Temporally Selective Attention Model for Social and Affective State Recognition in Multimedia Content

The sheer amount of human-centric multimedia content has led to increased research on human behavior understanding. Most existing methods model behavioral sequences without considering the temporal saliency. This work is motivated by the psychological observation that temporally selective attention enables the human perceptual system to process the most relevant information. In this paper, we introduce a new approach, named Temporally Selective Attention Model (TSAM), designed to selectively attend to salient parts of human-centric video sequences. Our TSAM models learn to recognize affective and social states using a new loss function called speaker-distribution loss. Extensive experiments show that our model achieves the state-of-the-art performance on rapport detection and multimodal sentiment analysis. We also show that our speaker-distribution loss function can generalize to other computational models, improving the prediction performance of deep averaging network and Long Short Term Memory (LSTM).