FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2913664580> ?p ?o ?g. }

• W2913664580 endingPage "3356" @default.
• W2913664580 startingPage "3343" @default.
• W2913664580 abstract "Recently, convolutional neural network (CNN) has attracted tremendous attention and has achieved great success in many image processing tasks. In this paper, we focus on CNN technology combined with image restoration to facilitate video coding performance and propose the content-aware CNN based in-loop filtering for high-efficiency video coding (HEVC). In particular, we quantitatively analyze the structure of the proposed CNN model from multiple dimensions to make the model interpretable and optimal for CNN-based loop filtering. More specifically, each coding tree unit (CTU) is treated as an independent region for processing, such that the proposed content-aware multimodel filtering mechanism is realized by the restoration of different regions with different CNN models under the guidance of the discriminative network. To adapt the image content, the discriminative neural network is learned to analyze the content characteristics of each region for the adaptive selection of the deep learning model. The CTU level control is also enabled in the sense of rate-distortion optimization. To learn the CNN model, an iterative training method is proposed by simultaneously labeling filter categories at the CTU level and fine-tuning the CNN model parameters. The CNN based in-loop filter is implemented after sample adaptive offset in HEVC, and extensive experiments show that the proposed approach significantly improves the coding performance and achieves up to 10.0% bit-rate reduction. On average, 4.1%, 6.0%, 4.7%, and 6.0% bit-rate reduction can be obtained under all intra, low delay, low delay P, and random access configurations, respectively." @default.
• W2913664580 created "2019-02-21" @default.
• W2913664580 creator A5003527952 @default.
• W2913664580 creator A5039832462 @default.
• W2913664580 creator A5040292663 @default.
• W2913664580 creator A5042401810 @default.
• W2913664580 creator A5055937409 @default.
• W2913664580 creator A5076651778 @default.
• W2913664580 creator A5085955762 @default.
• W2913664580 date "2019-07-01" @default.
• W2913664580 modified "2023-10-15" @default.
• W2913664580 title "Content-Aware Convolutional Neural Network for In-Loop Filtering in High Efficiency Video Coding" @default.
• W2913664580 cites W1984077106 @default.
• W2913664580 cites W2017620942 @default.
• W2913664580 cites W2017801928 @default.
• W2913664580 cites W2043854246 @default.
• W2913664580 cites W2045737896 @default.
• W2913664580 cites W2056061164 @default.
• W2913664580 cites W2063854625 @default.
• W2913664580 cites W2064674198 @default.
• W2913664580 cites W2096933452 @default.
• W2913664580 cites W2097117768 @default.
• W2913664580 cites W2107503352 @default.
• W2913664580 cites W2108569186 @default.
• W2913664580 cites W2110158442 @default.
• W2913664580 cites W2122086266 @default.
• W2913664580 cites W2123113293 @default.
• W2913664580 cites W2124187578 @default.
• W2913664580 cites W2136604529 @default.
• W2913664580 cites W2140196014 @default.
• W2913664580 cites W2140199336 @default.
• W2913664580 cites W2142683286 @default.
• W2913664580 cites W2146395539 @default.
• W2913664580 cites W2152029399 @default.
• W2913664580 cites W2155893237 @default.
• W2913664580 cites W2194775991 @default.
• W2913664580 cites W2205371690 @default.
• W2913664580 cites W2242218935 @default.
• W2913664580 cites W2382163890 @default.
• W2913664580 cites W2474073286 @default.
• W2913664580 cites W2477177239 @default.
• W2913664580 cites W2508457857 @default.
• W2913664580 cites W2510648513 @default.
• W2913664580 cites W2518546937 @default.
• W2913664580 cites W2605341393 @default.
• W2913664580 cites W2610472635 @default.
• W2913664580 cites W2614073204 @default.
• W2913664580 cites W2741012957 @default.
• W2913664580 cites W2751646824 @default.
• W2913664580 cites W2752154940 @default.
• W2913664580 cites W2793408333 @default.
• W2913664580 cites W2896754546 @default.
• W2913664580 cites W2901921200 @default.
• W2913664580 cites W2904617026 @default.
• W2913664580 cites W2919115771 @default.
• W2913664580 cites W3104540617 @default.
• W2913664580 cites W4231887697 @default.
• W2913664580 doi "https://doi.org/10.1109/tip.2019.2896489" @default.
• W2913664580 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30714920" @default.
• W2913664580 hasPublicationYear "2019" @default.
• W2913664580 type Work @default.
• W2913664580 sameAs 2913664580 @default.
• W2913664580 citedByCount "138" @default.
• W2913664580 countsByYear W29136645802019 @default.
• W2913664580 countsByYear W29136645802020 @default.
• W2913664580 countsByYear W29136645802021 @default.
• W2913664580 countsByYear W29136645802022 @default.
• W2913664580 countsByYear W29136645802023 @default.
• W2913664580 crossrefType "journal-article" @default.
• W2913664580 hasAuthorship W2913664580A5003527952 @default.
• W2913664580 hasAuthorship W2913664580A5039832462 @default.
• W2913664580 hasAuthorship W2913664580A5040292663 @default.
• W2913664580 hasAuthorship W2913664580A5042401810 @default.
• W2913664580 hasAuthorship W2913664580A5055937409 @default.
• W2913664580 hasAuthorship W2913664580A5076651778 @default.
• W2913664580 hasAuthorship W2913664580A5085955762 @default.
• W2913664580 hasConcept C105795698 @default.
• W2913664580 hasConcept C11413529 @default.
• W2913664580 hasConcept C153180895 @default.
• W2913664580 hasConcept C154945302 @default.
• W2913664580 hasConcept C175291020 @default.
• W2913664580 hasConcept C179518139 @default.
• W2913664580 hasConcept C190750250 @default.
• W2913664580 hasConcept C199360897 @default.
• W2913664580 hasConcept C31972630 @default.
• W2913664580 hasConcept C33923547 @default.
• W2913664580 hasConcept C41008148 @default.
• W2913664580 hasConcept C57273362 @default.
• W2913664580 hasConcept C81363708 @default.
• W2913664580 hasConcept C97931131 @default.
• W2913664580 hasConceptScore W2913664580C105795698 @default.
• W2913664580 hasConceptScore W2913664580C11413529 @default.
• W2913664580 hasConceptScore W2913664580C153180895 @default.
• W2913664580 hasConceptScore W2913664580C154945302 @default.
• W2913664580 hasConceptScore W2913664580C175291020 @default.
• W2913664580 hasConceptScore W2913664580C179518139 @default.
• W2913664580 hasConceptScore W2913664580C190750250 @default.
• W2913664580 hasConceptScore W2913664580C199360897 @default.

• next