[iva] Call for participation: GENEA Challenge 2023 on speech-driven gesture generation

[woo]

/********************************************************************

Call for participation: GENEA Challenge 2023 on speech-driven gesture 
generation
Starting date: May 1

Location: Official Grand Challenge of ICMI 2023, Paris, France

Website: https://genea-workshop.github.io/2023/challenge/
*********************************************************************

Overview
*********************

The state of the art in co-speech gesture generation is difficult to 
assess, since every research group tends to use their own data, 
embodiment, and evaluation methodology. To better understand and compare 
methods for gesture generation and evaluation, we are continuing the 
GENEA (Generation and Evaluation of Non-verbal Behaviour for Embodied 
Agents) Challenge, wherein different gesture-generation approaches are 
evaluated side by side in a large user study. This 2023 challenge is a 
Grand Challenge for ICMI 2023 and is a follow-up to the first and second 
editions of the GENEA Challenge, arranged in 2020 and 2022.

This year the challenge will focus on gesture synthesis in a dyadic 
setting, i.e., gestures that depend not only on speech, but also on the 
behaviour of an interlocutor in a conversation. We invite researchers in 
academia and industry working on any form of corpus-based non-verbal 
behaviour generation and gesticulation to submit entries to the 
challenge, whether their method is driven by rule or machine learning. 
Participants are provided a large, common dataset of speech 
(audio+aligned text transcriptions) and 3D motion to develop their 
systems, and then use these systems to generate motion on given test 
inputs. The generated motion clips are rendered onto a common virtual 
agent and evaluated for aspects such as motion quality and 
appropriateness in a large-scale crowdsourced user study.

Data

*********************

The 2023 challenge is based on the _Talking With Hands 16.2M_ dataset 
(https://github.com/facebookresearch/TalkingWithHands32M [1]). The 
official challenge dataset also includes additional annotations, and is 
only available to registered participants.

Timeline

*********************

April 1  - Participant registration opens

May 1 - Challenge training dataset released to participants

June 7 - Test input released to participants

June 14 - Deadline for participants to submit generated motion

July 3 - Release of crowdsourced evaluation results to participants

July 14 - Paper submission deadline

August 4 - Author notification

August 11 - Camera-ready papers due

October 9 or 13 - Challenge presentations at ICMI

If you would like to receive a notification when challenge registration 
opens, please follow this link: https://forms.gle/MFEXv84xGL3NrY3d9/.

Challenge paper

*********************

Challenge participants are required to submit a paper that describes 
their system and findings, and will present their work at the Grand 
Challenge session at ICMI. All accepted papers will be part of the ACM 
ICMI 2023 main proceedings. Papers that are not accepted will have a 
chance to be considered for the GENEA Workshop 2023, whose papers are 
published in the ACM ICMI 2023 companion proceedings.

Links:
------
[1] https://github.com/facebookresearch/TalkingWithHands32M
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.uni-bielefeld.de/mailman2/unibi/public/iva-list/attachments/20230322/82949403/attachment.html>