A 20TB multimodal dyadic corpus with face video, thermal dynamics, voice, physiology, and stance annotations for 45 interactions enables new social signal modeling.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
citing papers explorer
-
Inter-Stance: A Dyadic Multimodal Corpus for Conversational Stance Analysis
A 20TB multimodal dyadic corpus with face video, thermal dynamics, voice, physiology, and stance annotations for 45 interactions enables new social signal modeling.
- Ordering Matters: Rank-Aware Selective Fusion for Blended Emotion Recognition