Dual Temporal Scale Convolutional Neural Network for MicroExpression Recognition | |
Peng,Min1,2; Wang,Chongyang1,2; Chen,Tong1,2,3; Liu,Guangyuan1,2; Fu,Xiaolan3 | |
第一作者 | Peng,Min ; Wang,Chongyang |
通讯作者邮箱 | c_tong@swu.edu.cn |
心理所单位排序 | 3 |
摘要 | 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. |
关键词 | micro-expression recognition deep learning optical flow convolutional neural network feature fusion |
2017 | |
语种 | 英语 |
DOI | org/10.3389/fpsyg.2017.01745 |
发表期刊 | FRONTIERS IN PSYCHOLOGY |
ISSN | 1664-1078 |
卷号 | 8页码:1-12 |
URL | 查看原文 |
收录类别 | SSCI |
取样对象 | 人类 |
性别 | 男 ; 女 |
年龄组 | 青年(18岁-29岁) |
被试数量 | CASMEI database: 19 ,CASMEII database: 26 |
测试或任务 | micro-expression recognition ;Dual T emporal Scale Convolutional Neural Network |
因变量指标 | recognition rate |
统计方法 | Deep Learning |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.psych.ac.cn/handle/311026/25632 |
专题 | 认知与发展心理学研究室 |
作者单位 | 1.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 |
推荐引用方式 GB/T 7714 | Peng,Min,Wang,Chongyang,Chen,Tong,et al. Dual Temporal Scale Convolutional Neural Network for MicroExpression Recognition[J]. FRONTIERS IN PSYCHOLOGY,2017,8:1-12. |
APA | Peng,Min,Wang,Chongyang,Chen,Tong,Liu,Guangyuan,&Fu,Xiaolan.(2017).Dual Temporal Scale Convolutional Neural Network for MicroExpression Recognition.FRONTIERS IN PSYCHOLOGY,8,1-12. |
MLA | Peng,Min,et al."Dual Temporal Scale Convolutional Neural Network for MicroExpression Recognition".FRONTIERS IN PSYCHOLOGY 8(2017):1-12. |
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 | ||
Dual Temporal Scale (2129KB) | 期刊论文 | 作者接受稿 | 限制开放 | CC BY-NC-SA | 请求全文 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论