This workshop aims at advancing the state-of-the-art in the problem of analysis of human affective behavior in-the-wild. Representing human emotions has been a basic topic of research. The most frequently used emotion representation is the categorical one, including the seven basic categories, i.e., Anger, Disgust, Fear, Happiness, Sadness, Surprise and Neutral. Discrete emotion representation can also be described in terms of the Facial Action Coding System model, in which all possible facial actions are described in terms of Action Units (AUs). Finally, the dimensional model of affect has been proposed as a means to distinguish between subtly different displays of affect and encode small changes in the intensity of each emotion on a continuous scale. The 2-D Valence and Arousal Space (VA-Space) is the most usual dimensional emotion representation; valence shows how positive or negative an emotional state is, whilst arousal shows how passive or active it is.
The workshop is composed of the following: At first, it contains three Challenges, which are based, for the first time, on the same database; these target (i) dimensional affect recognition (in terms of valence and arousal), (ii) categorical affect classification (in terms of the seven basic emotions) and (iii) facial action unit detection, in -the-wild. These Challenges will produce a significant step forward when compared to previous events. In particular, they use the Aff-Wild2, the first comprehensive benchmark for all three affect recognition tasks in-the-wild. In addition, the Workshop does not only focus on the three Challenges. It will solicit any original paper on databases, benchmarks and technical contributions related to affect recognition, using audio, visual or other modalities (e.g., EEG), in unconstrained conditions. Either uni-modal, or multi-modal approaches will be considered. It would be of particular interest to see methodologies that study detection of action units based on audio data.
- Stefanos Zafeiriou
- Dimitrios Kollias
- Attila Schulc