Full metadata record
DC poleHodnotaJazyk
dc.contributor.authorSvoboda, Pavel
dc.contributor.authorHradiš, Michal
dc.contributor.authorBařina, David
dc.contributor.authorZemčík, Pavel
dc.contributor.editorSkala, Václav
dc.date.accessioned2016-07-25T13:06:20Z
dc.date.available2016-07-25T13:06:20Z
dc.date.issued2016
dc.identifier.citationJournal of WSCG. 2016, vol. 24, no. 2, p. 63-72.en
dc.identifier.issn1213-6972 (print)
dc.identifier.issn1213-6980 (CD-ROM)
dc.identifier.issn1213-6964 (on-line)
dc.identifier.urihttp://wscg.zcu.cz/WSCG2016/!_2016_Journal_WSCG-No-2.pdf
dc.identifier.urihttp://hdl.handle.net/11025/21649
dc.format10 s.cs
dc.format.mimetypeapplication/pdf
dc.language.isoenen
dc.publisherVáclav Skala - UNION Agencycs
dc.relation.ispartofseriesJournal of WSCGen
dc.rights© Václav Skala - UNION Agencycs
dc.subjecthluboké učenícs
dc.subjectkonvoluční neuronová síťcs
dc.subjectJPEGcs
dc.titleCompression artifacts removal using convolutional neural networksen
dc.typečlánekcs
dc.typearticleen
dc.rights.accessopenAccessen
dc.type.versionpublishedVersionen
dc.description.abstract-translatedThis paper shows that it is possible to train large and deep convolutional neural networks (CNN) for JPEG compression artifacts reduction, and that such networks can provide significantly better reconstruction quality compared to previously used smaller networks as well as to any other state-of-the-art methods. We were able to train networks with 8 layers in a single step and in relatively short time by combining residual learning, skip architecture, and symmetric weight initialization. We provide further insights into convolution networks for JPEG artifact reduction by evaluating three different objectives, generalization with respect to training dataset size, and generalization with respect to JPEG quality level.en
dc.subject.translateddeep learningen
dc.subject.translatedconvolutional neural networksen
dc.subject.translatedJPEGen
dc.type.statusPeer-revieweden
Vyskytuje se v kolekcích:Volume 24, Number 2 (2016)

Soubory připojené k záznamu:
Soubor Popis VelikostFormát 
Svoboda.pdfPlný text2,67 MBAdobe PDFZobrazit/otevřít
Zobrazit minimální záznam Zobrazit statistiky


Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam: http://hdl.handle.net/11025/21649

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.

hledání
navigace
  1. DSpace at University of West Bohemia
  2. Publikace ZČU / UWB Publications
  3. Časopisy ZČU / UWB Journals
  4. Journal of WSCG
  5. Volume 24 (2016)
  6. Volume 24, Number 2 (2016)