Full metadata record
DC pole | Hodnota | Jazyk |
---|---|---|
dc.contributor.author | Brahimi, Sourour | |
dc.contributor.author | Ben Aoun, Najib | |
dc.contributor.author | Ben Amar, Chokri | |
dc.contributor.author | Benoit, Alexandre | |
dc.contributor.author | Lambert, Patrick | |
dc.contributor.editor | Skala, Václav | |
dc.date.accessioned | 2019-05-07T07:40:37Z | - |
dc.date.available | 2019-05-07T07:40:37Z | - |
dc.date.issued | 2018 | |
dc.identifier.citation | Journal of WSCG. 2018, vol. 26, no. 2, p. 104-111. | en |
dc.identifier.issn | 1213-6972 (print) | |
dc.identifier.issn | 1213-6980 (CD-ROM) | |
dc.identifier.issn | 1213-6964 (on-line) | |
dc.identifier.uri | wscg.zcu.cz/WSCG2018/!_2018_Journal_WSCG-No-2.pdf | |
dc.identifier.uri | http://hdl.handle.net/11025/34596 | |
dc.format | 8 s. | cs |
dc.format.mimetype | application/pdf | |
dc.language.iso | en | en |
dc.publisher | Václav Skala - UNION Agency | cs |
dc.relation.ispartofseries | Journal of WSCG | en |
dc.rights | © Václav Skala - UNION Agency | cs |
dc.subject | sémantická segmentace | cs |
dc.subject | konvoluční neuronová síť | cs |
dc.subject | plně konvoluční DenseNet | cs |
dc.subject | hustý blok | cs |
dc.subject | víceměřítková jaderná predikce | cs |
dc.title | Multiscale fully convolutional denseNet for semantic segmentation | en |
dc.type | článek | cs |
dc.type | article | en |
dc.rights.access | openAccess | en |
dc.type.version | publishedVersion | en |
dc.description.abstract-translated | In the computer vision field, semantic segmentation represents a very interesting task. Convolutional Neural Network methods have shown their great performances in comparison with other semantic segmentation methods. In this paper, we propose a multiscale fully convolutional DenseNet approach for semantic segmentation. Our approach is based on the successful fully convolutional DenseNet method. It is reinforced by integrating a multiscale kernel prediction after the last dense block which performs model averaging over different spatial scales and provides more flexibility of our network to presume more information. Experiments on two semantic segmentation benchmarks: CamVid and Cityscapes have shown the effectiveness of our approach which has outperformed many recent works. | en |
dc.subject.translated | semantic segmentation | en |
dc.subject.translated | convolutional neural network | en |
dc.subject.translated | fully convolutional DenseNet | en |
dc.subject.translated | dense block | en |
dc.subject.translated | multiscale kernel prediction | en |
dc.identifier.doi | https://doi.org/10.24132/JWSCG.2018.26.2.5 | |
dc.type.status | Peer-reviewed | en |
Vyskytuje se v kolekcích: | Volume 26, Number 2 (2018) |
Soubory připojené k záznamu:
Soubor | Popis | Velikost | Formát | |
---|---|---|---|---|
aoun.pdf | Plný text | 3,26 MB | Adobe PDF | Zobrazit/otevřít |
Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam:
http://hdl.handle.net/11025/34596
Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.