中文版 | English
Title

Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning

Author
Corresponding AuthorJianguo Zhang; Min Xu
Joint first authorJiahao Xia
DOI
Publication Years
2022
Conference Name
Conference on Computer Vision and Pattern Recognition (CVPR)
ISSN
1063-6919
ISBN
978-1-6654-6947-0
Source Title
Volume
2022-June
Pages
4042-4051
Conference Date
18-24 June 2022
Conference Place
New Orleans, LA, USA
Publication Place
10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA
Publisher
Abstract
Heatmap regression methods have dominated face alignment area in recent years while they ignore the inherent relation between different landmarks. In this paper, we propose a Sparse Local Patch Transformer (SLPT) for learning the inherent relation. The SLPT generates the representation of each single landmark from a local patch and aggregates them by an adaptive inherent relation based on the attention mechanism. The subpixel coordinate of each landmark is predicted independently based on the aggregated feature. Moreover, a coarse-to-fine framework is further introduced to incorporate with the SLPT, which enables the initial landmarks to gradually converge to the target facial landmarks using fine-grained features from dynamically resized local patches. Extensive experiments carried out on three popular benchmarks, including WFLW, 300W and COFW, demonstrate that the proposed method works at the state-of-the-art level with much less computational complexity by learning the inherent relation between facial landmarks. The code is available at the project website(1).
Keywords
SUSTech Authorship
Corresponding
Language
English
URL[Source Record]
Indexed By
Funding Project
program of China Scholarships Council[202006130004]
WOS Research Area
Computer Science ; Imaging Science & Photographic Technology
WOS Subject
Computer Science, Artificial Intelligence ; Imaging Science & Photographic Technology
WOS Accession No
WOS:000867754204030
EI Accession Number
20224613120153
Data Source
IEEE
PDF urlhttps://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9879432
Citation statistics
Cited Times [WOS]:0
Document TypeConference paper
Identifierhttp://kc.sustech.edu.cn/handle/2SGJ60CL/406480
DepartmentDepartment of Computer Science and Engineering
Affiliation
1.Faculty of Engineering and IT, University of Technology Sydney
2.Dept. of Comp. Sci. and Eng., Southern University of Science and Technology
3.CaimCar
Corresponding Author AffilicationSouthern University of Science and Technology
Recommended Citation
GB/T 7714
Jiahao Xia,Weiwei Qu,Wenjian Huang,et al. Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning[C]. 10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA:IEEE COMPUTER SOC,2022:4042-4051.
Files in This Item:
File Name/Size DocType Version Access License
Xia_Sparse_Local_Pat(4509KB) Restricted Access--
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Export to Excel
Export to Csv
Altmetrics Score
Google Scholar
Similar articles in Google Scholar
[Jiahao Xia]'s Articles
[Weiwei Qu]'s Articles
[Wenjian Huang]'s Articles
Baidu Scholar
Similar articles in Baidu Scholar
[Jiahao Xia]'s Articles
[Weiwei Qu]'s Articles
[Wenjian Huang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Jiahao Xia]'s Articles
[Weiwei Qu]'s Articles
[Wenjian Huang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
No comment.

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