PSYCH OpenIR  > 中国科学院行为科学重点实验室
基于多任务中级特征个性化学习的微表情识别
Alternative TitleMulti-task middle-level feature individualization learning for micro-expression recognition. Computer Engineering and Applications
刘振; 王甦菁; 李擎
First Author刘振
Correspondent Emailliqing@bistu.edu.cn¡£
Contribution Rank2
Abstract微表情是一种短暂的面部表情,揭示了一个人试图隐藏的真实情感。本文对现有的一种多任务中级特征学习方法进行了改进,提出了一种多任务中级特征个性化学习方法用于微表情识别。对于每个低级特征,计算类内k最近邻时,去除同一人的同类微表情;计算类间k最近邻时,保留同一人的不同类表情,并减小k值。采用个性化学习方法,生成具有更多判别信息的中级特征。在微表情数据集CASME2上的实验表明,所提出的方法具有更好的识别性能。
Other AbstractAbstract:Micro-expressions are fleeting facial expressions that expose a genuine emotions that a person tries to conceal. An existing multi-task middle-level feature learning is improved, and a multi-task middle-level feature individualization learning method for micro-expression recognition is proposed. The same kind of micro-expressions of the same person are removed for calculating its interclass nearest neighbors; the different kind of micro-expressions of the same person are retained and the k value is reduced for calculating its interclass nearest neighbors. A middle-level feature with more discriminative information is generated by individualization learning method. Experimental results on spontaneous micro-expression database CASME2 show that the proposed method has better recognition performance.
Keyword微表情识别 个性化学习 中级特征
2018
Language中文
Source Publication计算机工程与应用
ISSN1002-8331
Pages6
Subtype期刊论文
Project Intro.国家自然科学基金(No.61471046,No.61772511);; 北京市教委市属高校创新能力提升计划项目(No.TJSHG201510772017)
Document Type期刊论文
Identifierhttp://ir.psych.ac.cn/handle/311026/29682
Collection中国科学院行为科学重点实验室
Affiliation1.北京信息科技大学高动态导航技术北京市重点实验室
2.中国科学院心理研究所行为科学重点实验室
Recommended Citation
GB/T 7714
刘振,王甦菁,李擎. 基于多任务中级特征个性化学习的微表情识别[J]. 计算机工程与应用,2018:6.
APA 刘振,王甦菁,&李擎.(2018).基于多任务中级特征个性化学习的微表情识别.计算机工程与应用,6.
MLA 刘振,et al."基于多任务中级特征个性化学习的微表情识别".计算机工程与应用 (2018):6.
Files in This Item:
File Name/Size DocType Version Access License
基于多任务中级特征个性化学习的微表情识别(865KB)期刊论文出版稿限制开放CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[刘振]'s Articles
[王甦菁]'s Articles
[李擎]'s Articles
Baidu academic
Similar articles in Baidu academic
[刘振]'s Articles
[王甦菁]'s Articles
[李擎]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[刘振]'s Articles
[王甦菁]'s Articles
[李擎]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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