Analysing Affective Behavior in the second ABAW2 Competition

TL;DR

This paper analyzes the ABAW2 2021 Competition, which focuses on automatic affect analysis through three challenges on valence-arousal, expression, and action units, using the large-scale Aff-Wild2 database.

Contribution

It introduces the ABAW2 competition, details its three challenges, and provides baseline systems and evaluation metrics for affective behavior analysis.

Findings

Baseline system results are presented for each challenge.

The Aff-Wild2 database is validated as a comprehensive benchmark.

The competition fosters progress in in-the-wild affective behavior analysis.

Abstract

The Affective Behavior Analysis in-the-wild (ABAW2) 2021 Competition is the second -- following the first very successful ABAW Competition held in conjunction with IEEE FG 2020- Competition 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, basic expression classification and 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 ICCV 2021. We present the three Challenges, with the utilized Competition corpora. We outline the evaluation metrics and present the baseline system with its results. More information regarding the Competition is provided in the Competition site: https://ibug.doc.ic.ac.uk/resources/iccv-2021-2nd-abaw.