N. Liu et al., "Super Wide Regression Network for Unsupervised Cross-Database Facial Expression Recognition," 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, 2018, pp. 1897-1901. doi: 10.1109/ICASSP.2018.8461322
Super wide regression network for unsupervised cross-database facial expression recognition
|Author:||Liu, Na1,2,3; Zhang, Baofeng3,1; Zong, Yuan4;|
1School of Computer Science and Engineering, Tianjin University of Technology, China
2Center for Machine Vision and Signal Analysis, University of Oulu, Finland
3School of Electrical and Electronic Engineering, Tianjin University of Technology, China
4Research Center for Learning Science, Southeast University, China
|Online Access:||PDF Full Text (PDF, 0.4 MB)|
|Persistent link:|| http://urn.fi/urn:nbn:fi-fe2019040511202
Institute of Electrical and Electronics Engineers,
|Publish Date:|| 2019-04-05
Unsupervised cross-database facial expression recognition (FER) is a challenging problem, in which the training and testing samples belong to different facial expression databases. For this reason, the training (source) and testing (target) facial expression samples would have different feature distributions and hence the performance of lots of existing FER methods may decrease. To solve this problem, in this paper we propose a novel super wide regression network (SWiRN) model, which serves as the regression parameter to bridge the original feature space and the label space and herein in each layer the maximum mean discrepancy (MMD) criterion is used to enforce the source and target facial expression samples to share the same or similar feature distributions. Consequently, the learned SWiRN is able to predict the expression categories of the target samples although we have no access to any label information of target samples. We conduct extensive cross-database FER experiments on CK+, eNTERFACE, and Oulu-CASIA VIS facial expression databases to evaluate the proposed SWiRN. Experimental results show that our SWiRN model achieves more promising performance than recent proposed cross-database emotion recognition methods.
Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing
|Pages:||1897 - 1901|
2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
IEEE International Conference on Acoustics, Speech and Signal Processing
|Type of Publication:||
A4 Article in conference proceedings
|Field of Science:||
113 Computer and information sciences
This research was supported by the Natural Science Foundation of China under Grants 61172185 and 61602345, the Application Foundation and Advanced Technology Research Project of Tianjin, the Academy of Finland, Tekes Fidipro program and Infotech Oulu.
© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.