中国科学院深圳先进技术研究院机构知识库(SIAT OpenIR): Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks.
SIAT OpenIR  > 集成所
Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks.
Zhang, Kaipeng; Zhang, Zhanpeng; Li, Zhifeng; Qiao, Yu
2016
Source PublicationIEEE SIGNAL PROCESSING LETTERS
Subtype期刊论文
AbstractFace detection and alignment in unconstrained environment are challenging due to various poses, illuminations, and occlusions. Recent studies show that deep learning approaches can achieve impressive performance on these two tasks. In this letter, we propose a deep cascaded multitask framework that exploits the inherent correlation between detection and alignment to boost up their performance. In particular, our framework leverages a cascadedarchitecture with three stages of carefully designed deep convolutional networks to predict face and landmark location in a coarse-to-fine manner. In addition, we propose a new online hard sample mining strategy that further improves the performance in practice. Our method achieves superior accuracy over the state-of-the-art techniques on the challenging face detection dataset and benchmark and WIDER FACE benchmarks for face detection, and annotated facial landmarks in the wild benchmark for face alignment, while keeps real-time performance.
URL查看原文
Indexed BySCI
Language英语
Department多媒体集成技术研究中心
Document Type期刊论文
Identifierhttp://ir.siat.ac.cn/handle/172644/9803
Collection集成所
AffiliationIEEE SIGNAL PROCESSING LETTERS
Recommended Citation
GB/T 7714
Zhang, Kaipeng,Zhang, Zhanpeng,Li, Zhifeng,et al. Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks.[J]. IEEE SIGNAL PROCESSING LETTERS,2016.
APA Zhang, Kaipeng,Zhang, Zhanpeng,Li, Zhifeng,&Qiao, Yu.(2016).Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks..IEEE SIGNAL PROCESSING LETTERS.
MLA Zhang, Kaipeng,et al."Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks.".IEEE SIGNAL PROCESSING LETTERS (2016).
Files in This Item: Download All
File Name/Size DocType Version Access License
集成-多媒体2016025.pdf(757KB) 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, Kaipeng]'s Articles
[Zhang, Zhanpeng]'s Articles
[Li, Zhifeng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang, Kaipeng]'s Articles
[Zhang, Zhanpeng]'s Articles
[Li, Zhifeng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang, Kaipeng]'s Articles
[Zhang, Zhanpeng]'s Articles
[Li, Zhifeng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 集成-多媒体2016025.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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