Global-Local Attention for Emotion Recognition

TL;DR

This paper introduces a novel deep network with global-local attention for emotion recognition, effectively integrating facial and contextual cues to improve accuracy over existing methods.

Contribution

The proposed global-local attention mechanism uniquely combines facial and context features, enhancing emotion recognition performance and interpretability.

Findings

Outperforms state-of-the-art on recent emotion datasets

Produces more meaningful attention maps

Demonstrates improved discrimination of emotional cues

Abstract

Human emotion recognition is an active research area in artificial intelligence and has made substantial progress over the past few years. Many recent works mainly focus on facial regions to infer human affection, while the surrounding context information is not effectively utilized. In this paper, we proposed a new deep network to effectively recognize human emotions using a novel global-local attention mechanism. Our network is designed to extract features from both facial and context regions independently, then learn them together using the attention module. In this way, both the facial and contextual information is used to infer human emotions, therefore enhancing the discrimination of the classifier. The intensive experiments show that our method surpasses the current state-of-the-art methods on recent emotion datasets by a fair margin. Qualitatively, our global-local attention module can extract more meaningful attention maps than previous methods. The source code and trained model of our network are available at https://github.com/minhnhatvt/glamor-net