Analysing Affective Behavior in the Second ABAW2 Competition

Dimitrios Kollias, Stefanos Zafeiriou; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2021, pp. 3652-3660

The Affective Behavior Analysis in-the-wild (ABAW2) 2021 Competition is the second Competition -following the first very successful ABAW Competition held in conjunction with IEEE Conference on Face and Gesture Recognition 2020- that aims at automatically analyzing affect. ABAW2 is split into three Challenges, each one addressing one of the three main behavior tasks of Valence-Arousal Estimation, Seven Basic Expression Classification and Twelve Action Unit Detection. All three Challenges are based on a common benchmark database, Aff-Wild2, which is a large scale in-the-wild database and the first one to be annotated for all these three tasks. In this paper, we describe this Competition, to be held in conjunction with the International Conference on Computer Vision (ICCV) 2021. We present the three Challenges, with the utilized Competition corpora. We outline the evaluation metrics and present both the baseline systems and the top-5 performing teams' per Challenge; finally we present the obtained results of the baseline systems and of all participating teams. More information regarding the Competition, the leaderboard of each Challenge and details for accessing the utilized database, are provided in the Competition website: https://ibug.doc.ic.ac.uk/resources/iccv-2021-2nd-abaw/.