Geometry Guided Pose-Invariant Facial Expression Recognition

doi:10.1109/TIP.2020.2972114

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

	Geometry Guided Pose-Invariant Facial Expression Recognition
	Zhang, Feifei 3,4; Zhang, Tianzhu 2,4; Mao, Qirong 3; Xu, Changsheng 1,2,4
刊名	IEEE TRANSACTIONS ON IMAGE PROCESSING
	2020
卷号	29 页码:4445-4460
关键词	Facial expression recognition facial image synthesis generative adversarial network facial landmarks
ISSN号	1057-7149
DOI	10.1109/TIP.2020.2972114
通讯作者	Xu, Changsheng(csxu@nlpr.ia.ac.cn)
英文摘要	Driven by recent advances in human-centered computing, Facial Expression Recognition (FER) has attracted significant attention in many applications. However, most conventional approaches either perform face frontalization on a non-frontal facial image or learn separate classifier for each pose. Different from existing methods, this paper proposes an end-to-end deep learning model that allows to simultaneous facial image synthesis and pose-invariant facial expression recognition by exploiting shape geometry of the face image. The proposed model is based on generative adversarial network (GAN) and enjoys several merits. First, given an input face and a target pose and expression designated by a set of facial landmarks, an identity-preserving face can be generated through guiding by the target pose and expression. Second, the identity representation is explicitly disentangled from both expression and pose variations through the shape geometry delivered by facial landmarks. Third, our model can automatically generate face images with different expressions and poses in a continuous way to enlarge and enrich the training set for the FER task. Our approach is demonstrated to perform well when compared with state-of-the-art algorithms on both controlled and in-the-wild benchmark datasets including Multi-PIE, BU-3DFE, and SFEW. The code is included in the supplementary material.
资助项目	National Key Research and Development Program of China[2017YFB1002804] ; National Natural Science Foundation of China (NSFC)[61720106006] ; National Natural Science Foundation of China (NSFC)[61721004] ; National Natural Science Foundation of China (NSFC)[61832002] ; National Natural Science Foundation of China (NSFC)[61532009] ; National Natural Science Foundation of China (NSFC)[U1705262] ; National Natural Science Foundation of China (NSFC)[U1836220] ; National Natural Science Foundation of China (NSFC)[61702511] ; National Natural Science Foundation of China (NSFC)[61672267] ; National Natural Science Foundation of China (NSFC)[61751211] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-JSC039] ; Research Program of National Laboratory of Pattern Recognition[Z-2018007]
WOS关键词	GAUSSIAN-PROCESSES ; MULTIVIEW
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:000526525300001
资助机构	National Key Research and Development Program of China ; National Natural Science Foundation of China (NSFC) ; Key Research Program of Frontier Sciences, CAS ; Research Program of National Laboratory of Pattern Recognition
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/38824]
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.Jiangsu Univ, Sch Comp Sci & Commun Engn, Zhenjiang 212000, Jiangsu, Peoples R China 4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Feifei,Zhang, Tianzhu,Mao, Qirong,et al. Geometry Guided Pose-Invariant Facial Expression Recognition[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2020,29:4445-4460.
APA	Zhang, Feifei,Zhang, Tianzhu,Mao, Qirong,&Xu, Changsheng.(2020).Geometry Guided Pose-Invariant Facial Expression Recognition.IEEE TRANSACTIONS ON IMAGE PROCESSING,29,4445-4460.
MLA	Zhang, Feifei,et al."Geometry Guided Pose-Invariant Facial Expression Recognition".IEEE TRANSACTIONS ON IMAGE PROCESSING 29(2020):4445-4460.