A large, crowdsourced evaluation of gesture generation systems on common data:
The GENEA Challenge 2020
Taras Kucherenko, Patrik Jonell, Youngwoo Yoon, Pieter Wolfert, Gustav Eje Henter
[first workshop paper] | [conference paper (IUI 2021)]
SUMMARY
Hand and body gestures play an important role in human communication, and automatically generating such gestures is therefore an important research area for conversational agents such as virtual avatars and social robots. To help the field of automated gesture generation move forward, we ran the first gesture-generation challenge – the GENEA Challenge 2020 – comparing many different gesture-generation methods on the same data in a large, crowdsourced evaluation. The intent is to help the community figure out what is important for good automatic gesture generation.
This page collects papers, videos, and other resources from our challenge. For more information about the design and results of the challenge, and what we learned from it, please see our main paper on the challenge, published at IUI 2021.
Main video explaining the paper:
Open-source materials:
User-study video stimuli DOI: 10.5281/zenodo.4080919
3D coordinates of submitted motion DOI: 10.5281/zenodo.4088319
Submitted BVH files DOI: 10.5281/zenodo.4785119
Code for visualising gesture motion GENEA visualizer
Code for computing the numerical evaluation metrics GENEA numerical evaluations
The StyleGestures entry to the GENEA Challenge 2020
The FineMotion entry to the GENEA Challenge 2020
Double-DCCCAE: Estimation of Body Gestures From Speech Waveform
CGVU: Semantics-guided 3D Body Gesture Synthesis
Speech Gesture Generation from Acoustic and Textual Information using LSTMs
Citation format:
@inproceedings{kucherenko2021large,
author = {Kucherenko, Taras and Jonell, Patrik and Yoon, Youngwoo and Wolfert, Pieter and Henter, Gustav Eje},
title = {A Large, Crowdsourced Evaluation of Gesture Generation Systems on Common Data: The {GENEA} {C}hallenge 2020},
year = {2021},
isbn = {9781450380171},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3397481.3450692},
doi = {10.1145/3397481.3450692},
booktitle = {26th International Conference on Intelligent User Interfaces},
pages = {11--21},
numpages = {11},
keywords = {evaluation paradigms, conversational agents, gesture generation},
location = {College Station, TX, USA},
series = {IUI '21}
}