Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896732071> ?p ?o ?g. }
- W2896732071 endingPage "63106" @default.
- W2896732071 startingPage "63094" @default.
- W2896732071 abstract "It has been shown that deep convolutional neural networks (CNNs) reduce JPEG compression artifacts better than the previous approaches. However, the latest video compression standards have more complex artifacts than the JPEG, including the flickering which is not well reduced by the CNN-based methods developed for still images. Moreover, recent video compression algorithms include in-loop filters which reduce the blocking artifacts, and thus post-processing barely improves the performance. In this paper, we propose a temporal-CNN architecture to reduce the artifacts in video compression standards as well as in JPEG. Specifically, we exploit a simple CNN structure and introduce a new training strategy that captures the temporal correlation of the consecutive frames in videos. The similar patches are aggregated from the neighboring frames by a simple motion search method, and they are fed to the CNN, which further reduces the artifacts. Experiments show that our approach shows improvements over the conventional CNN-based methods with similar complexities for image and video compression standards, such as MPEG-2, AVC, and HEVC, with average PSNR gain of 1.27, 0.47, and 0.23 dB, respectively." @default.
- W2896732071 created "2018-10-26" @default.
- W2896732071 creator A5020815483 @default.
- W2896732071 creator A5026534904 @default.
- W2896732071 creator A5044629097 @default.
- W2896732071 creator A5052386336 @default.
- W2896732071 creator A5055171648 @default.
- W2896732071 creator A5056899449 @default.
- W2896732071 creator A5083360792 @default.
- W2896732071 date "2018-01-01" @default.
- W2896732071 modified "2023-09-25" @default.
- W2896732071 title "Reduction of Video Compression Artifacts Based on Deep Temporal Networks" @default.
- W2896732071 cites W1903029394 @default.
- W2896732071 cites W2017801928 @default.
- W2896732071 cites W2091902424 @default.
- W2896732071 cites W2097117768 @default.
- W2896732071 cites W2102605133 @default.
- W2896732071 cites W2123113293 @default.
- W2896732071 cites W2129833832 @default.
- W2896732071 cites W2133665775 @default.
- W2896732071 cites W2135065661 @default.
- W2896732071 cites W2140196014 @default.
- W2896732071 cites W2140199336 @default.
- W2896732071 cites W2142683286 @default.
- W2896732071 cites W2155893237 @default.
- W2896732071 cites W2163674598 @default.
- W2896732071 cites W2194775991 @default.
- W2896732071 cites W2242218935 @default.
- W2896732071 cites W2320725294 @default.
- W2896732071 cites W2476548250 @default.
- W2896732071 cites W2477177239 @default.
- W2896732071 cites W2508457857 @default.
- W2896732071 cites W2509123681 @default.
- W2896732071 cites W2510648513 @default.
- W2896732071 cites W2519021537 @default.
- W2896732071 cites W2527006979 @default.
- W2896732071 cites W2556024076 @default.
- W2896732071 cites W2749658623 @default.
- W2896732071 cites W2752154940 @default.
- W2896732071 cites W2755240195 @default.
- W2896732071 cites W2766341514 @default.
- W2896732071 cites W3104540617 @default.
- W2896732071 cites W3105540235 @default.
- W2896732071 doi "https://doi.org/10.1109/access.2018.2876864" @default.
- W2896732071 hasPublicationYear "2018" @default.
- W2896732071 type Work @default.
- W2896732071 sameAs 2896732071 @default.
- W2896732071 citedByCount "23" @default.
- W2896732071 countsByYear W28967320712019 @default.
- W2896732071 countsByYear W28967320712020 @default.
- W2896732071 countsByYear W28967320712021 @default.
- W2896732071 countsByYear W28967320712022 @default.
- W2896732071 countsByYear W28967320712023 @default.
- W2896732071 crossrefType "journal-article" @default.
- W2896732071 hasAuthorship W2896732071A5020815483 @default.
- W2896732071 hasAuthorship W2896732071A5026534904 @default.
- W2896732071 hasAuthorship W2896732071A5044629097 @default.
- W2896732071 hasAuthorship W2896732071A5052386336 @default.
- W2896732071 hasAuthorship W2896732071A5055171648 @default.
- W2896732071 hasAuthorship W2896732071A5056899449 @default.
- W2896732071 hasAuthorship W2896732071A5083360792 @default.
- W2896732071 hasBestOaLocation W28967320711 @default.
- W2896732071 hasConcept C106030495 @default.
- W2896732071 hasConcept C115961682 @default.
- W2896732071 hasConcept C127413603 @default.
- W2896732071 hasConcept C128840427 @default.
- W2896732071 hasConcept C13481523 @default.
- W2896732071 hasConcept C153180895 @default.
- W2896732071 hasConcept C154945302 @default.
- W2896732071 hasConcept C171146098 @default.
- W2896732071 hasConcept C198751489 @default.
- W2896732071 hasConcept C202474056 @default.
- W2896732071 hasConcept C23431618 @default.
- W2896732071 hasConcept C25797200 @default.
- W2896732071 hasConcept C28855332 @default.
- W2896732071 hasConcept C31972630 @default.
- W2896732071 hasConcept C41008148 @default.
- W2896732071 hasConcept C511840579 @default.
- W2896732071 hasConcept C57654395 @default.
- W2896732071 hasConcept C65483669 @default.
- W2896732071 hasConcept C78548338 @default.
- W2896732071 hasConcept C81363708 @default.
- W2896732071 hasConcept C9417928 @default.
- W2896732071 hasConceptScore W2896732071C106030495 @default.
- W2896732071 hasConceptScore W2896732071C115961682 @default.
- W2896732071 hasConceptScore W2896732071C127413603 @default.
- W2896732071 hasConceptScore W2896732071C128840427 @default.
- W2896732071 hasConceptScore W2896732071C13481523 @default.
- W2896732071 hasConceptScore W2896732071C153180895 @default.
- W2896732071 hasConceptScore W2896732071C154945302 @default.
- W2896732071 hasConceptScore W2896732071C171146098 @default.
- W2896732071 hasConceptScore W2896732071C198751489 @default.
- W2896732071 hasConceptScore W2896732071C202474056 @default.
- W2896732071 hasConceptScore W2896732071C23431618 @default.
- W2896732071 hasConceptScore W2896732071C25797200 @default.
- W2896732071 hasConceptScore W2896732071C28855332 @default.
- W2896732071 hasConceptScore W2896732071C31972630 @default.
- W2896732071 hasConceptScore W2896732071C41008148 @default.