Matches in SemOpenAlex for { <https://semopenalex.org/work/W3184587525> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W3184587525 endingPage "103226" @default.
- W3184587525 startingPage "103226" @default.
- W3184587525 abstract "While deep learning-based image compression methods have shown impressive coding performance, most existing methods are still in the mire of two limitations: (1) unpredictable compression efficiency gain when adopting convolutional neural networks with different depths, and (2) lack of an accurate model to estimate the entropy during the training process. To address these two problems, in this paper, a deep multi-stage representation based image compression (MSRIC) method is proposed. Owing to this architecture, the detail information of shallow stages and the compact information of deep stages can be utilized for image reconstruction. Furthermore, a data-dependent channel-wised factorized probability model (DCFPM) is adopted to increase the accuracy of entropy estimation. Experimental results indicate that the proposed method guarantees better perceptual performance at a wide range of bit-rates. Also, ablation studies are carried out to validate the above mentioned technologies." @default.
- W3184587525 created "2021-08-02" @default.
- W3184587525 creator A5010185627 @default.
- W3184587525 creator A5034579880 @default.
- W3184587525 creator A5046605531 @default.
- W3184587525 creator A5057732142 @default.
- W3184587525 date "2021-08-01" @default.
- W3184587525 modified "2023-10-16" @default.
- W3184587525 title "Deep image compression with multi-stage representation" @default.
- W3184587525 cites W1991719850 @default.
- W3184587525 cites W2099563019 @default.
- W3184587525 cites W2108598243 @default.
- W3184587525 cites W2140196014 @default.
- W3184587525 cites W2146395539 @default.
- W3184587525 cites W2597747080 @default.
- W3184587525 cites W2789010967 @default.
- W3184587525 cites W2798309714 @default.
- W3184587525 cites W2962847516 @default.
- W3184587525 cites W2962891349 @default.
- W3184587525 cites W2963149687 @default.
- W3184587525 cites W2963711615 @default.
- W3184587525 cites W2970340508 @default.
- W3184587525 cites W2981613960 @default.
- W3184587525 cites W3001966324 @default.
- W3184587525 cites W3034469748 @default.
- W3184587525 doi "https://doi.org/10.1016/j.jvcir.2021.103226" @default.
- W3184587525 hasPublicationYear "2021" @default.
- W3184587525 type Work @default.
- W3184587525 sameAs 3184587525 @default.
- W3184587525 citedByCount "3" @default.
- W3184587525 countsByYear W31845875252020 @default.
- W3184587525 countsByYear W31845875252022 @default.
- W3184587525 crossrefType "journal-article" @default.
- W3184587525 hasAuthorship W3184587525A5010185627 @default.
- W3184587525 hasAuthorship W3184587525A5034579880 @default.
- W3184587525 hasAuthorship W3184587525A5046605531 @default.
- W3184587525 hasAuthorship W3184587525A5057732142 @default.
- W3184587525 hasConcept C106301342 @default.
- W3184587525 hasConcept C108583219 @default.
- W3184587525 hasConcept C11413529 @default.
- W3184587525 hasConcept C115961682 @default.
- W3184587525 hasConcept C121332964 @default.
- W3184587525 hasConcept C13481523 @default.
- W3184587525 hasConcept C153180895 @default.
- W3184587525 hasConcept C154945302 @default.
- W3184587525 hasConcept C41008148 @default.
- W3184587525 hasConcept C62520636 @default.
- W3184587525 hasConcept C78548338 @default.
- W3184587525 hasConcept C81363708 @default.
- W3184587525 hasConcept C9417928 @default.
- W3184587525 hasConceptScore W3184587525C106301342 @default.
- W3184587525 hasConceptScore W3184587525C108583219 @default.
- W3184587525 hasConceptScore W3184587525C11413529 @default.
- W3184587525 hasConceptScore W3184587525C115961682 @default.
- W3184587525 hasConceptScore W3184587525C121332964 @default.
- W3184587525 hasConceptScore W3184587525C13481523 @default.
- W3184587525 hasConceptScore W3184587525C153180895 @default.
- W3184587525 hasConceptScore W3184587525C154945302 @default.
- W3184587525 hasConceptScore W3184587525C41008148 @default.
- W3184587525 hasConceptScore W3184587525C62520636 @default.
- W3184587525 hasConceptScore W3184587525C78548338 @default.
- W3184587525 hasConceptScore W3184587525C81363708 @default.
- W3184587525 hasConceptScore W3184587525C9417928 @default.
- W3184587525 hasFunder F4320321001 @default.
- W3184587525 hasFunder F4320336035 @default.
- W3184587525 hasLocation W31845875251 @default.
- W3184587525 hasOpenAccess W3184587525 @default.
- W3184587525 hasPrimaryLocation W31845875251 @default.
- W3184587525 hasRelatedWork W2731899572 @default.
- W3184587525 hasRelatedWork W2732542196 @default.
- W3184587525 hasRelatedWork W2738221750 @default.
- W3184587525 hasRelatedWork W2999805992 @default.
- W3184587525 hasRelatedWork W3116150086 @default.
- W3184587525 hasRelatedWork W3133861977 @default.
- W3184587525 hasRelatedWork W4200173597 @default.
- W3184587525 hasRelatedWork W4312417841 @default.
- W3184587525 hasRelatedWork W4321369474 @default.
- W3184587525 hasRelatedWork W564581980 @default.
- W3184587525 hasVolume "79" @default.
- W3184587525 isParatext "false" @default.
- W3184587525 isRetracted "false" @default.
- W3184587525 magId "3184587525" @default.
- W3184587525 workType "article" @default.