Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFace

TL;DR

This paper introduces Aff-Wild2, a comprehensive in-the-wild audiovisual database annotated for multiple emotion and behavior tasks, and demonstrates state-of-the-art performance using CNN and CNN-RNN models with ArcFace loss.

Contribution

The creation of Aff-Wild2, the largest multi-task in-the-wild emotion database, and the development of new CNN-based models with ArcFace loss for improved emotion recognition.

Findings

Achieved state-of-the-art results on 10 emotion databases.

Demonstrated the effectiveness of ArcFace loss in emotion recognition.

Extended the largest in-the-wild database to include multiple behavior annotations.

Abstract

Affective computing has been largely limited in terms of available data resources. The need to collect and annotate diverse in-the-wild datasets has become apparent with the rise of deep learning models, as the default approach to address any computer vision task. Some in-the-wild databases have been recently proposed. However: i) their size is small, ii) they are not audiovisual, iii) only a small part is manually annotated, iv) they contain a small number of subjects, or v) they are not annotated for all main behavior tasks (valence-arousal estimation, action unit detection and basic expression classification). To address these, we substantially extend the largest available in-the-wild database (Aff-Wild) to study continuous emotions such as valence and arousal. Furthermore, we annotate parts of the database with basic expressions and action units. As a consequence, for the first time, this allows the joint study of all three types of behavior states. We call this database Aff-Wild2. We conduct extensive experiments with CNN and CNN-RNN architectures that use visual and audio modalities; these networks are trained on Aff-Wild2 and their performance is then evaluated on 10 publicly available emotion databases. We show that the networks achieve state-of-the-art performance for the emotion recognition tasks. Additionally, we adapt the ArcFace loss function in the emotion recognition context and use it for training two new networks on Aff-Wild2 and then re-train them in a variety of diverse expression recognition databases. The networks are shown to improve the existing state-of-the-art. The database, emotion recognition models and source code are available at http://ibug.doc.ic.ac.uk/resources/aff-wild2.