1. DeepCoder: Semi-Parametric Variational Autoencoders for Automatic Facial Action Coding
- Author
-
Björn Schuller, Stefanos Eleftheriadis, Robert Walecki, Ognjen Rudovic, Maja Pantic, Dieu Linh Tran, and Commission of the European Communities
- Subjects
FOS: Computer and information sciences ,Technology ,LATENT VARIABLE MODELS ,Computer science ,Computer Vision and Pattern Recognition (cs.CV) ,Feature extraction ,Computer Science - Computer Vision and Pattern Recognition ,02 engineering and technology ,Iterative reconstruction ,010501 environmental sciences ,01 natural sciences ,Computer Science, Artificial Intelligence ,symbols.namesake ,Engineering ,0202 electrical engineering, electronic engineering, information engineering ,Gaussian process ,cs.CV ,0105 earth and related environmental sciences ,Parametric statistics ,Facial expression ,Science & Technology ,business.industry ,Deep learning ,Probabilistic logic ,Engineering, Electrical & Electronic ,Pattern recognition ,REPRESENTATIONS ,Computer Science ,symbols ,020201 artificial intelligence & image processing ,Artificial intelligence ,ddc:004 ,business ,Coding (social sciences) - 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 nonparametric (ordinal GPs) VAEs, for joint learning of (1) 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., Comment: ICCV 2017 - accepted more...
- Published
- 2017
- Full Text
- View/download PDF