AffectAI-Capture is a reproducible multimodal protocol for small-group meetings that integrates eye tracking, physiology, audio, video, and self-reports around a single event timeline and standardized outputs.
In: 2003 IEEE International Conference on Acoustics, Speech, and Signal Pro- cessing (ICASSP ’03)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
A cross-domain evaluation pipeline for AI meeting summaries finds no statistically significant accuracy differences among GPT models but shows gpt-5.1 leading on retention metrics like completeness (0.886) and coverage (0.942).
citing papers explorer
-
AffectAI-Capture: A Reproducible Multimodal Protocol for Small-Group Meeting Research
AffectAI-Capture is a reproducible multimodal protocol for small-group meetings that integrates eye tracking, physiology, audio, video, and self-reports around a single event timeline and standardized outputs.
-
Evaluating AI Meeting Summaries with a Reusable Cross-Domain Pipeline
A cross-domain evaluation pipeline for AI meeting summaries finds no statistically significant accuracy differences among GPT models but shows gpt-5.1 leading on retention metrics like completeness (0.886) and coverage (0.942).