中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 多媒体计算与图形学团队
Weakly-Supervised Facial Expression Recognition in the Wild With Noisy Data

文献类型：期刊论文

作者Zhang, Feifei4; Xu, Mingliang1; Xu, Changsheng2,3,4
刊名IEEE TRANSACTIONS ON MULTIMEDIA
出版日期2022
卷号24页码:1800-1814
关键词Noise measurement Face recognition Data models Task analysis Training data Training Annotations Facial expression recognition noisy labeled data clean labels end-to-end pose modeling noise modeling
ISSN号1520-9210
DOI10.1109/TMM.2021.3072786
通讯作者Xu, Changsheng(csxu@nlpr.ia.ac.cn)
英文摘要Facial expression recognition (FER) has attracted much attention in recent years due to its wide applications. While some progress has been achieved thanks to the emergence of deep learning, the challenge occasioned by pose variations remains. Therefore, most conventional approaches mainly perform FER under laboratory-controlled environment, and the FER in-the-wild has received relatively less attention. To implement the FER in-the-wild, the pose-invariant expression recognition model would be a possible solution but for a paucity of training data. Sufficient training data with reliable expression labels on FER tasks typically are unavailable. This paper devotes to addressing the problem of how to model pose variations in facial images, and how to leverage noisy data in the web to boost the FER performance. The proposed model is implemented in an end-to-end weakly supervised manner and enjoys several merits. First, the proposed model utilizes massive noisy labeled data to boost the performance of the FER classifier trained on a small set of clean labels. Second, we offer a novel pose modeling network to adaptively capture the discrepancy in the deep representation space of facial images under different head poses, and consequently, the pose-invariant expression representations can be learned in our model. Last, to exploit the reliable information in the noisy data, we formulate a noise modeling network, which is capable of learning the mapping from feature space to the residuals between clean labels and noisy labels. We validate the proposed approach on four public FER benchmarks: AffectNet, RAF-DB, SFEW, and BU-3DFE. Extensive experiments show that the proposed method performs favorably against state-of-the-art methods.
WOS关键词MULTIVIEW ; POSE
资助项目National Key Research and Development Program of China[2017YFB1002804] ; National Natural Science Foundation of China[61720106006] ; National Natural Science Foundation of China[62002355] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[61832002] ; National Natural Science Foundation of China[61532009] ; National Natural Science Foundation of China[U1705262] ; National Natural Science Foundation of China[U1836220] ; National Natural Science Foundation of China[61751211] ; National Natural Science Foundation of China[62072455] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-JSC039] ; National Postdoctoral Program for Innovative Talents[BX20190367] ; Jiangsu Province key research and development plan[BE2020036]
WOS研究方向Computer Science ; Telecommunications
语种英语
WOS记录号WOS:000778959200005
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Key Research and Development Program of China ; National Natural Science Foundation of China ; Key Research Program of Frontier Sciences, CAS ; National Postdoctoral Program for Innovative Talents ; Jiangsu Province key research and development plan
源URL[http://ir.ia.ac.cn/handle/173211/48370]  
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.Zhengzhou Univ, Sch Informat Engn, Zhengzhou 450000, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
3.Peng Cheng Lab, Shenzhen 518066, 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,Xu, Mingliang,Xu, Changsheng. Weakly-Supervised Facial Expression Recognition in the Wild With Noisy Data[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2022,24:1800-1814.
APA Zhang, Feifei,Xu, Mingliang,&Xu, Changsheng.(2022).Weakly-Supervised Facial Expression Recognition in the Wild With Noisy Data.IEEE TRANSACTIONS ON MULTIMEDIA,24,1800-1814.
MLA Zhang, Feifei,et al."Weakly-Supervised Facial Expression Recognition in the Wild With Noisy Data".IEEE TRANSACTIONS ON MULTIMEDIA 24(2022):1800-1814.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。