CASIA OpenIR  > 模式识别国家重点实验室  > 机器人视觉
Two-Stream Deep Correlation Network for Frontal Face Recovery
Zhang, Ting1,2; Dong, Qiulei1,2,3; Tang, Ming1; Hu, Zhanyi1,2,3
Source PublicationIEEE SIGNAL PROCESSING LETTERS
2017-10-01
Volume24Issue:10Pages:1478-1482
SubtypeArticle
AbstractPose and textural variations are two dominant factors to affect the performance of face recognition. It is widely believed that generating the corresponding frontal face froma face image of an arbitrary pose is an effective step toward improving the recognition performance. In the literature, however, the frontal face is generally recovered by only exploring textural characteristic. In this letter, we propose a two-stream deep correlation network, which incorporates both geometric and textural features for frontal face recovery. Given a face image under an arbitrary pose as input, geometric and textural characteristics are first extracted from two separate streams. The extracted characteristics are then fused through the proposed multiplicative patch correlation layer. These two steps are integrated into one network for end-to-end training and prediction, which is demonstrated effective compared with state-of-the-art methods on the benchmark datasets.
KeywordCorrelation Layer Deep Neural Network Frontal Face Recovery Geometric Stream Textural Stream
WOS HeadingsScience & Technology ; Technology
DOI10.1109/LSP.2017.2736542
WOS KeywordRECOGNITION ; IDENTITY ; SPACE ; MODEL
Indexed BySCI
Language英语
Funding OrganizationStrategic Priority Research Program of the Chinese Academy of Sciences(XDB02070002) ; National Natural Science Foundation of China(61421004 ; 61375042 ; 61573359)
WOS Research AreaEngineering
WOS SubjectEngineering, Electrical & Electronic
WOS IDWOS:000408775600006
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/19712
Collection模式识别国家重点实验室_机器人视觉
Corresponding AuthorDong, Qiulei
Affiliation1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
3.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Zhang, Ting,Dong, Qiulei,Tang, Ming,et al. Two-Stream Deep Correlation Network for Frontal Face Recovery[J]. IEEE SIGNAL PROCESSING LETTERS,2017,24(10):1478-1482.
APA Zhang, Ting,Dong, Qiulei,Tang, Ming,&Hu, Zhanyi.(2017).Two-Stream Deep Correlation Network for Frontal Face Recovery.IEEE SIGNAL PROCESSING LETTERS,24(10),1478-1482.
MLA Zhang, Ting,et al."Two-Stream Deep Correlation Network for Frontal Face Recovery".IEEE SIGNAL PROCESSING LETTERS 24.10(2017):1478-1482.
Files in This Item: Download All
File Name/Size DocType Version Access License
Two-Stream Deep Corr(375KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang, Ting]'s Articles
[Dong, Qiulei]'s Articles
[Tang, Ming]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang, Ting]'s Articles
[Dong, Qiulei]'s Articles
[Tang, Ming]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang, Ting]'s Articles
[Dong, Qiulei]'s Articles
[Tang, Ming]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Two-Stream Deep Correlation Network for Frontal Face Recovery.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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