CASIA OpenIR  > 多媒体计算与图形学团队
Joint Representation and Estimator Learning for Facial Action Unit Intensity Estimation
Yong Zhang1; Baoyuan Wu1; Weiming Dong2; Zhifeng Li1; Wei Liu1; Bao-Gang Hu2; Qiang Ji3
2019-06
Conference Name2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Source PublicationIEEE/CVF Conference on Computer Vision and Pattern Recognition
Pages3457-3466
Conference Date2019-6
Conference PlaceLong Beach, CA, USA
Abstract

Facial action unit (AU) intensity is an index to characterize human expressions. Accurate AU intensity estimation depends on three major elements: image representation, intensity estimator, and supervisory information. Most existing methods learn intensity estimator with fixed image representation, and rely on the availability of fully annotated supervisory information. In this paper, a novel general framework for AU intensity estimation is presented, which differs from traditional estimation methods in two aspects. First, rather than keeping image representation fixed, it simultaneously learns representation and intensity estimator to achieve an optimal solution. Second, it allows incorporating weak supervisory training signal from human knowledge (e.g. feature smoothness, label smoothness, label ranking, and positive label), which makes our model trainable even fully annotated information is not available. More specifically, human knowledge is represented as either soft or hard constraints which are encoded as regularization terms or equality/inequality constraints, respectively. On top of our novel framework, we additionally propose an efficient algorithm for optimization based on Alternating Direction Method of Multipliers (ADMM). Evaluations on two benchmark databases show that our method outperforms competing methods under different ratios of AU intensity annotations, especially for small ratios.

Indexed ByEI
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/23907
Collection多媒体计算与图形学团队
Corresponding AuthorBaoyuan Wu
Affiliation1.Tencent AI Lab
2.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
3.Rensselaer Polytechnic Institute
Recommended Citation
GB/T 7714
Yong Zhang,Baoyuan Wu,Weiming Dong,et al. Joint Representation and Estimator Learning for Facial Action Unit Intensity Estimation[C],2019:3457-3466.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yong Zhang]'s Articles
[Baoyuan Wu]'s Articles
[Weiming Dong]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yong Zhang]'s Articles
[Baoyuan Wu]'s Articles
[Weiming Dong]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yong Zhang]'s Articles
[Baoyuan Wu]'s Articles
[Weiming Dong]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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