MultiMediate: Multi-modal Behaviour Analysis for Artificial Mediation Call for Papers

== Call for Participation in ACM MM'24 Grand Challenge ==

== MultiMediate: Multi-modal Behaviour Analysis for Artificial Mediation ==

== https://multimediate-challenge.org/ ==

Artificial mediators are a promising approach to support
conversations, but at present their abilities are limited by
insufficient progress in behaviour sensing and analysis. The
MultiMediate challenge is designed to work towards the vision of
effective artificial mediators by facilitating and measuring progress
on key social behaviour sensing and analysis tasks. This year, the
challenge focuses on the estimation of engagement across different
domains. In addition, we continue to accept submissions to the most
popular tasks of previous MultiMediate iterations, including
backchannel detection, eye contact detection, and bodily behaviour
recognition.

== Engagement Estimation Task ==

Knowing how engaged participants are is important for a mediator whose
goal it is to keep engagement at a high level. The complex nature of
engagement makes it prone to influences of context
variables. Engagement might be expressed differently by people of
different cultures, in different group compositions (dyadic vs. more
than two people), and differently in professional vs. private
contexts. In MultiMediate ’24 we pose the challenge of creating
engagement estimation approaches that are able to transfer across such
context factors. For training, the challenge will make use of the
Novice-Expert Interaction (NoXi) database consisting of
screen-mediated dyadic conversations. For evaluation, we introduce
three novel out-of-domain datasets annotated with engagement scores:
(1) additional data in the NoXi setting from four additional
languages, (2) data from co-located group discussions, and (3) dyadic
speed dating interactions in a videoconferencing setting. For all
datasets, we release comprehensive pre-computed featuresets.

== Continuing Tasks ==

We continue to invite submission to the three most popular tasks from
MultiMediate'21-'23: Eye contact detection, backchannel
detection, and bodily behaviour recognition. All of these tasks make
use of the MPIIGroupInteraction dataset, which consists of group
discussions of 3-4 participants.

== Dataset & Evaluation Protocol ==

Training datasets for all tasks are available from our website. We
additionally provide baseline implementations along with pre-computed
features to minimise the overhead for participants. Test sets will be
released two weeks before the challenge deadline. Participants will in
turn submit their predictions for evaluation against ground truth on
our servers. For previous years' tasks, the test sets are already
published and three evaluations on the test set can be performed per
month.

== How to Participate ==

Instructions are available at https://multimediate-challenge.org/ 

Paper submission deadline: 12 July 2024

== Organisers ==

Philipp Müller (German Research Center for Artificial Intelligence)

Jan Alexandersson (German Research Center for Artificial Intelligence)

Tobias Baur (Augsburg University)

Dominik Schiller (Augsburg University)

Michael Dietz (Augsburg University)

Elisabeth André (Augsburg University)

Anna Penzkofer (University of Stuttgart)

Andreas Bulling (University of Stuttgart)

Michal Balazia (INRIA Sophia Antipolis)
François Brémond (INRIA Sophia Antipolis)