Publication: Research of Neural Networks Efficiency in Video Generation Problem
Дата
2021
Авторы
Ryabets, G. A.
Aralov, A. A.
Uskov, D. A.
Khabarov, D. L.
Усков, Даниил Алексеевич
Journal Title
Journal ISSN
Volume Title
Издатель
Аннотация
© 2021 IEEE.This paper describes the research of video generation using neural networks. The main ideas of several existing approaches based on the generative adversarial networks are presented and their characteristics are compared. During this research, vid2vid approach was selected and its effectiveness was examined. The process of collecting the corresponding dataset is described. Influence of various factors, such as training and segmentation parameters, on the model's effectiveness was studied during the experiments and obtained results were analyzed. The conclusions are presented and the directions of further research are formulated.
Описание
Ключевые слова
Цитирование
Research of Neural Networks Efficiency in Video Generation Problem / Ryabets, G.A. [et al.] // Proceedings of the 2021 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering, ElConRus 2021. - 2021. - P. 627-632. - 10.1109/ElConRus51938.2021.9396226
URI
https://www.doi.org/10.1109/ElConRus51938.2021.9396226
https://www.scopus.com/record/display.uri?eid=2-s2.0-85104703170&origin=resultslist
http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS_CPL&DestLinkType=FullRecord&UT=WOS:000669709800139
https://openrepository.mephi.ru/handle/123456789/24032
https://www.scopus.com/record/display.uri?eid=2-s2.0-85104703170&origin=resultslist
http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS_CPL&DestLinkType=FullRecord&UT=WOS:000669709800139
https://openrepository.mephi.ru/handle/123456789/24032