Three-Stream Convolutional Neural Network with Squeeze-and-Excitation Block for Near-Infrared Facial Expression Recognition

doi:10.3390/electronics8040385

PSYCH OpenIR > 认知与发展心理学研究室

	Three-Stream Convolutional Neural Network with Squeeze-and-Excitation Block for Near-Infrared Facial Expression Recognition
	Chen, Ying 1,2; Zhang, Zhihao 1,2; Zhong, Lei 1,2; Chen, Tong 1,2,3; Chen, Juxiang 1,2; Yu, Yeda 1,2
第一作者	Chen, Ying
通讯作者邮箱	c_tong@swu.edu.cn
心理所单位排序	3
摘要	Near-infrared (NIR) facial expression recognition is resistant to illumination change. In this paper, we propose a three-stream three-dimensional convolution neural network with a squeeze-and-excitation (SE) block for NIR facial expression recognition. We fed each stream with different local regions, namely the eyes, nose, and mouth. By using an SE block, the network automatically allocated weights to different local features to further improve recognition accuracy. The experimental results on the Oulu-CASIA NIR facial expression database showed that the proposed method has a higher recognition rate than some state-of-the-art algorithms.
关键词	NIR facial expression recognition SE block 3D CNN adaptive feature weights calibration
	2019-04-01
语种	英语
DOI	10.3390/electronics8040385
发表期刊	ELECTRONICS
ISSN	2079-9292
卷号	8 期号:4 页码:15
期刊论文类型	article
收录类别	SCI
资助项目	National Natural Science Foundation of China[61301297] ; National Natural Science Foundation of China[61502398] ; Southwest University Undergraduate Science and Technology Innovation Fund[20600901]
出版者	MDPI
WOS关键词	SYSTEM ; MODEL ; 3D
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:000467751100016
资助机构	National Natural Science Foundation of China ; Southwest University Undergraduate Science and Technology Innovation Fund
引用统计	被引频次：10[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.psych.ac.cn/handle/311026/29272
专题	认知与发展心理学研究室
通讯作者	Chen, Tong
作者单位	1.Southwest Univ, Chongqing Key Lab Nonlinear Circuit & Intelligent, Chongqing 400715, Peoples R China 2.Chinese Acad Sci, Chongqing Key Lab Artificial Intelligence & Serv, Chongqing Inst Green & Intelligent Technol, Chongqing 400715, Peoples R China 3.Chinese Acad Sci, Inst Psychol, Beijing 100101, Peoples R China
通讯作者单位	中国科学院心理研究所
推荐引用方式 GB/T 7714	Chen, Ying,Zhang, Zhihao,Zhong, Lei,et al. Three-Stream Convolutional Neural Network with Squeeze-and-Excitation Block for Near-Infrared Facial Expression Recognition[J]. ELECTRONICS,2019,8(4):15.
APA	Chen, Ying,Zhang, Zhihao,Zhong, Lei,Chen, Tong,Chen, Juxiang,&Yu, Yeda.(2019).Three-Stream Convolutional Neural Network with Squeeze-and-Excitation Block for Near-Infrared Facial Expression Recognition.ELECTRONICS,8(4),15.
MLA	Chen, Ying,et al."Three-Stream Convolutional Neural Network with Squeeze-and-Excitation Block for Near-Infrared Facial Expression Recognition".ELECTRONICS 8.4(2019):15.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Three-Stream Convolu（1523KB）	期刊论文	作者接受稿	限制开放	CC BY-NC-SA	请求全文