MUMBAI
multi-person, multimodal board game affect and interaction analysis dataset
Metehan Doyran (Universiteit Utrecht)
Arjan Schimmel (Universiteit Utrecht)
Pınar Baki (Boğaziçi University)
Kübra Ergin (Sahibinden.com, Istanbul)
Batıkan Türkmen (Boğaziçi University)
Almıla Akdağ Akdag Salah (Universiteit Utrecht, TU Delft - DesIgning Value in Ecosystems, Boğaziçi University)
Sander C.J. Bakkes (Universiteit Utrecht)
Heysem Kaya (Universiteit Utrecht)
Ronald Poppe (Universiteit Utrecht)
Albert Ali Salah (Universiteit Utrecht)
More Info
expand_more
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
Board games are fertile grounds for the display of social signals, and they provide insights into psychological indicators in multi-person interactions. In this work, we introduce a new dataset collected from four-player board game sessions, recorded via multiple cameras, and containing over 46 hours of visual material. The new MUMBAI dataset is extensively annotated with emotional moments for all game sessions. Additional data comes from personality and game experience questionnaires. Our four-person setup allows the investigation of non-verbal interactions beyond dyadic settings. We present three benchmarks for expression detection and emotion classification and discuss potential research questions for the analysis of social interactions and group dynamics during board games.
help_outline