Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

SUPER WIDE REGRESSION NETWORK FOR UNSUPERVISED CROSS-DATABASE FACIAL EXPRESSION RECOGNITION

Abstract: 

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.

up
0 users have voted:

Paper Details

Authors:
Baofeng Zhang, Yuan Zong, Li Liu,Jie Chen, Guoying Zhao, Junchao Zhu
Submitted On:
13 April 2018 - 8:17am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Na Liu
Paper Code:
2838
Document Year:
2018
Cite

Document Files

ICASSP2018_2838.pdf

(120)

Subscribe

[1] Baofeng Zhang, Yuan Zong, Li Liu,Jie Chen, Guoying Zhao, Junchao Zhu, "SUPER WIDE REGRESSION NETWORK FOR UNSUPERVISED CROSS-DATABASE FACIAL EXPRESSION RECOGNITION", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2696. Accessed: May. 25, 2019.
@article{2696-18,
url = {http://sigport.org/2696},
author = {Baofeng Zhang; Yuan Zong; Li Liu;Jie Chen; Guoying Zhao; Junchao Zhu },
publisher = {IEEE SigPort},
title = {SUPER WIDE REGRESSION NETWORK FOR UNSUPERVISED CROSS-DATABASE FACIAL EXPRESSION RECOGNITION},
year = {2018} }
TY - EJOUR
T1 - SUPER WIDE REGRESSION NETWORK FOR UNSUPERVISED CROSS-DATABASE FACIAL EXPRESSION RECOGNITION
AU - Baofeng Zhang; Yuan Zong; Li Liu;Jie Chen; Guoying Zhao; Junchao Zhu
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2696
ER -
Baofeng Zhang, Yuan Zong, Li Liu,Jie Chen, Guoying Zhao, Junchao Zhu. (2018). SUPER WIDE REGRESSION NETWORK FOR UNSUPERVISED CROSS-DATABASE FACIAL EXPRESSION RECOGNITION. IEEE SigPort. http://sigport.org/2696
Baofeng Zhang, Yuan Zong, Li Liu,Jie Chen, Guoying Zhao, Junchao Zhu, 2018. SUPER WIDE REGRESSION NETWORK FOR UNSUPERVISED CROSS-DATABASE FACIAL EXPRESSION RECOGNITION. Available at: http://sigport.org/2696.
Baofeng Zhang, Yuan Zong, Li Liu,Jie Chen, Guoying Zhao, Junchao Zhu. (2018). "SUPER WIDE REGRESSION NETWORK FOR UNSUPERVISED CROSS-DATABASE FACIAL EXPRESSION RECOGNITION." Web.
1. Baofeng Zhang, Yuan Zong, Li Liu,Jie Chen, Guoying Zhao, Junchao Zhu. SUPER WIDE REGRESSION NETWORK FOR UNSUPERVISED CROSS-DATABASE FACIAL EXPRESSION RECOGNITION [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2696