Emotion recognition and understanding is a vital componentin human-machine interaction. Dimensional models of affectsuch as those using valence and arousal have advantages overtraditional categorical ones due to the complexity of emo-tional states in humans. However, dimensional emotion an-notations are difficult and expensive to collect, therefore theyare still limited in the affective computing community. To ad-dress these issues, we propose a method to generate syntheticimages from existing categorical emotion datasets using facemorphing, with full control over the resulting sample distri-bution as well as dimensional labels in the circumplex space,while achieving augmentation factors of at least 20x or more.
View on arXiv