Publication:
Classification and Generation of Virtual Dancer Social Behaviors Based on Deep Learning in a Simple Virtual Environment Paradigm

Простая страница элемента
dc.contributor.authorKuzmin, A. I.
dc.contributor.authorSemyonov, D. A.
dc.contributor.authorSamsonovich, A. V.
dc.contributor.authorСамсонович, Алексей Владимир
dc.date.accessioned2024-12-26T10:39:59Z
dc.date.available2024-12-26T10:39:59Z
dc.date.issued2022
dc.description.abstract© 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.This work examines one possibility of using a deep neural network to control a virtual dance partner behavior. A neural-network-based system is designed and used for classification, evaluation, prediction, and generation of socially emotional behavior of a virtual actor. The network is trained using deep learning on the data generated with an algorithm implementing the eBICA cognitive architecture. Results show that, in the selected virtual dance paradigm, (1) the functionality of the cognitive model can be efficiently transferred to the neural network using deep learning, allowing the network to generate socially emotional behavior of a dance partner similar to a human participant behavior or the behavior generated algorithmically based on eBICA, and (2) the trained neural network can correctly identify the character types of virtual dance partners based on their behavior. When considered together with related studies, our findings lead to more general implications extending beyond the selected paradigm.
dc.format.extentС. 231-242
dc.identifier.citationKuzmin, A. I. Classification and Generation of Virtual Dancer Social Behaviors Based on Deep Learning in a Simple Virtual Environment Paradigm / Kuzmin, A.I., Semyonov, D.A., Samsonovich, A.V. // Studies in Computational Intelligence. - 2022. - 1032 SCI. - P. 231-242. - 10.1007/978-3-030-96993-6_23
dc.identifier.doi10.1007/978-3-030-96993-6_23
dc.identifier.urihttps://www.doi.org/10.1007/978-3-030-96993-6_23
dc.identifier.urihttps://www.scopus.com/record/display.uri?eid=2-s2.0-85127671804&origin=resultslist
dc.identifier.urihttp://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS_CPL&DestLinkType=FullRecord&UT=WOS:000833484200023
dc.identifier.urihttps://openrepository.mephi.ru/handle/123456789/28946
dc.relation.ispartofStudies in Computational Intelligence
dc.titleClassification and Generation of Virtual Dancer Social Behaviors Based on Deep Learning in a Simple Virtual Environment Paradigm
dc.typeConference Paper
dspace.entity.typePublication
oaire.citation.volume1032 SCI
relation.isAuthorOfPublication424d77f0-6c5e-4d4b-b473-a29e8ac49488
relation.isAuthorOfPublication.latestForDiscovery424d77f0-6c5e-4d4b-b473-a29e8ac49488
relation.isOrgUnitOfPublication010157d0-1f75-46b2-ab5b-712e3424b4f5
relation.isOrgUnitOfPublication.latestForDiscovery010157d0-1f75-46b2-ab5b-712e3424b4f5
Файлы
Коллекции
Публикации