Abstract
Analyzing emotion from verbal and non-verbal behavioral cues is critical for many intelligent human-centric systems. The emotional cues can be captured using audio, video, motion-capture (mocap) or other modalities. We propose a generalized graph approach to emotion recognition that can take any time-varying (dynamic) data modality as input. To alleviate the problem of optimal graph construction, we cast this as a joint graph learning and classification task. To this end, we present the \emph{Learnable Graph Inception Network} (L-GrIN) that jointly learns to recognize emotion and to identify the underlying graph structure in data. Our architecture comprises multiple novel components: a new graph convolution operation, a graph inception layer, learnable adjacency, and a learnable pooling function that yields a graph-level embedding. We evaluate the proposed architecture on four benchmark emotion recognition databases spanning three different modalities (video, audio, mocap), where each database captures one of the following emotional cues: facial expressions, speech and body gestures. We achieve state-of-the-art performance on all databases outperforming several competitive baselines and relevant existing methods.
Abstract (translated)
URL
https://arxiv.org/abs/2008.02661
