热门
A Deep Regression Architecture with Two-Stage Re-initialization for High Performance Facial Landmark Detection
文献类型：会议论文
| 作者 | Lv, Jiangjing; Shao, Xiaohu ; Xing, Junliang; Cheng, Cheng; Zhou, Xi
|
| 出版日期 | 2017 |
| 会议日期 | JUL 21-26, 2016 |
| 会议地点 | Honolulu, HI |
| DOI | 10.1109/CVPR.2017.393 |
| 页码 | 3691-3700 |
| 通讯作者 | Lv, JJ (reprint author), Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Beijing, Peoples R China. ; Lv, JJ (reprint author), Univ Chinese Acad Sci, Beijing, Peoples R China. |
| 英文摘要 | Regression based facial landmark detection methods usually learns a series of regression functions to update the landmark positions from an initial estimation. Most of existing approaches focus on learning effective mapping functions with robust image features to improve performance. The approach to dealing with the initialization issue, however, receives relatively fewer attentions. In this paper, we present a deep regression architecture with two-stage re-initialization to explicitly deal with the initialization problem. At the global stage, given an image with a rough face detection result, the full face region is firstly re-initialized by a supervised spatial transformer network to a canonical shape state and then trained to regress a coarse landmark estimation. At the local stage, different face parts are further separately re-initialized to their own canonical shape states, followed by another regression subnetwork to get the final estimation. Our proposed deep architecture is trained from end to end and obtains promising results using different kinds of unstable initialization. It also achieves superior performances over many competing algorithms. |
| 会议录 | 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
 |
| 语种 | 英语 |
| ISSN号 | 1063-6919 |
| WOS记录号 | WOS:000418371403082 |
| 源URL | [http://119.78.100.138/handle/2HOD01W0/369]  |
| 专题 | 智能安全技术研究中心 |
| 作者单位 | (1) Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Beijing, Peoples R China; (2) Univ Chinese Acad Sci, Beijing, Peoples R China; (3) Chinese Acad Sci, Inst Automat, Beijing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Lv, Jiangjing,Shao, Xiaohu,Xing, Junliang,et al. A Deep Regression Architecture with Two-Stage Re-initialization for High Performance Facial Landmark Detection[C]. 见:. Honolulu, HI. JUL 21-26, 2016. |
入库方式： OAI收割
来源：重庆绿色智能技术研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。