Facial Affect Recognition in the Wild Using Multi-Task Learning Convolutional Network
This work addresses the problem of automated facial affect analysis in real-world scenarios for applications in human-computer interaction and psychology, presenting an incremental improvement through multi-task learning.
The paper tackles facial affect recognition in unconstrained environments by proposing MTANet, a multi-task learning convolutional network based on SE-ResNet modules, which simultaneously estimates valence and arousal, action units, and seven basic emotions, achieving CCC rates of 0.28 and 0.34 for valence and arousal, and F1-scores of 0.427 and 0.32 for action units detection and emotion classification.
This paper presents a neural network based method Multi-Task Affect Net(MTANet) submitted to the Affective Behavior Analysis in-the-Wild Challenge in FG2020. This method is a multi-task network and based on SE-ResNet modules. By utilizing multi-task learning, this network can estimate and recognize three quantified affective models: valence and arousal, action units, and seven basic emotions simultaneously. MTANet achieve Concordance Correlation Coefficient(CCC) rates of 0.28 and 0.34 for valence and arousal, F1-score of 0.427 and 0.32 for AUs detection and categorical emotion classification.