MultiMediate'23: Engagement Estimation and Bodily Behaviour Recognition in Social Interactions
This work addresses the problem of enabling machines to analyze human social behaviour for improved interaction, but it is incremental as it focuses on dataset annotation and baseline setup rather than new methods.
The paper introduced the MultiMediate'23 challenge, tackling engagement estimation and bodily behaviour recognition in social interactions by providing novel annotations for the NOXI database and MPIIGroupInteraction corpus, with baseline results established for both tasks.
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.