Salience Adjustment for Context-Based Emotion Recognition
This work addresses emotion recognition for social interaction analysis, but it appears incremental as it builds on existing methods like Bayesian Cue Integration and Visual-Language Models.
The paper tackled emotion recognition in dynamic social contexts by proposing a salience-adjusted framework that integrates facial and contextual cues, showing enhanced performance in prisoner's dilemma scenarios.
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.