Filters








4 Hits in 4.9 sec

The GENEA Challenge 2020:Benchmarking gesture-generation systems on common data [article]

Taras Kucherenko, Patrik Jonell, Youngwoo Yoon, Pieter Wolfert, Gustav Eje Henter
2020 Zenodo  
Presented at the GENEA Workshop 2020, part of IVA'20.  ...  We are also grateful to Ulysses Bernardet for input and to Kevin El Haddad, Ulme Wennberg, Dmytro Kalpakchi, Bram The GENEA Challenge 2020: Benchmarking gesture-generation systems on common data Willemsen  ...  ACKNOWLEDGMENTS The GENEA Challenge 2020 used the Trinity Speech-Gesture Dataset collected by Ylva Ferstl and Rachel McDonnell.  ... 
doi:10.5281/zenodo.4094697 fatcat:iybcr46mdzbq7kipl7jwatglza

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
2021
To address this situation, we launched the GENEA Challenge, a gesture-generation challenge wherein participating teams built automatic gesture-generation systems on a common dataset, and the resulting  ...  systems were evaluated in parallel in a large, crowdsourced user study using the same motion-rendering pipeline.  ...  ACKNOWLEDGMENTS The GENEA Challenge 2020 used the Trinity Speech-Gesture Dataset collected by Ylva  ... 
doi:10.48550/arxiv.2102.11617 fatcat:lkmztlpfu5dctlkm2ynk6x2ga4

CGVU: Semantics-guided 3D Body Gesture Synthesis [article]

Kunkun Pang, Taku Komura, Hanbyul Joo, Takaaki Shiratori
2020 Zenodo  
Presented at the GENEA Workshop 2020, part of IVA'20.  ...  Besides, both our proposed system and other gesture generation approaches were evaluated in a large user study during GENEA 2020 challenge. RELATED WORKS Speech-to-Gesture.  ...  GENEA 2020 challenge conduct qualitative researches to evaluate different gesture-generation approaches and human gestures.  ... 
doi:10.5281/zenodo.4090879 fatcat:i4f7mb6janbx7nahbtr3xa7xaa

HEMVIP: Human Evaluation of Multiple Videos in Parallel [article]

Patrik Jonell, Youngwoo Yoon, Pieter Wolfert, Taras Kucherenko, Gustav Eje Henter
2021 arXiv   pre-print
Building on standards used for evaluating the quality of multimedia codecs, this paper instead introduces a framework for granular rating of multiple comparable videos in parallel.  ...  Common evaluation paradigms either present individual stimuli to be scored on Likert-type scales, or ask users to compare and rate videos in a pairwise fashion.  ...  ACKNOWLEDGMENTS The authors wish to thank Jonas Beskow, Dmytro Kalpakchi, and Bram Willemsen for their feedback on the paper. This  ... 
arXiv:2101.11898v1 fatcat:4ygg34glyjhzdbw2baycah4fee