CASIA OpenIR  > 智能感知与计算研究中心
Fast Multi-view Face Alignment via Multi-task Auto-encoders
Qi Li; Zhenan Sun; Ran He(赫然)
2017-10
会议名称International Joint Conference on Biometrics (IJCB)
会议日期2017-10
会议地点Denver, America
摘要Face alignment is an important problem in computer vision. It is still an open  problem due to the variations of facial attributes (~\eg, head pose, facial expression, illumination variation). Many studies have shown that face alignment and facial attribute analysis are often correlated. This paper develops a two-stage multi-task Auto-encoders framework for fast face alignment by incorporating head pose information to handle large view variations. In the first and second stages, multi-task Auto-encoders are used to roughly locate and further refine facial landmark locations with related pose information, respectively. Besides, the shape constraint is naturally encoded into our two-stage face alignment framework to preserve facial structures. A coarse-to-fine strategy is adopted to refine the facial landmark results with the shape constraint. Furthermore, the computational cost of our method is much lower than its deep learning competitors. Experimental results on various challenging datasets show the effectiveness of the proposed method.
收录类别EI
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/19691
专题智能感知与计算研究中心
作者单位Center for Research on Intelligent Perception and Computing, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China
推荐引用方式
GB/T 7714
Qi Li,Zhenan Sun,Ran He. Fast Multi-view Face Alignment via Multi-task Auto-encoders[C],2017.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
0172.pdf(302KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Qi Li]的文章
[Zhenan Sun]的文章
[Ran He(赫然)]的文章
百度学术
百度学术中相似的文章
[Qi Li]的文章
[Zhenan Sun]的文章
[Ran He(赫然)]的文章
必应学术
必应学术中相似的文章
[Qi Li]的文章
[Zhenan Sun]的文章
[Ran He(赫然)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 0172.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。