Kollias, D;
Tzirakis, P;
Nicolaou, MA;
Papaioannou, A;
Zhao, G;
Schuller, BW;
Kotsia, I;
(2019)
Deep Affect Prediction in-the-wild: Aff-Wild Database and Challenge, Deep Architectures, and Beyond.
International Journal of Computer Vision
, 127
pp. 907-929.
10.1007/s11263-019-01158-4.
Preview |
Text
Kollias2019_Article_DeepAffectPredictionIn-the-Wil.pdf - Published Version Download (2MB) | Preview |
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 this far, although containing naturalistic emotional states, have been captured in highly controlled recording conditions. In this paper, we introduce the Aff-Wild benchmark for training and evaluating affect recognition algorithms. We also report on the results of the First Affect-in-the-wild Challenge (Aff-Wild Challenge) that was recently organized 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. Furthermore, we design and extensively train an end-to-end deep neural architecture which performs prediction of continuous emotion dimensions based on visual cues. The proposed deep learning architecture, AffWildNet, includes convolutional and recurrent neural network layers, exploiting the invariant properties of convolutional features, while also modeling temporal dynamics that arise in human behavior via the recurrent layers. The AffWildNet produced state-of-the-art results on the Aff-Wild Challenge. We then exploit the AffWild database for learning features, which can be used as priors for achieving best performances both for dimensional, as well as categorical emotion recognition, using the RECOLA, AFEW-VA and EmotiW 2017 datasets, compared to all other methods designed for the same goal. The database and emotion recognition models are available at http://ibug.doc.ic.ac.uk/resou rces/first -affec t-wild-chall enge.
| Type: | Article |
|---|---|
| Title: | Deep Affect Prediction in-the-wild: Aff-Wild Database and Challenge, Deep Architectures, and Beyond |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1007/s11263-019-01158-4 |
| Publisher version: | https://doi.org/10.1007/s11263-019-01158-4 |
| Language: | English |
| Additional information: | This work is licensed under a Creative Commons Attribution 4.0 International License. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in the credit line; if the material is not included under the Creative Commons license, users will need to obtain permission from the license holder to reproduce the material. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/ |
| Keywords: | Deep, Convolutional, Recurrent, Aff-Wild, Database, Challenge, In-the-wild, Facial, Dimensional, Categorical, Emotion, Recognition, Valence, Arousal, AffWildNet, RECOLA, AFEW, AFEW-VA, EmotiW |
| UCL classification: | UCL |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10069135 |
Archive Staff Only
 |
View Item |
