GENEA Challenge
Title
The GENEA Challenge 2022: Full-body speech-driven gesture generation
Website
https://genea-workshop.github.io/2022/challenge/
Abstract
The GENEA (Generation and Evaluation of Non-verbal Behaviour for Embodied Agents) Grand Challenge 2022 aims at bringing together researchers that use different methods for non-verbal-behaviour generation and evaluation, and hopes to stimulate the discussions on how to improve both the generation methods and the evaluation of the results.
The challenge topic is speech-driven gesture generation. Participants are provided a large, common dataset of speech (audio+aligned text) 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 crowdsourced user study. More details will be available when the dataset is released. You can refer to the previous challenge here (be aware that the challenge dataset is different from the previous one).
Tentative timeline
April 8 – Participant registration opens
May 16 – Challenge training dataset released to participants
June 20 – Test input released to participants
June 27 – Deadline for participants to submit generated motion, start of evaluation
July 11 – Release of crowdsourced evaluation results to participants
July 20 – Paper submission deadline (TBD)
August 10 – Paper notification
August 17 August 23 – Camera-ready papers due
November 7 or 11 – Challenge presentations at ICMI
Contact
genea-contact@googlegroups.com
icmi2022-challenge-chairs@acm.org
Organizers
Pieter Wolfert MSc., IDLab Ghent University – imec, Ghent Belgium
Dr. Taras Kucherenko, SEED – Electronic Arts, Stockholm Sweden
Dr. Youngwoo Yoon, ETRI, South Korea
Dr. Zerrin Yumak, Utrecht University, Utrecht, The Netherlands
Dr. Gustav Eje Henter, KTH Royal Institute of Technology, Stockholm, Sweden
Carla Viegas, CMU, USA