中国科学院深圳先进技术研究院机构知识库(SIAT OpenIR): Deep Face Attributes Recognition Using Spatial Transformer Network
SIAT OpenIR  > 集成所
Deep Face Attributes Recognition Using Spatial Transformer Network
Tan Lianzhi; Li Zhifeng; Qiao Yu
2016
Conference NameICIA2016
Conference Place荷兰阿姆斯特丹
AbstractFace alignment is very crucial to the task of face attributes recognition. The performance of face attributes recognition would notably degrade if the fiducial points of the original face images are not precisely detected due to large lighting, pose and occlusion variations. In order to alleviate this problem, we propose a spatial transform based deep CNNs to improve the performance of face attributes recognition. In this approach, we first learn appropriate transformation parameters by a carefully designed spatial transformer network called LoNet to align the original face images, and then recognize the face attributes based on the aligned face images using a deep network called ClNet. To the best of our knowledge, this is the first attempt to use spatial transformer network in face attributes recognition task. Extensive experiments on two large and challenging databases (CelebA and LFWA) clearly demonstrate the effectiveness of the proposed approach over the current state-of-the-art.
Department多媒体集成技术研究中心
Indexed ByEI
Language英语
Document Type会议论文
Identifierhttp://ir.siat.ac.cn/handle/172644/10012
Collection集成所
Affiliation2016
Recommended Citation
GB/T 7714
Tan Lianzhi,Li Zhifeng,Qiao Yu. Deep Face Attributes Recognition Using Spatial Transformer Network[C],2016.
Files in This Item: Download All
File Name/Size DocType Version Access License
集成-多媒体2016018.pdf(778KB) 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
[Tan Lianzhi]'s Articles
[Li Zhifeng]'s Articles
[Qiao Yu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Tan Lianzhi]'s Articles
[Li Zhifeng]'s Articles
[Qiao Yu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Tan Lianzhi]'s Articles
[Li Zhifeng]'s Articles
[Qiao Yu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 集成-多媒体2016018.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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