ABAW: Valence-Arousal Estimation, Expression Recognition, Action Unit Detection & Emotional Reaction Intensity Estimation Challenges

Dimitrios Kollias, Panagiotis Tzirakis, Alice Baird, Alan Cowen, Stefanos Zafeiriou

Abstract: The 5th ABAW Competition is part of the respective Workshop held in conjunction with IEEE CVPR 2023 and is a continuation of the Competitions held at ECCV 2022, IEEE CVPR 2022, ICCV 2021, IEEE FG 2020 and CVPR 2017 Conferences. It is dedicated at automatically analyzing affect. For this year’s Competition, we feature two corpora: i) an extended version of the Aff-Wild2 database and ii) the Hume-Reaction dataset. The former database is an audiovisual (A/V) one of around 600 videos of around 3M frames and is annotated for: a) two continuous affect dimensions, valence (how positive/negative a person is) and arousal (how active/passive a person is); b) basic expressions (e.g. happiness, neutral); and c) action units (i.e., facial muscle actions). The latter dataset is A/V in which reactions of individuals to emotional stimuli have been annotated for seven emotional expression intensities. Thus the 5th ABAW Competition encompasses four Challenges: i) Valence-Arousal Estimation, ii) Expression Classification, iii) Action Unit Detection, and iv) Emotional Reaction Intensity Estimation. In this paper, we present these Challenges and their corpora, we outline the evaluation metrics and present the baseline systems and top performing teams’ per Challenge along with their obtained performance. More information for the Competition can be found in: https://ibug.doc.ic.ac.uk/resources/ cvpr-2023-5th-abaw.