DeepCoder: semi-parametric variational autoencoders for automatic facial action coding
File(s)
Accepted version
Author(s)
Type
Conference Paper
Abstract
Human face exhibits an inherent hierarchy in its representations (i.e., holistic facial expressions can be encoded via a set of facial action units (AUs) and their intensity). Variational (deep) auto-encoders (VAE) have shown great results in unsupervised extraction of hierarchical latent representations from large amounts of image data, while being robust to noise and other undesired artifacts. Potentially, this makes VAEs a suitable approach for learning facial features for AU intensity estimation. Yet, most existing VAE-based methods apply classifiers learned separately from the encoded features. By contrast, the non-parametric. (probabilistic) approaches, such as Gaussian Processes (GPs), typically outperform their parametric counterparts, but cannot deal easily with large amounts of data. To this end, we propose a novel VAE semi-parametric modeling framework, named DeepCoder, which combines the modeling power of parametric (convolutional) and non-parametric. (ordinal GPs) VAEs, for joint learning of(l) latent representations at multiple levels in a task hierarchy1, and (2) classification of multiple ordinal outputs. We show on benchmark datasets for AU intensity estimation that the proposed DeepCoder outperforms the state-of-the-art approaches, and related VAEs and deep learning models.
Date Issued
2017-12
Date Acceptance
2017-12-01
Citation
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, 16, pp.3209-3218
ISSN
1550-5499
Publisher
IEEE
Start Page
3209
End Page
3218
Journal / Book Title
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
Volume
16
Copyright Statement
© 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Sponsor
Commission of the European Communities
Grant Number
688835
Source
16th IEEE International Conference on Computer Vision (ICCV)
Subjects
Science & Technology
Technology
Computer Science, Artificial Intelligence
Engineering, Electrical & Electronic
Computer Science
Engineering
LATENT VARIABLE MODELS
REPRESENTATIONS
Publication Status
Published
Start Date
2017-10-22
Finish Date
2017-10-29
Coverage Spatial
Venice, ITALY
Date Publish Online
2017-12-25