DeepCoder: Semi-parametric Variational Autoencoders for Automatic Facial Action Coding
This work addresses facial expression analysis for applications like human-computer interaction, but it is incremental as it builds on existing VAE and Gaussian Process methods.
The authors tackled the problem of automatic facial action unit (AU) intensity estimation by proposing DeepCoder, a semi-parametric variational autoencoder framework that combines parametric and non-parametric models for joint learning of hierarchical latent representations and ordinal classification, achieving state-of-the-art performance on benchmark datasets.
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.