Feature-wise Optimization and Performance-weighted Multimodal Fusion for Social Perception Recognition

Automatic social perception recognition is a new task to mimic the measurement of human traits, which was previously done by humans via questionnaires. We evaluated unimodal and multimodal systems to predict agentive and communal traits from the LMU-ELP dataset. We optimized variants of recurrent neural networks from each feature from audio and video data and then fused them to predict the traits. Results on the development set show a consistent trend that multimodal fusion outperforms unimodal systems. The performance-weighted fusion also consistently outperforms mean and maximum fusions. We found two important factors that influence the performance of performance-weighted fusion. These factors are normalization and the number of models.