CASIA OpenIR  > 模式识别国家重点实验室  > 视频内容安全
Towards Robust and Accurate Multi-View and Partially-Occluded Face Alignment
Xing, Junliang1; Niu, Zhiheng2; Huang, Junshi3; Hu, Weiming4; Zhou, Xi5; Yan, Shuicheng3,6
AbstractFace alignment acts as an important task in computer vision. Regression-based methods currently dominate the approach to solving this problem, which generally employ a series of mapping functions from the face appearance to iteratively update the face shape hypothesis. One keypoint here is thus how to perform the regression procedure. In this work, we formulate this regression procedure as a sparse coding problem. We learn two relational dictionaries, one for the face appearance and the other one for the face shape, with coupled reconstruction coefficient to capture their underlying relationships. To deploy this model for face alignment, we derive the relational dictionaries in a stage-wised manner to perform close-loop refinement of themselves,i.e., the face appearance dictionary is first learned from the face shape dictionary and then used to update the face shape hypothesis, and the updated face shape dictionary from the shape hypothesis is in return used to refine the face appearance dictionary. To improve the model accuracy, we extend this model hierarchically from the whole face shape to face part shapes, thus both the global and local view variations of a face are captured. To locate facial landmarks under occlusions, we further introduce an occlusion dictionary into the face appearance dictionary to recover face shape from partially occluded face appearance. The occlusion dictionary is learned in a data driven manner from background images to represent a set of elemental occlusion patterns, a sparse combination of which models various practical partial face occlusions. By integrating all these technical innovations, we obtain a robust and accurate approach to locate facial landmarks under different face views and possibly severe occlusions for face images in the wild. Extensive experimental analyses and evaluations on different benchmark datasets, as well as two new datasets built by ourselves, have demonstrated the robustness and accuracy of our proposed model, especially for face images with large view variations and/or severe occlusions.
KeywordFace Alignment Dictionary Learning Sparse Representation Appearance-shape Modeling
WOS HeadingsScience & Technology ; Technology
Indexed BySCI
Funding Organization973 basic research program of China(2014CB349303) ; Natural Science Foundation of China(61672519 ; Strategic Priority Research Program of the CAS(XDB02070003) ; 61303178 ; 61472421 ; U1636218)
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS IDWOS:000426687100016
Citation statistics
Cited Times:3[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Affiliation1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Delphi Deutschland GMBH, Adv Engn Elect & Safety, Delphipl 1, D-42119 Wuppertal, North Rhine Wes, Germany
3.AI Inst Qihoo 360 Co, Jiuxianqiao Rd, Beijing 100015, Peoples R China
4.Univ Chinese Acad Sci, Chinese Acad Sci, Inst Automat,Natl Lab Pattern Recognit, CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing 100190, Peoples R China
5.Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Intelligent Media Tech Res Ctr, Chongqing 400714, Peoples R China
6.Natl Univ Singapore, Dept Elect & Comp Engn, Singapore 117576, Singapore
Recommended Citation
GB/T 7714
Xing, Junliang,Niu, Zhiheng,Huang, Junshi,et al. Towards Robust and Accurate Multi-View and Partially-Occluded Face Alignment[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2018,40(4):987-1001.
APA Xing, Junliang,Niu, Zhiheng,Huang, Junshi,Hu, Weiming,Zhou, Xi,&Yan, Shuicheng.(2018).Towards Robust and Accurate Multi-View and Partially-Occluded Face Alignment.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,40(4),987-1001.
MLA Xing, Junliang,et al."Towards Robust and Accurate Multi-View and Partially-Occluded Face Alignment".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 40.4(2018):987-1001.
Files in This Item: Download All
File Name/Size DocType Version Access License
TPAMI17HSRD.pdf(8206KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Xing, Junliang]'s Articles
[Niu, Zhiheng]'s Articles
[Huang, Junshi]'s Articles
Baidu academic
Similar articles in Baidu academic
[Xing, Junliang]'s Articles
[Niu, Zhiheng]'s Articles
[Huang, Junshi]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Xing, Junliang]'s Articles
[Niu, Zhiheng]'s Articles
[Huang, Junshi]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: TPAMI17HSRD.pdf
Format: Adobe PDF
All comments (0)
No comment.

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