A main directional maximal difference analysis for spotting facial movements from long-term videos

doi:10.1016/j.neucom.2016.12.034

	A main directional maximal difference analysis for spotting facial movements from long-term videos
	Wang,Su-Jing 1; Wu,Shuhang 2; Qian,Xingsheng 1; Li,Jingxiu 3; Fu,Xiaolan4,5
第一作者	Wang, Su-Jing
通讯作者邮箱	wangsujing@psych.ac.cn
心理所单位排序	1
摘要	There is an increasing interests in micro-expression researches. Spotting micro-expressions in long-term videos is very important, not only for providing clues for lie detection, but also for reducing the labor required to collect micro-expression data. However, little progress has been made in spotting micro-expressions. In this paper, we propose a Main Directional Maximal Difference (MDMD) Analysis for micro-expression spotting. MDMD uses the magnitude maximal difference in the main direction of optical flow features to spot facial movements, including micro-expressions. Using block structured facial regions, MDMD obtains more accurate features of movement of expressions for automatically spotting micro-expressions and macro-expressions from videos. This method involves both the temporal and spatial locations of face movements. Evaluations using the CAS(ME)(2) database containing micro-expressions and macro-expressions show that MDMD is more robust than some state-of-the-art algorithms.
关键词	Micro-expression recognition Macro-expression Micro-expression spotting Optical flow
	2017-03-22
语种	英语
DOI	10.1016/j.neucom.2016.12.034
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
卷号	230 页码:382-389
期刊论文类型	Article
URL	查看原文
收录类别	SCI ; SSCI
WOS关键词	RECOGNITION ; DECEPTION ; SCHIZOPHRENIA ; REMEDIATION ; CUES
WOS标题词	Science & Technology ; Technology
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000394061800035
测试或任务	micro-expression recognition
因变量指标	MDMO feature; optical flow feature;LBP-TOP and HOOF feature; Micro-expression recognition rates
资助机构	National Natural Science Foundation of China(61379095 ; Beijing Natural Science Foundation(4152055) ; 61375009)
引用统计	被引频次：53[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/311026/21241
专题	中国科学院行为科学重点实验室
作者单位	1.Inst Psychol, CAS Key Lab Behav Sci, Beijing 100101, Peoples R China; 2.Northeastern Univ, Coll Informat Sci & Engn, Shenyang, Peoples R China; 3.Harbin Med Univ, Affiliated Hosp 4, Dept Cardiol, Harbin 150001, Peoples R China; 4.Chinese Acad Sci, Inst Psychol, State Key Lab Brain & Cognit Sci, Beijing 100101, Peoples R China; 5.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
第一作者单位	中国科学院行为科学重点实验室
推荐引用方式 GB/T 7714	Wang,Su-Jing,Wu,Shuhang,Qian,Xingsheng,et al. A main directional maximal difference analysis for spotting facial movements from long-term videos[J]. NEUROCOMPUTING,2017,230:382-389.
APA	Wang,Su-Jing,Wu,Shuhang,Qian,Xingsheng,Li,Jingxiu,&Fu,Xiaolan.(2017).A main directional maximal difference analysis for spotting facial movements from long-term videos.NEUROCOMPUTING,230,382-389.
MLA	Wang,Su-Jing,et al."A main directional maximal difference analysis for spotting facial movements from long-term videos".NEUROCOMPUTING 230(2017):382-389.

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
A main directional m（1586KB）	期刊论文	出版稿	限制开放	CC BY-NC-SA	请求全文