Emotion Recognition with Incomplete Labels Using Modified Multi-task Learning Technique
This work addresses emotion recognition in the wild for applications like human-computer interaction, but it is incremental as it builds on existing multi-task learning methods.
The paper tackled emotion recognition with incomplete labels by using a modified multi-task learning technique that leverages associations between seven basic emotions and twelve action units from the AffWild2 dataset, resulting in large performance improvements for both tasks compared to single-label models.
The task of predicting affective information in the wild such as seven basic emotions or action units from human faces has gradually become more interesting due to the accessibility and availability of massive annotated datasets. In this study, we propose a method that utilizes the association between seven basic emotions and twelve action units from the AffWild2 dataset. The method based on the architecture of ResNet50 involves the multi-task learning technique for the incomplete labels of the two tasks. By combining the knowledge for two correlated tasks, both performances are improved by a large margin compared to those with the model employing only one kind of label.