The field of emotion recognition and modeling is moving towards a more nuanced understanding of human emotions, taking into account individual differences, contextual factors, and temporal dynamics. Recent studies have highlighted the importance of integrating physiological, psychological, and behavioral data to improve emotion recognition accuracy. The use of multimodal datasets, such as those including eye-tracking, EEG, and personality assessments, has been shown to enhance the precision of emotion modeling. Additionally, research has focused on the temporal dynamics of emotional processes, including facial mimicry and emotional impulsivity. These advancements have significant implications for the development of more accurate, adaptive, and individualized emotion recognition systems. Noteworthy papers include:

• A study on modelling emotions in face-to-face settings, which demonstrated the benefit of combining eye-tracking data, temporal dynamics, and personality traits to enhance emotion detection.
• The introduction of a novel multimodal emotion recognition dataset, EVA-MED, which captures a broad spectrum of affective responses while accounting for individual differences.
• A study on exploring the temporal dynamics of facial mimicry in emotion processing, which revealed significant emotional variations and correlations with personality traits.