MultiMediate'23: Engagement Estimation and Bodily Behaviour Recognition in Social Interactions
Philipp M\"uller, Michal Balazia, Tobias Baur, Michael Dietz,, Alexander Heimerl, Dominik Schiller, Mohammed Guermal, Dominike Thomas,, Fran\c{c}ois Br\'emond, Jan Alexandersson, Elisabeth Andr\'e, Andreas Bulling

TL;DR
This paper introduces the MultiMediate'23 challenge focusing on engagement estimation and bodily behaviour recognition in social interactions, providing new annotated datasets and baseline results for these tasks.
Contribution
It presents the first controlled challenge for social behaviour analysis, with novel annotations and baseline results for engagement and bodily behaviour recognition.
Findings
New annotated datasets for engagement and bodily behaviour
Baseline results established for both tasks
First controlled challenge in social behaviour analysis
Abstract
Automatic analysis of human behaviour is a fundamental prerequisite for the creation of machines that can effectively interact with- and support humans in social interactions. In MultiMediate'23, we address two key human social behaviour analysis tasks for the first time in a controlled challenge: engagement estimation and bodily behaviour recognition in social interactions. This paper describes the MultiMediate'23 challenge and presents novel sets of annotations for both tasks. For engagement estimation we collected novel annotations on the NOvice eXpert Interaction (NOXI) database. For bodily behaviour recognition, we annotated test recordings of the MPIIGroupInteraction corpus with the BBSI annotation scheme. In addition, we present baseline results for both challenge tasks.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
