A Large, Crowdsourced Evaluation of Gesture Generation Systems on Common Data: The GENEA Challenge 2020

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 102
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorKucherenko, Tarasko
dc.contributor.authorJonell, Patrikko
dc.contributor.authorYoon, Youngwooko
dc.contributor.authorWolfert, Pieterko
dc.contributor.authorHenter, Gustav Ejeko
dc.date.accessioned2021-11-03T06:48:28Z-
dc.date.available2021-11-03T06:48:28Z-
dc.date.created2021-10-26-
dc.date.issued2021-04-
dc.identifier.citation26th International Conference on Intelligent User Interfaces: Where HCI Meets AI, IUI 2021, pp.11 - 21-
dc.identifier.urihttp://hdl.handle.net/10203/288667-
dc.description.abstractCo-speech gestures, gestures that accompany speech, play an important role in human communication. Automatic co-speech gesture generation is thus a key enabling technology for embodied conversational agents (ECAs), since humans expect ECAs to be capable of multi-modal communication. Research into gesture generation is rapidly gravitating towards data-driven methods. Unfortunately, individual research efforts in the field are difficult to compare: There are no established benchmarks, and each study tends to use its own dataset, motion visualisation, and evaluation methodology. 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. Since differences in evaluation outcomes between systems now are solely attributable to differences between the motion-generation methods, this enables benchmarking recent approaches against one another in order to get a better impression of the state of the art in the field. This paper reports on the purpose, design, results, and implications of our challenge.-
dc.languageEnglish-
dc.publisherAssociation for Computing Machinery-
dc.titleA Large, Crowdsourced Evaluation of Gesture Generation Systems on Common Data: The GENEA Challenge 2020-
dc.typeConference-
dc.identifier.scopusid2-s2.0-85102546745-
dc.type.rimsCONF-
dc.citation.beginningpage11-
dc.citation.endingpage21-
dc.citation.publicationname26th International Conference on Intelligent User Interfaces: Where HCI Meets AI, IUI 2021-
dc.identifier.conferencecountryUS-
dc.identifier.conferencelocationTexas-
dc.identifier.doi10.1145/3397481.3450692-
dc.contributor.localauthorYoon, Youngwoo-
dc.contributor.nonIdAuthorKucherenko, Taras-
dc.contributor.nonIdAuthorJonell, Patrik-
dc.contributor.nonIdAuthorWolfert, Pieter-
dc.contributor.nonIdAuthorHenter, Gustav Eje-
Appears in Collection
RIMS Conference Papers
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0