Exploring Expression-related Self-supervised Learning for Affective Behaviour Analysis
This addresses the problem of expensive annotation for affective datasets, offering a more scalable solution for researchers and practitioners in affective computing.
The paper tackled expression classification in affective behavior analysis by proposing ContraWarping, a self-supervised learning method, which outperformed most existing supervised methods on the Aff-Wild2 dataset.
This paper explores an expression-related self-supervised learning (SSL) method (ContraWarping) to perform expression classification in the 5th Affective Behavior Analysis in-the-wild (ABAW) competition. Affective datasets are expensive to annotate, and SSL methods could learn from large-scale unlabeled data, which is more suitable for this task. By evaluating on the Aff-Wild2 dataset, we demonstrate that ContraWarping outperforms most existing supervised methods and shows great application potential in the affective analysis area. Codes will be released on: https://github.com/youqingxiaozhua/ABAW5.