Learning Representations for Facial Actions From Unlabeled Videos

Facial actions are usually encoded as anatomy-based action units (AUs), the labelling of which demands expertise and thus is time-consuming and expensive. To alleviate the labelling demand, we propose to leverage the large number of unlabelled videos by proposing a twin-cycle autoencoder (TAE) to le...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence Vol. 44; no. 1; pp. 302 - 317
Main Authors: Li, Yong, Zeng, Jiabei, Shan, Shiguang
Format: Journal Article
Language:English
Published: United States IEEE 01.01.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Algorithms
Decoupling
Displacement
encoder-decoder structure
Face
Facial action unit detection
feature disentanglement
Feature extraction
Gold
Head
Head movement
Image management
Image quality
Image reconstruction
Image retrieval
Labelling
Learning
Magnetic heads
Movement
representation learning
Representations
self-supervised learning
Task analysis
Video
Videos
ISSN:0162-8828, 1939-3539, 2160-9292, 1939-3539
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Facial actions are usually encoded as anatomy-based action units (AUs), the labelling of which demands expertise and thus is time-consuming and expensive. To alleviate the labelling demand, we propose to leverage the large number of unlabelled videos by proposing a twin-cycle autoencoder (TAE) to learn discriminative representations for facial actions. TAE is inspired by the fact that facial actions are embedded in the pixel-wise displacements between two sequential face images (hereinafter, source and target) in the video. Therefore, learning the representations of facial actions can be achieved by learning the representations of the displacements. However, the displacements induced by facial actions are entangled with those induced by head motions. TAE is thus trained to disentangle the two kinds of movements by evaluating the quality of the synthesized images when either the facial actions or head pose is changed, aiming to reconstruct the target image. Experiments on AU detection show that TAE can achieve accuracy comparable to other existing AU detection methods including some supervised methods, thus validating the discriminant capacity of the representations learned by TAE. TAE's ability in decoupling the action-induced and pose-induced movements is also validated by visualizing the generated images and analyzing the facial image retrieval results qualitatively and quantitatively.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0162-8828
1939-3539
2160-9292
1939-3539
DOI:10.1109/TPAMI.2020.3011063