7th ABAW Competition: Multi-Task Learning and Compound Expression Recognition
Dimitrios Kollias, Stefanos Zafeiriou, Irene Kotsia, Abhinav Dhall, Shreya Ghosh, Chunchang Shao, Guanyu Hu
TL;DR
This paper presents the 7th ABAW Competition (ECCV 2024), featuring two sub-challenges: Multi-Task Learning (simultaneous valence-arousal estimation, eight-expression recognition, and twelve AU detection) and Compound Expression Recognition (seven compound expressions). It leverages the static s-Aff-Wild2 dataset for MTL and a 56-video subset of C-EXPR-DB for CE, detailing datasets, preprocessing, evaluation metrics, and baseline systems. The baseline uses a VGG16-based architecture pre-trained on VGGFACE, with face cropping/alignment via RetinaFace and MixAugment augmentation, reporting an overall MTL baseline of approximately $32\%$ vs. $30\%$ without augmentation. These benchmarks provide a standardized platform for advancing robust, in-the-wild affective analysis with implications for human-centered AI and intelligent agents.
Abstract
This paper describes the 7th Affective Behavior Analysis in-the-wild (ABAW) Competition, which is part of the respective Workshop held in conjunction with ECCV 2024. The 7th ABAW Competition addresses novel challenges in understanding human expressions and behaviors, crucial for the development of human-centered technologies. The Competition comprises of two sub-challenges: i) Multi-Task Learning (the goal is to learn at the same time, in a multi-task learning setting, to estimate two continuous affect dimensions, valence and arousal, to recognise between the mutually exclusive classes of the 7 basic expressions and 'other'), and to detect 12 Action Units); and ii) Compound Expression Recognition (the target is to recognise between the 7 mutually exclusive compound expression classes). s-Aff-Wild2, which is a static version of the A/V Aff-Wild2 database and contains annotations for valence-arousal, expressions and Action Units, is utilized for the purposes of the Multi-Task Learning Challenge; a part of C-EXPR-DB, which is an A/V in-the-wild database with compound expression annotations, is utilized for the purposes of the Compound Expression Recognition Challenge. In this paper, we introduce the two challenges, detailing their datasets and the protocols followed for each. We also outline the evaluation metrics, and highlight the baseline systems and their results. Additional information about the competition can be found at \url{https://affective-behavior-analysis-in-the-wild.github.io/7th}.