PSYCH OpenIR  > 认知与发展心理学研究室
Dual Temporal Scale Convolutional Neural Network for MicroExpression Recognition
Min Peng1,2; Chongyang Wang1,2; Tong Chen1,2,3; Guangyuan Liu1,2; Xiaolan Fu3
2017
Source PublicationFRONTIERS IN PSYCHOLOGY
Correspondent Emailc_tong@swu.edu.cn
ISSN1664-1078
Volume8Issue:不详Pages:1-12
Abstract

Facial micro-expression is a brief involuntary facial movement and can reveal the genuine emotion that people try to conceal. Traditional methods of spontaneous micro-expression recognition rely excessively on sophisticated hand-crafted feature design and the recognition rate is not high enough for its practical application. In this paper, we proposed a Dual Temporal Scale Convolutional Neural Network (DTSCNN) for spontaneous micro-expressions recognition. The DTSCNN is a two-stream network. Different of streamof DTSCNN is used to adapt to different frame rate ofmicro-expression
video clips. Each stream of DSTCNN consists of independent shallow network for avoiding the overfitting problem. Meanwhile, we fed the networks with optical-flow sequences to ensure that the shallow networks can further acquire higher-level features. Experimental results on spontaneous micro-expression databases (CASME I/II) showed that our method can achieve a recognition rate almost 10% higher than what some state-of-the-art method can achieve.

Keywordmicro-expression recognition deep learning optical flow convolutional neural network feature fusion
DOIorg/10.3389/fpsyg.2017.01745
Indexed BySSCI
Language英语
Citation statistics
Document Type期刊论文
Identifierhttp://ir.psych.ac.cn/handle/311026/25632
Collection认知与发展心理学研究室
Corresponding AuthorTong Chen
Affiliation1.Chongqing Key Laboratory of Non-linear Circuit and Intelligent Information Processing, Southwest University, Chongqing, China
2.School of Electronic and Information Engineering, Southwest University, Chongqing, China
3.Institute of Psychology, University of Chinese Academy of Sciences, Beijing, China
Recommended Citation
GB/T 7714
Min Peng,Chongyang Wang,Tong Chen,et al. Dual Temporal Scale Convolutional Neural Network for MicroExpression Recognition[J]. FRONTIERS IN PSYCHOLOGY,2017,8(不详):1-12.
APA Min Peng,Chongyang Wang,Tong Chen,Guangyuan Liu,&Xiaolan Fu.(2017).Dual Temporal Scale Convolutional Neural Network for MicroExpression Recognition.FRONTIERS IN PSYCHOLOGY,8(不详),1-12.
MLA Min Peng,et al."Dual Temporal Scale Convolutional Neural Network for MicroExpression Recognition".FRONTIERS IN PSYCHOLOGY 8.不详(2017):1-12.
Files in This Item:
File Name/Size DocType Version Access License
Dual Temporal Scale (2129KB)期刊论文作者接受稿限制开放CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Min Peng]'s Articles
[Chongyang Wang]'s Articles
[Tong Chen]'s Articles
Baidu academic
Similar articles in Baidu academic
[Min Peng]'s Articles
[Chongyang Wang]'s Articles
[Tong Chen]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Min Peng]'s Articles
[Chongyang Wang]'s Articles
[Tong Chen]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Dual Temporal Scale Convolutional Neural Network for MicroExpression Recognition.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.