期刊论文

Chen, Jingying;Yang, Zongkai

英文

IEEE ACCESS

2169-3536

2020

8

7383-7393

10.1109/ACCESS.2020.2963913

This work was supported in part by the National Key Research and Development Program of China under Grant 2018YFB1004504, in part by the National Natural Science Foundation under Grant 61977027 and Grant 61772380, in part by the Hubei Province Technological Innovation Major Project under Grant 2019AAA044, in part by the Science and Technology Major Project of Hubei Province (Next-Generation AI Technologies) under Grant 2019AEA170, in part by the Foundation for Innovative Research Groups of Hubei Province under Grant 2017CFA007, and in part by the Research Funds of CCNU from the Colleges' Basic Research and Operation of MOE under Grant CCNU19Z02002, Grant CCNU18KFY02, and Grant 2019CXZZ014.

本校为第一且通讯机构

One key challenge in facial expression recognition (FER) is the extraction of discriminative features from critical facial regions. Because of their promising ability to learn discriminative features, visual attention mechanisms are increasingly used to address pattern recognition problems. This paper presents a novel multiple attention network that simulates humans & x2019; coarse-to-fine visual attention to improve expression recognition performance. In the proposed network, a region-aware sub-net (RASnet) learns binary masks for locating expression-related critical regions with coarse-to-fi...