Multiple Emotion Descriptors Estimation at the ABAW3 Challenge
This work addresses emotion recognition for affective computing applications, but it is incremental as it builds on existing theories and datasets.
The paper tackled the problem of estimating multiple emotion descriptors from facial expressions by designing distinct architectures for facial action units and emotion messages, achieving superior performance over two baseline models on the ABAW3 challenge dataset.
To describe complex emotional states, psychologists have proposed multiple emotion descriptors: sparse descriptors like facial action units; continuous descriptors like valence and arousal; and discrete class descriptors like happiness and anger. According to Ekman and Friesen, 1969, facial action units are sign vehicles that convey the emotion message, while discrete or continuous emotion descriptors are the messages perceived and expressed by human. In this paper, we designed an architecture for multiple emotion descriptors estimation in participating the ABAW3 Challenge. Based on the theory of Ekman and Friesen, 1969, we designed distinct architectures to measure the sign vehicles (i.e., facial action units) and the message (i.e., discrete emotions, valence and arousal) given their different properties. The quantitative experiments on the ABAW3 challenge dataset has shown the superior performance of our approach over two baseline models.