Salience Adjustment for Context-Based Emotion Recognition

TL;DR

This paper introduces a salience-adjusted framework combining Bayesian Cue Integration and Visual-Language Models to improve emotion recognition by dynamically weighting facial and contextual cues, especially in social scenarios.

Contribution

It proposes a novel salience adjustment method for context-aware emotion recognition that integrates Bayesian and visual-language models for better accuracy.

Findings

Salience adjustment improves emotion recognition performance.

Framework effectively captures complex social emotional cues.

Demonstrated on prisoner's dilemma scenarios with human and automatic annotations.

Abstract

Emotion recognition in dynamic social contexts requires an understanding of the complex interaction between facial expressions and situational cues. This paper presents a salience-adjusted framework for context-aware emotion recognition with Bayesian Cue Integration (BCI) and Visual-Language Models (VLMs) to dynamically weight facial and contextual information based on the expressivity of facial cues. We evaluate this approach using human annotations and automatic emotion recognition systems in prisoner's dilemma scenarios, which are designed to evoke emotional reactions. Our findings demonstrate that incorporating salience adjustment enhances emotion recognition performance, offering promising directions for future research to extend this framework to broader social contexts and multimodal applications.