Abstract

Automatic understanding of human affect using visual signals is of great importance in everyday human–machine interactions. Appraising human emotional states, behaviors and reactions displayed in real-world settings, can be accomplished using latent continuous dimensions (e.g., the circumplex model of affect). Valence (i.e., how positive or negative is an emotion) and arousal (i.e., power of the activation of the emotion) constitute popular and effective representations for affect. Nevertheless, the majority of collected datasets until 2016, although containing naturalistic emotional states, have been captured in highly controlled recording conditions. In this work, we introduce the Aff-Wild benchmark for training and evaluating affect recognition algorithms. We also organized the First Affect-in-the-wild Challenge (Aff-Wild Challenge) in conjunction with CVPR 2017 on the Aff-Wild database, and was the first ever challenge on the estimation of valence and arousal in-the-wild. Finally, we propose an end-to-end deep learning architecture, AffWildNet, which produces state-of-the-art results on the Aff-Wild Database. 

How to acquire the data

The Aff-Wild database has been extended with more videos and annotations in terms of action units, basic expressions (and valence-arousal). The newly formed database is called Aff-Wild2. More details can be found here.
If you wish to access Aff-Wild specifically, please follow the same application procedure outlined in the link above for Aff-Wild2. In your application email, please clearly indicate that you are requesting access to the Aff-Wild database.

Source Code

The source code and the trained weights of various models can be found in the following github repository:

https://github.com/dkollias/Aff-Wild-models

Note that the source code and the model weights are made available for academic non-commercial research purposes only. If you want to use them for any other purpose (eg industrial -either research or commercial-) email: d.kollias@qmul.ac.uk 

Important Information

• All the images of the database are obtained from Youtube. We are not responsible for the content nor the meaning of these images.