Multimodal Conversational Events Estimation in Complex Social Scenes

Conference Paper (2025)
Author(s)

Litian Li (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Research Group
Pattern Recognition and Bioinformatics
DOI related publication
https://doi.org/10.1145/3716553.3750821 Final published version
More Info
expand_more
Publication Year
2025
Language
English
Research Group
Pattern Recognition and Bioinformatics
Bibliographical Note
Green Open Access added to TU Delft Institutional Repository as part of the Taverne amendment. More information about this copyright law amendment can be found at https://www.openaccess.nl. Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.
Pages (from-to)
716-720
Publisher
ACM
ISBN (electronic)
9798400714993
Event
27th International Conference on Multimodal Interaction, ICMI 2025 (2025-10-13 - 2025-10-17), Canberra, Australia
Downloads counter
28
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Conversational events, such as speaking turns, backchannels, topic changes, and laughter, are central to the structure of multiparty interaction and play a key role in shaping its dynamics. However, detecting such events in real world social settings remains challenging due to perceptual ambiguity, visual occlusion, signal noise, and limitations in acquiring high quality audio data. This work addresses these challenges by focusing on spontaneous interactions in socially complex and privacy sensitive environments, exploring multimodal, nonverbal cues that do not rely on audio. The goal is to develop a novel modeling approach for group context awareness to infer conversational events and support social scene understanding under real world constraints..

Files

3716553.3750821.pdf
(pdf | 1.19 Mb)
- Embargo expired in 12-04-2026
License info not available