PSYCH OpenIR  > 中国科学院行为科学重点实验室
Action Units recognition based on Deep Spatial-Convolutional and Multi-label Residual network
Wang, Su-Jing1; Lin, Bo2; Wang, Yong2; Yi, Tongqiang2; Zou, Bochao3,4; Lyu, Xiang-wen4
Corresponding AuthorWang, Su-Jing(wangsujing@psych.ac.cn)
2019-09-24
Source PublicationNEUROCOMPUTING
ISSN0925-2312
Volume359Pages:130-138
AbstractFacial Action Unit (AU) recognition is an essential step in the facial analysis. A facial image has one or more AU(s). Given an AU, the number of images without the AU is far greater than that of images with the AU. So, AU recognition is not only a sample imbalance problem but also a multi-label learning problem. For the two problems, we proposed a novel Multi-label Slope Rate (MSR) loss function and an Advanced-MSR (Ad-MSR) loss function in deep network architecture to recognize AU. For other characters of AU recognition, a local convolution and residual units are used in the architecture. The experimental results on two expression databases labeled AU show that the proposed loss functions not only address overfitting of the network on the training set and enhancing the generalization ability on the test set. The proposed architecture also gets well performance in the databases. (C) 2019 Elsevier B.V. All rights reserved.
KeywordSample imbalance problem AU recognition Multi-label learning Local convolution Residual unit
DOI10.1016/j.neucom.2019.05.018
Indexed BySCI ; SCI
Language英语
Funding OrganizationNational Natural Science Foundation of China ; National Engineering Laboratory for Public Security Risk Perception and Control by Big Data
Funding ProjectNational Natural Science Foundation of China[61772511] ; National Engineering Laboratory for Public Security Risk Perception and Control by Big Data[18112403]
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000478960700012
PublisherELSEVIER
WOS KeywordFACIAL EXPRESSIONS ; MACHINE
Citation statistics
Document Type期刊论文
Identifierhttp://ir.psych.ac.cn/handle/311026/29576
Collection中国科学院行为科学重点实验室
Corresponding AuthorWang, Su-Jing
Affiliation1.Chinese Acad Sci, Inst Psychol, Key Lab Behav Sci, Beijing 100101, Peoples R China
2.Xi An Jiao Tong Univ, Coll Software, Xian 710000, Shaanxi, Peoples R China
3.Capital Med Univ, Adv Innovat Ctr Human Brain Protect, Beijing 100054, Peoples R China
4.China Acad Elect & Informat Technol, Beijing 100041, Peoples R China
Recommended Citation
GB/T 7714
Wang, Su-Jing,Lin, Bo,Wang, Yong,et al. Action Units recognition based on Deep Spatial-Convolutional and Multi-label Residual network[J]. NEUROCOMPUTING,2019,359:130-138.
APA Wang, Su-Jing,Lin, Bo,Wang, Yong,Yi, Tongqiang,Zou, Bochao,&Lyu, Xiang-wen.(2019).Action Units recognition based on Deep Spatial-Convolutional and Multi-label Residual network.NEUROCOMPUTING,359,130-138.
MLA Wang, Su-Jing,et al."Action Units recognition based on Deep Spatial-Convolutional and Multi-label Residual network".NEUROCOMPUTING 359(2019):130-138.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang, Su-Jing]'s Articles
[Lin, Bo]'s Articles
[Wang, Yong]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang, Su-Jing]'s Articles
[Lin, Bo]'s Articles
[Wang, Yong]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang, Su-Jing]'s Articles
[Lin, Bo]'s Articles
[Wang, Yong]'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.