Facial expression recognition using densely connected convolutional neural network and hierarchical spatial attention

被引：23

作者：

Gan, Chenquan ^{[1
,2
,3
]}

Xiao, Junhao ^{[1
]}

Wang, Zhangyi ^{[1
]}

Zhang, Zufan ^{[1
,2
,3
]}

Zhu, Qingyi ^{[4
]}

机构：

[1] Chongqing Univ Posts & Telecommun, Sch Commun & Informat Engn, Chongqing 400065, Peoples R China

[2] Chongqing Key Lab Mobile Commun Technol, Chongqing 400065, Peoples R China

[3] Minist Educ, Engn Res Ctr Mobile Commun, Chongqing 400065, Peoples R China

[4] Chongqing Univ Posts & Telecommun, Sch Cyber Secur & Informat Law, Chongqing 400065, Peoples R China

来源：

IMAGE AND VISION COMPUTING | 2022年 / 117卷

关键词：

Facial image; Facial expression recognition; Densely connected convolutional neural; network; Spatial attention; HISTOGRAM; FEATURES;

D O I：

10.1016/j.imavis.2021.104342

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper is dedicated to eliminating the impact of redundant information from emotional-unrelated regions on facial expression recognition (FER). To this end, a densely connected convolutional neural network with hierarchical spatial attention is proposed. Specifically, it can adaptively locate salient regions and focus on the emotional related features so that the facial expressions can be represented more efficiently. This superior performance is also verified by some experiments. Experimental results reveal that the proposed method can distinguish facial expression more accurately than existing state-of-the-art methods.(c) 2021 Elsevier B.V. All rights reserved.

引用

页数：9

共 33 条

[1]

[Anonymous], 2010, 2010 IEEE COMPUTER S, DOI [10. 1109/CVPRW.2010.5543262, DOI 10.1109/CVPRW.2010.5543262]

[2] cGAN Based Facial Expression Recognition for Human-Robot Interaction [J].

Deng, Jia ;

Pang, Gaoyang ;

Zhang, Zhiyu ;

Pang, Zhibo ;

Yang, Huayong ;

Yang, Geng .

IEEE ACCESS, 2019, 7 :9848-9859

[3]

Fan Y., 2018, P INT C ARTIFICIAL N, P8494

[4] Sparse attention based separable dilated convolutional neural network for targeted sentiment analysis [J].

Gan, Chenquan ;

Wang, Lu ;

Zhang, Zufan ;

Wang, Zhangyi .

KNOWLEDGE-BASED SYSTEMS, 2020, 188

[5] Multiple Attention Network for Facial Expression Recognition [J].

Gan, Yanling ;

Chen, Jingying ;

Yang, Zongkai ;

Xu, Luhui .

IEEE ACCESS, 2020, 8 :7383-7393

[6] Automatic Facial Expression Recognition Using Features of Salient Facial Patches [J].

Happy, S. L. ;

Routray, Aurobinda .

IEEE TRANSACTIONS ON AFFECTIVE COMPUTING, 2015, 6 (01) :1-12

[7] Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition [J].

He, Ran ;

Wu, Xiang ;

Sun, Zhenan ;

Tan, Tieniu .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2019, 41 (07) :1761-1773

[8]

Hu J, 2018, PROC CVPR IEEE, P7132, DOI [10.1109/CVPR.2018.00745, 10.1109/TPAMI.2019.2913372]

[9] Convolutional Network with Densely Backward Attention for Facial Expression Recognition [J].

Hua, Cam-Hao ;

Thien Huynh-The ;

Seo, Hyunseok ;

Lee, Sungyoung .

PROCEEDINGS OF THE 2020 14TH INTERNATIONAL CONFERENCE ON UBIQUITOUS INFORMATION MANAGEMENT AND COMMUNICATION (IMCOM), 2020,

[10] Densely Connected Convolutional Networks [J].

Huang, Gao ;

Liu, Zhuang ;

van der Maaten, Laurens ;

Weinberger, Kilian Q. .

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :2261-2269

← 1 2 3 4 →