn, Shijiazhuang 050035, Hebei, Peoples R China 3.Beijing Key Lab Adv Informat Sci & Network Techno, Beijing 100044, Peoples R China 4.Beijing Jiaotong Univ, State Key Lab Rail Traff Control & Safety, Beijing 100044, Peoples R China 5.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Fu, Yunfang,Ruan, Qiuqi,Luo, Ziyan,et al. FERLrTc: 2D+3D facial expression recognition via low-rank tensor completion[J]. SIGNAL PROCESSING,2019,161:74-88.
APA	Fu, Yunfang,Ruan, Qiuqi,Luo, Ziyan,Jin, Yi,An, Gaoyun,&Wan, Jun.(2019).FERLrTc: 2D+3D facial expression recognition via low-rank tensor completion.SIGNAL PROCESSING,161,74-88.
MLA	Fu, Yunfang,et al."FERLrTc: 2D+3D facial expression recognition via low-rank tensor completion".SIGNAL PROCESSING 161(2019):74-88.