MUMBAI: multi-person, multimodal board game affect and interaction analysis dataset

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 hour...

Full description

Saved in:
Bibliographic Details
Published in:Journal on multimodal user interfaces 2021-12, Vol.15 (4), p.373-391
Main Authors: Doyran, Metehan, Schimmel, Arjan, Baki, Pınar, Ergin, Kübra, Türkmen, Batıkan, Salah, Almıla Akdağ, Bakkes, Sander C. J., Kaya, Heysem, Poppe, Ronald, Salah, Albert Ali
Format: Article
Language:English
Subjects:
Computer Science
Datasets
Games
Group dynamics
Image Processing and Computer Vision
Original Paper
Signal,Image and Speech Processing
Social factors
User Interfaces and Human Computer Interaction
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1783-7677
1783-8738
DOI:10.1007/s12193-021-00364-0