Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
The paper introduces VIP-MINGLE, a comprehensive multimodal dataset designed to facilitate the study of group conversations in both in-person and videoconferencing contexts, comprising 59 hours of recordings from 32 groups with 105 participants. This dataset includes a variety of data types, such as raw audio/video, psychometric data, and processed multimodal features, enabling a nuanced analysis of conversational dynamics. The findings indicate significant behavioral distribution shifts across modalities between the two settings, underscoring the necessity for a dataset that bridges these environments to enhance model development for group interactions.
Significant behavioral shifts in group conversation dynamics reveal that context matters more than previously understood, highlighting the need for datasets that span both in-person and virtual interactions.
Group conversations are a fundamental yet complex form of social interaction central to human cognition and telecommunication technology. While understanding and facilitating these interactions has been a long-standing goal, findings are often isolated within specific in-person or videoconferencing settings due to a scarcity of datasets that bridge the two. We introduce VIP-MINGLE, a multimodal dataset comprising 59 hours of recordings (32 groups, 105 participants), featuring paired within-subject sessions in both settings. The dataset includes raw audio/video, psychometric data, processed multimodal features (e.g., diarized speech, facial expressions, transcriptions), and time-resolved human annotations. Our analysis reveals significant behavioral distribution shifts across multiple modalities between settings, reinforcing the need for a cross-setting corpus. VIP-MINGLE serves as a critical resource for developing robust models of group conversations across settings.