Multi-Label Class Balancing Algorithm for Action Unit Detection
This work addresses dataset imbalance for researchers in affective computing, but it is incremental as it builds on existing methods for a specific challenge.
The paper tackles the problem of imbalanced datasets in Action Unit detection by introducing a multi-label class balancing algorithm, achieving competitive performance on the ABAW challenge benchmark.
Isolated facial movements, so-called Action Units, can describe combined emotions or physical states such as pain. As datasets are limited and mostly imbalanced, we present an approach incorporating a multi-label class balancing algorithm. This submission is subject to the Action Unit detection task of the Affective Behavior Analysis in-the-wild (ABAW) challenge at the IEEE Conference on Face and Gesture Recognition 2020.