Emotion and Mood Recognition

The paper identifies individualized brain-body signatures of positive emotions using multimodal neurophysiological data and finds that emotions are represented by person-specific multimodal ensembles.

ASD-FER introduces a benchmark dataset for facial emotion recognition in children with ASD and evaluates multiple models, finding ViT achieves the highest accuracy on a held-out set.

The paper shows that shared experimental materials in decoding benchmarks inflate cross-participant accuracy and alter method rankings.