Published November 5, 2026
| Version 1.0
Other
Open
Supplementary Material and Reproducibility Records for When Audio and Video Mislead: Evaluating Multimodal AI for Conversational Emotion Recognition
Description
Supplementary material and reproducibility records for the AICompS 2026 paper "When Audio and Video Mislead: Evaluating Multimodal AI for Conversational Emotion Recognition". Raw MELD and IEMOCAP media, dataset transcripts, free-form model responses and model weights are not redistributed. Licenses on this record apply only to the authors' own materials; third-party datasets, models and dependencies retain their own terms.