arXiv subjects

Dustin Freeman

Publications and source records attributed to Dustin Freeman.

4 recordsLinked to original sources

arXiv2026

VIP-MINGLE: A Corpus for Videoconference and In-Person Multimodal Interaction in Group Language Engagement

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.

cs.HC↗

arXiv2025

Multimodal Fusion with Semi-Supervised Learning Minimizes Annotation Quantity for Modeling Videoconference Conversation Experience

Group conversations over videoconferencing are a complex social behavior. However, the subjective moments of negative experience, where the conversation loses fluidity or enjoyment remain understudied. These moments are infrequent in naturalistic data, and thus training a supervised learning (SL) model requires costly manual data annotation. We applied semi-supervised learning (SSL) to leverage targeted labeled and unlabeled clips for training multimodal (audio, facial, text) deep features to predict non-fluid or unenjoyable moments in holdout videoconference sessions. The modality-fused co-training SSL achieved an ROC-AUC of 0.9 and an F1 score of 0.6, outperforming SL models by up to 4% with the same amount of labeled data. Remarkably, the best SSL model with just 8% labeled data matched 96% of the SL model's full-data performance. This shows an annotation-efficient framework for modeling videoconference experience.

eess.AS↗

arXiv2025

Multimodal Machine Learning Can Predict Videoconference Fluidity and Enjoyment

Videoconferencing is now a frequent mode of communication in both professional and informal settings, yet it often lacks the fluidity and enjoyment of in-person conversation. This study leverages multimodal machine learning to predict moments of negative experience in videoconferencing. We sampled thousands of short clips from the RoomReader corpus, extracting audio embeddings, facial actions, and body motion features to train models for identifying low conversational fluidity, low enjoyment, and classifying conversational events (backchanneling, interruption, or gap). Our best models achieved an ROC-AUC of up to 0.87 on hold-out videoconference sessions, with domain-general audio features proving most critical. This work demonstrates that multimodal audio-video signals can effectively predict high-level subjective conversational outcomes. In addition, this is a contribution to research on videoconferencing user experience by showing that multimodal machine learning can be used to identify rare moments of negative user experience for further study or mitigation.

cs.LG↗

arXiv2015

A Dataset of Naturally Occurring, Whole-Body Background Activity to Reduce Gesture Conflicts

In real settings, natural body movements can be erroneously recognized by whole-body input systems as explicit input actions. We call body activity not intended as input actions "background activity." We argue that understanding background activity is crucial to the success of always-available whole-body input in the real world. To operationalize this argument, we contribute a reusable study methodology and software tools to generate standardized background activity datasets composed of data from multiple Kinect cameras, a Vicon tracker, and two high-definition video cameras. Using our methodology, we create an example background activity dataset for a television-oriented living room setting. We use this dataset to demonstrate how it can be used to redesign a gestural interaction vocabulary to minimize conflicts with the real world. The software tools and initial living room dataset are publicly available (http://www.dgp.toronto.edu/~dustin/backgroundactivity/).

cs.HC↗