文献类型：期刊文献

英文题名：A visual attention based ROI detection method for facial expression recognition

作者：Sun, Wenyun[1];Zhao, Haitao[2];Jin, Zhong[1]

机构：[1]Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, Nanjing, Jiangsu, Peoples R China;[2]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai, Peoples R China

年份：2018

卷号：296

起止页码：12

外文期刊名：NEUROCOMPUTING

收录：;EI(收录号：20181404969406);WOS:【SCI-EXPANDED(收录号:WOS:000430227900002)】；

基金：This work is partially supported by National Natural Science Foundation of China under Grant nos. 61373063, 61375007, 61233011, 91420201, 61472187 and by National Basic Research Program of China under Grant No. 2014CB349303.

语种：英文

外文关键词：Facial expression recognition; Action unit; Visual attention mechanism

摘要：In this paper, an eleven-layered Convolutional Neural Network with Visual Attention is proposed for facial expression recognition. The network is composed of three components. First, local convolutional features of faces are extracted by a stack of ten convolutional layers. Second, the regions of interest are automatically determined according to these local features by the embedded attention model. Third, the local features in these regions are aggregated and used to infer the emotional label. These three components are integrated into a single network which can be trained in an end-to-end scheme. Extensive experiments on four kinds of data (namely aligned frontal faces, faces in different poses, aligned unconstrained faces, and grouped unconstrained faces) prove that the proposed method can improve the accuracy and obtain good visualization. The visualization shows that the learned regions of interest are partly consistent with the locations of emotion specific Action Units. This founding confirms the interpretation of Facial Action Coding System and Emotional Facial Action Coding System from a machine learning perspective. (C) 2018 Elsevier B.V. All rights reserved.