keywords:"RUNet" - Výsledky hledání - Digitální repozitář

host :: přihlásit Digitální repozitář
		Hledej		Nový záznam		Nápověda		O repozitáři

Hlavní stránka > Výsledky hledání: keywords:"RUNet"

Hledej:

Tipy pro vyhledávaní :: Rozšířené hledání

Hledej ve sbírkách:

Seřadit podle:	Zobrazit výsledky:	Výstupní formát:

	Comic Images Super-Resolution Using Deep Learning Zdravecký, Peter ; Juránek, Roman (oponent) ; Španěl, Michal (vedoucí práce) This paper demonstrates a super-resolution method for improving the resolution and quality of comic images by using deep learning. The challenging part of the task was to keep the quality of the text parts and drawings simultaneously, without significant deformation of any part. Two deep neural networks were used to achieve satisfying results. U-Net network and its modification called Robust U-Net. The chosen loss functions to train these networks were the Mean Squared Error and Perceptual loss. The work contains experiments on U-Net and modified RUNet networks with a combination of each loss function. Additional experiments looked at how the number of used blocks from the VGG16 loss network affects the Perceptual loss function. Experiments have shown that a Robust U-Net network using a Perceptual loss with three extracted blocks got the best results. Úplný záznam
	Cute Cats on a Rescue Mission: An Obituary to YouTube in Russia? Polheim, Annemarie Elisabeth ; Kolenovská, Daniela (vedoucí práce) ; Svoboda, Karel (oponent) Bibliographic note POLHEIM, Annemarie. 2022. Cute Cats on a Resue Mission: An Obituary to YouTube in Russia? 67 p. Master thesis. Charles University, Faculty of Social Sciences, Institute of International Studies. Supervisor Mgr. Daniela Kolenovská, Ph.D. Abstract Russia's 2022 invasion of Ukraine has accelerated internet regulation and cutbacks on free expression in Russia. YouTube is one of the most established hybrid media platforms and an important source of information in the country. It is likely that the platform may be banned by Roskomnadzor at any time, as it blocks Russian state channels. The aim of this thesis is to outline the characteristics of the Russian YouTube landscape and to contribute to the understanding of current transformations of the Russian media system. Two datasets of YouTube channel networks, retrieved on January 6 and March 14, 2022, are analysed and compared. The data consists of YouTube channels of the Russian political spectrum and surrounding channels, as well as their links to each other (subscriptions, recommendations). A significant increase in the English-language clusters and the Russian-language educational cluster between January and March, and a decrease in the Russian-language entertainment and political clusters was observed. The findings, however, did not allow a... Úplný záznam
	Comic Images Super-Resolution Using Deep Learning Zdravecký, Peter ; Juránek, Roman (oponent) ; Španěl, Michal (vedoucí práce) This paper demonstrates a super-resolution method for improving the resolution and quality of comic images by using deep learning. The challenging part of the task was to keep the quality of the text parts and drawings simultaneously, without significant deformation of any part. Two deep neural networks were used to achieve satisfying results. U-Net network and its modification called Robust U-Net. The chosen loss functions to train these networks were the Mean Squared Error and Perceptual loss. The work contains experiments on U-Net and modified RUNet networks with a combination of each loss function. Additional experiments looked at how the number of used blocks from the VGG16 loss network affects the Perceptual loss function. Experiments have shown that a Robust U-Net network using a Perceptual loss with three extracted blocks got the best results. Úplný záznam

Chcete být upozorněni, pokud se objeví nové záznamy odpovídající tomuto dotazu?
Přihlásit se k odběru RSS.

Digitální repozitář :: :: :: ::
Powered by v1.1.2
Spravuje

Tato stránka je dostupná také v následujících jazycích:
Česky English