Matches in SemOpenAlex for { <https://semopenalex.org/work/W2900996853> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W2900996853 endingPage "3700" @default.
- W2900996853 startingPage "3687" @default.
- W2900996853 abstract "While deep learning image compression methods have shown an impressive coding performance, most of them output a single-optimized-compression rate using a trained-specific network. However, in practice, it is essential to support the variable rate compression or meet a target rate with a high-coding performance. This paper proposes a novel image compression method, making it possible for a single convolutional neural network (CNN) model to generate the variable rate efficiently with an optimized rate-distortion (RD) performance. The method consists of CNN-based multi-scale decomposition transform and content adaptive rate allocation. Specifically, the transform network is learned to decompose the input image into several scales of representations while optimizing the RD performance for all scales. Rate allocation algorithms for two typical scenarios are provided to determine the optimal scale of each image block for a given target rate or quality factor. For a target rate, the allocation is adaptive based on content complexity. In addition, for a target quality factor which indicates a tradeoff between the rate and the quality, the optimal scale is determined by minimizing the RD cost. The experimental results have shown that our method has outperformed the JPEG2000 and BPG standards with high efficiency and the state-of-the-art RD performance as measured by the multi-scale structural similarity index metric. Moreover, our method can strictly control the rate to generate the target compression result." @default.
- W2900996853 created "2018-11-29" @default.
- W2900996853 creator A5002420179 @default.
- W2900996853 creator A5037989560 @default.
- W2900996853 creator A5077142689 @default.
- W2900996853 creator A5084923939 @default.
- W2900996853 date "2019-12-01" @default.
- W2900996853 modified "2023-10-15" @default.
- W2900996853 title "Efficient Variable Rate Image Compression With Multi-Scale Decomposition Network" @default.
- W2900996853 cites W1580389772 @default.
- W2900996853 cites W2001027782 @default.
- W2900996853 cites W2001112896 @default.
- W2900996853 cites W2086614154 @default.
- W2900996853 cites W2118217749 @default.
- W2900996853 cites W2119047110 @default.
- W2900996853 cites W2132984323 @default.
- W2900996853 cites W2140196014 @default.
- W2900996853 cites W2146395539 @default.
- W2900996853 cites W2148593155 @default.
- W2900996853 cites W2166816543 @default.
- W2900996853 cites W2194775991 @default.
- W2900996853 cites W2490784316 @default.
- W2900996853 cites W2597747080 @default.
- W2900996853 cites W2740336064 @default.
- W2900996853 cites W2963149687 @default.
- W2900996853 cites W4254197176 @default.
- W2900996853 doi "https://doi.org/10.1109/tcsvt.2018.2880492" @default.
- W2900996853 hasPublicationYear "2019" @default.
- W2900996853 type Work @default.
- W2900996853 sameAs 2900996853 @default.
- W2900996853 citedByCount "46" @default.
- W2900996853 countsByYear W29009968532019 @default.
- W2900996853 countsByYear W29009968532020 @default.
- W2900996853 countsByYear W29009968532021 @default.
- W2900996853 countsByYear W29009968532022 @default.
- W2900996853 countsByYear W29009968532023 @default.
- W2900996853 crossrefType "journal-article" @default.
- W2900996853 hasAuthorship W2900996853A5002420179 @default.
- W2900996853 hasAuthorship W2900996853A5037989560 @default.
- W2900996853 hasAuthorship W2900996853A5077142689 @default.
- W2900996853 hasAuthorship W2900996853A5084923939 @default.
- W2900996853 hasConcept C115961682 @default.
- W2900996853 hasConcept C124681953 @default.
- W2900996853 hasConcept C134306372 @default.
- W2900996853 hasConcept C13481523 @default.
- W2900996853 hasConcept C154945302 @default.
- W2900996853 hasConcept C159985019 @default.
- W2900996853 hasConcept C180016635 @default.
- W2900996853 hasConcept C182365436 @default.
- W2900996853 hasConcept C18903297 @default.
- W2900996853 hasConcept C192562407 @default.
- W2900996853 hasConcept C31972630 @default.
- W2900996853 hasConcept C33923547 @default.
- W2900996853 hasConcept C41008148 @default.
- W2900996853 hasConcept C54243161 @default.
- W2900996853 hasConcept C78548338 @default.
- W2900996853 hasConcept C86803240 @default.
- W2900996853 hasConcept C9417928 @default.
- W2900996853 hasConceptScore W2900996853C115961682 @default.
- W2900996853 hasConceptScore W2900996853C124681953 @default.
- W2900996853 hasConceptScore W2900996853C134306372 @default.
- W2900996853 hasConceptScore W2900996853C13481523 @default.
- W2900996853 hasConceptScore W2900996853C154945302 @default.
- W2900996853 hasConceptScore W2900996853C159985019 @default.
- W2900996853 hasConceptScore W2900996853C180016635 @default.
- W2900996853 hasConceptScore W2900996853C182365436 @default.
- W2900996853 hasConceptScore W2900996853C18903297 @default.
- W2900996853 hasConceptScore W2900996853C192562407 @default.
- W2900996853 hasConceptScore W2900996853C31972630 @default.
- W2900996853 hasConceptScore W2900996853C33923547 @default.
- W2900996853 hasConceptScore W2900996853C41008148 @default.
- W2900996853 hasConceptScore W2900996853C54243161 @default.
- W2900996853 hasConceptScore W2900996853C78548338 @default.
- W2900996853 hasConceptScore W2900996853C86803240 @default.
- W2900996853 hasConceptScore W2900996853C9417928 @default.
- W2900996853 hasFunder F4320309612 @default.
- W2900996853 hasFunder F4320321001 @default.
- W2900996853 hasFunder F4320327718 @default.
- W2900996853 hasIssue "12" @default.
- W2900996853 hasLocation W29009968531 @default.
- W2900996853 hasOpenAccess W2900996853 @default.
- W2900996853 hasPrimaryLocation W29009968531 @default.
- W2900996853 hasRelatedWork W142455045 @default.
- W2900996853 hasRelatedWork W1520703599 @default.
- W2900996853 hasRelatedWork W2066404474 @default.
- W2900996853 hasRelatedWork W2183077383 @default.
- W2900996853 hasRelatedWork W2365059698 @default.
- W2900996853 hasRelatedWork W2372078508 @default.
- W2900996853 hasRelatedWork W2381528364 @default.
- W2900996853 hasRelatedWork W2534615458 @default.
- W2900996853 hasRelatedWork W3165542721 @default.
- W2900996853 hasRelatedWork W4243608781 @default.
- W2900996853 hasVolume "29" @default.
- W2900996853 isParatext "false" @default.
- W2900996853 isRetracted "false" @default.
- W2900996853 magId "2900996853" @default.
- W2900996853 workType "article" @default.