DeepCoder: Semi-Parametric Variational Autoencoders for Automatic Facial Action Coding

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 representa...

Full description

Bibliographic Details

Published in:	2017 IEEE International Conference on Computer Vision (ICCV) pp. 3209 - 3218
Main Authors:	Dieu Linh Tran, Walecki, Robert, Rudovic, Ognjen, Eleftheriadis, Stefanos, Schuller, Bjorn, Pantic, Maja
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01-10-2017
Subjects:	Decoding Encoding Estimation Face Feature extraction Gold Image reconstruction
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!