CEP – Conversational Engagement Prediction - a challenge
We have collected a large dataset in group video-mediated communication
context and now we run the following challenge as part of the upcoming
ACM ICMI conference challenges:
I would be happy to provide more information and I would also
appreciate if you could distribute this information to people who are
interested in conversational engagement and multimodal signal analysis.
D-META Grand Challenge
at the International Conference of Multimodal Interaction (ICMI)
Santa Monica, October 2012.
The D-META Grand Challenge (Datasets for Multimodal Evaluation of Tasks
and Annotations) proposes to set up the basis for comparison, analysis,
and further improvement of multimodal data annotations and multimodal
interactive systems. Held by two coupled pillars, method benchmarking
and annotation evaluation, the D-META challenge envisions a starting
point for transparent and publicly available application and annotation
evaluation on multimodal data sets. We expect papers covering areas such
as: (i) applications of an algorithm to a data set(s) to solve precise
tasks, (ii) benchmark of several algorithms using the same data set(s),
(iii) extensions of the annotation scheme with new relevant features,
(iv) applications of the data to an automatic system, (v) discussions on
ecologically valid data sets and (vi) position papers of how to organize
the next challenge. Papers may target one of the following tasks
AVRGR Recognize gestures addressed to the robot by means of the
vision and the audio.
AVSR Detect, localize and track multiple speakers using
CEP Estimate the level of engagement in a video-mediated communication.
AVCGR Recognize conversational gestures in first encounter dialogues.
AVFGR Recognize feedback gestures in first encounter dialogues.
Please check the web site for more information:
http://d-meta.inrialpes.fr and keep in mind the important dates:
31-Jul-2012 Paper deadline
24-Aug-2012 Author notification
Oct-2012 Work presented at D-META’12
Hope you all take the time to participate and/or disseminate this
The D-META Grand Challenge Team.