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.
@article{arxiv.2308.08256,
title = {MultiMediate'23: Engagement Estimation and Bodily Behaviour Recognition in Social Interactions},
author = {Philipp Müller and Michal Balazia and Tobias Baur and Michael Dietz and Alexander Heimerl and Dominik Schiller and Mohammed Guermal and Dominike Thomas and François Brémond and Jan Alexandersson and Elisabeth André and Andreas Bulling},
journal= {arXiv preprint arXiv:2308.08256},
year = {2023}
}