FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2784572574> ?p ?o ?g. }

• W2784572574 abstract "Multiple description coding (MDC) is able to stably transmit the signal in the un-reliable and non-prioritized networks, which has been broadly studied for several decades. However, the traditional MDC doesn't well leverage image's context features to generate multiple descriptions. In this paper, we propose a novel standard-compliant convolutional neural network-based MDC framework in term of image's context features. Firstly, multiple description generator network (MDGN) is designed to produce appearance-similar yet feature-different multiple descriptions automatically according to image's content, which are compressed by standard codec. Secondly, we present multiple description reconstruction network (MDRN) including side reconstruction network (SRN) and central reconstruction network (CRN). When any one of two lossy descriptions is received at the decoder, SRN network is used to improve the quality of this decoded lossy description by removing the compression artifact and up-sampling simultaneously. Meanwhile, we utilize CRN network with two decoded descriptions as inputs for better reconstruction, if both of lossy descriptions are available. Thirdly, multiple description virtual codec network (MDVCN) is proposed to bridge the gap between MDGN network and MDRN network in order to train an end-to-end MDC framework. Here, two learning algorithms are provided to train our whole framework. In addition to structural similarity loss function, the produced descriptions are used as opposing labels with multiple description distance loss function to regularize the training of MDGN network. These losses guarantee that the generated description images are structurally similar yet finely diverse. Experimental results show a great deal of objective and subjective quality measurements to validate the efficiency of the proposed method." @default.
• W2784572574 created "2018-02-02" @default.
• W2784572574 creator A5003248833 @default.
• W2784572574 creator A5028127027 @default.
• W2784572574 creator A5030238978 @default.
• W2784572574 creator A5056401979 @default.
• W2784572574 date "2018-01-19" @default.
• W2784572574 modified "2023-10-16" @default.
• W2784572574 title "Multiple Description Convolutional Neural Networks for Image Compression" @default.
• W2784572574 cites W1522301498 @default.
• W2784572574 cites W1906770428 @default.
• W2784572574 cites W1978280057 @default.
• W2784572574 cites W2008399481 @default.
• W2784572574 cites W2056370875 @default.
• W2784572574 cites W2058289477 @default.
• W2784572574 cites W2064617372 @default.
• W2784572574 cites W2080949617 @default.
• W2784572574 cites W2096102601 @default.
• W2784572574 cites W2100224231 @default.
• W2784572574 cites W2106348390 @default.
• W2784572574 cites W2112977652 @default.
• W2784572574 cites W2116875419 @default.
• W2784572574 cites W2119936328 @default.
• W2784572574 cites W2122980421 @default.
• W2784572574 cites W2123095296 @default.
• W2784572574 cites W2126979605 @default.
• W2784572574 cites W2133665775 @default.
• W2784572574 cites W2135065661 @default.
• W2784572574 cites W2136098605 @default.
• W2784572574 cites W2141801739 @default.
• W2784572574 cites W2142683286 @default.
• W2784572574 cites W2144660376 @default.
• W2784572574 cites W2148037789 @default.
• W2784572574 cites W2151520469 @default.
• W2784572574 cites W2154239264 @default.
• W2784572574 cites W2159527094 @default.
• W2784572574 cites W2170868882 @default.
• W2784572574 cites W2171650331 @default.
• W2784572574 cites W2194757816 @default.
• W2784572574 cites W2271840356 @default.
• W2784572574 cites W2508457857 @default.
• W2784572574 cites W2766294690 @default.
• W2784572574 cites W2781154479 @default.
• W2784572574 cites W2962687329 @default.
• W2784572574 cites W2963125871 @default.
• W2784572574 cites W2963679601 @default.
• W2784572574 doi "https://doi.org/10.48550/arxiv.1801.06611" @default.
• W2784572574 hasPublicationYear "2018" @default.
• W2784572574 type Work @default.
• W2784572574 sameAs 2784572574 @default.
• W2784572574 citedByCount "0" @default.
• W2784572574 crossrefType "posted-content" @default.
• W2784572574 hasAuthorship W2784572574A5003248833 @default.
• W2784572574 hasAuthorship W2784572574A5028127027 @default.
• W2784572574 hasAuthorship W2784572574A5030238978 @default.
• W2784572574 hasAuthorship W2784572574A5056401979 @default.
• W2784572574 hasBestOaLocation W27845725741 @default.
• W2784572574 hasConcept C11413529 @default.
• W2784572574 hasConcept C115961682 @default.
• W2784572574 hasConcept C13481523 @default.
• W2784572574 hasConcept C135554599 @default.
• W2784572574 hasConcept C151730666 @default.
• W2784572574 hasConcept C153083717 @default.
• W2784572574 hasConcept C153180895 @default.
• W2784572574 hasConcept C154945302 @default.
• W2784572574 hasConcept C161765866 @default.
• W2784572574 hasConcept C165021410 @default.
• W2784572574 hasConcept C193415008 @default.
• W2784572574 hasConcept C2779343474 @default.
• W2784572574 hasConcept C31258907 @default.
• W2784572574 hasConcept C41008148 @default.
• W2784572574 hasConcept C57273362 @default.
• W2784572574 hasConcept C81363708 @default.
• W2784572574 hasConcept C86803240 @default.
• W2784572574 hasConcept C9390403 @default.
• W2784572574 hasConcept C9417928 @default.
• W2784572574 hasConceptScore W2784572574C11413529 @default.
• W2784572574 hasConceptScore W2784572574C115961682 @default.
• W2784572574 hasConceptScore W2784572574C13481523 @default.
• W2784572574 hasConceptScore W2784572574C135554599 @default.
• W2784572574 hasConceptScore W2784572574C151730666 @default.
• W2784572574 hasConceptScore W2784572574C153083717 @default.
• W2784572574 hasConceptScore W2784572574C153180895 @default.
• W2784572574 hasConceptScore W2784572574C154945302 @default.
• W2784572574 hasConceptScore W2784572574C161765866 @default.
• W2784572574 hasConceptScore W2784572574C165021410 @default.
• W2784572574 hasConceptScore W2784572574C193415008 @default.
• W2784572574 hasConceptScore W2784572574C2779343474 @default.
• W2784572574 hasConceptScore W2784572574C31258907 @default.
• W2784572574 hasConceptScore W2784572574C41008148 @default.
• W2784572574 hasConceptScore W2784572574C57273362 @default.
• W2784572574 hasConceptScore W2784572574C81363708 @default.
• W2784572574 hasConceptScore W2784572574C86803240 @default.
• W2784572574 hasConceptScore W2784572574C9390403 @default.
• W2784572574 hasConceptScore W2784572574C9417928 @default.
• W2784572574 hasLocation W27845725741 @default.
• W2784572574 hasOpenAccess W2784572574 @default.
• W2784572574 hasPrimaryLocation W27845725741 @default.
• W2784572574 hasRelatedWork W2175746458 @default.
• W2784572574 hasRelatedWork W2732542196 @default.

• next