Multi-Output Random Forests for Facial Action Unit Detection

Authors:

Abstract
Facial Action Unit (AU) prediction is a challenging task as it supposes analysing subtle muscular activations under a number of morphological and environmental variations. Furthermore, the scarcity of the available data makes end-to-end training (e.g. using deep learning techniques) difficult. In this paper, we propose to use recently proposed local expression-driven features along with a facial mesh refined using an adaptive strategy in order to better capture subtle deformations. Furthermore, we use multi-output Random Forests to capture the correlations between closely related AU description tasks. Eventually, we draw a thorough comparative study of different techniques for training multi-output Random Forests, and present a complete framework for AU detection that significantly outperforms state-of-the-art approaches on both prototypical and spontaneous data.