MultiMediate '23: Engagement Estimation and Bodily Behaviour Recognition in Social Interactions - Archive ouverte HAL
Communication Dans Un Congrès Année : 2023

MultiMediate '23: Engagement Estimation and Bodily Behaviour Recognition in Social Interactions

Mohammed Guermal
Dominike Thomas
Andreas Bulling

Résumé

Automatic analysis of human behaviour is a fundamental prerequisite for the creation of machines that can effectively interact withand 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.
Fichier principal
Vignette du fichier
2023_ACMMM.pdf (1.49 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04330332 , version 1 (08-12-2023)

Identifiants

Citer

Philipp Müller, Michal Balazia, Tobias Baur, Michael Dietz, Alexander Heimerl, et al.. MultiMediate '23: Engagement Estimation and Bodily Behaviour Recognition in Social Interactions. MM 2023 - The 31st ACM International Conference on Multimedia, ACM, Oct 2023, Ottawa, Canada. pp.9640-9645, ⟨10.1145/3581783.3613851⟩. ⟨hal-04330332⟩
90 Consultations
82 Téléchargements

Altmetric

Partager

More