# Context-Aware Emotion Recognition Networks

## TL;DR

This paper introduces CAER-Net, a deep neural network that improves emotion recognition by jointly analyzing facial expressions and contextual scene information using attention mechanisms and adaptive fusion.

## Contribution

The paper proposes a novel deep network architecture for context-aware emotion recognition and introduces a new benchmark dataset called CAER for evaluating such models.

## Key findings

- CAER-Net outperforms existing methods on several benchmarks.
- Context information significantly enhances emotion recognition accuracy.
- The CAER dataset provides a more comprehensive evaluation platform.

## Abstract

Traditional techniques for emotion recognition have focused on the facial expression analysis only, thus providing limited ability to encode context that comprehensively represents the emotional responses. We present deep networks for context-aware emotion recognition, called CAER-Net, that exploit not only human facial expression but also context information in a joint and boosting manner. The key idea is to hide human faces in a visual scene and seek other contexts based on an attention mechanism. Our networks consist of two sub-networks, including two-stream encoding networks to seperately extract the features of face and context regions, and adaptive fusion networks to fuse such features in an adaptive fashion. We also introduce a novel benchmark for context-aware emotion recognition, called CAER, that is more appropriate than existing benchmarks both qualitatively and quantitatively. On several benchmarks, CAER-Net proves the effect of context for emotion recognition. Our dataset is available at http://caer-dataset.github.io.