Matches in SemOpenAlex for { <https://semopenalex.org/work/W3005383687> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W3005383687 abstract "Lossless image compression is an important task in the field of multimedia communication. Traditional image codecs typically support lossless mode, such as WebP, JPEG2000, FLIF. Recently, deep learning based approaches have started to show the potential at this point. HyperPrior is an effective technique proposed for lossy image compression. This paper generalizes the hyperprior from lossy model to lossless compression, and proposes a L2-norm term into the loss function to speed up training procedure. Besides, this paper also investigated different parameterized models for latent codes, and propose to use Gaussian mixture likelihoods to achieve adaptive and flexible context models. Experimental results validate our method can outperform existing deep learning based lossless compression, and outperform the JPEG2000 and WebP for JPG images." @default.
- W3005383687 created "2020-02-14" @default.
- W3005383687 creator A5002294739 @default.
- W3005383687 creator A5045478397 @default.
- W3005383687 creator A5071945287 @default.
- W3005383687 creator A5089205282 @default.
- W3005383687 date "2020-02-05" @default.
- W3005383687 modified "2023-09-24" @default.
- W3005383687 title "Learned Lossless Image Compression with a HyperPrior and Discretized Gaussian Mixture Likelihoods" @default.
- W3005383687 cites W1522301498 @default.
- W3005383687 cites W2108598243 @default.
- W3005383687 cites W2119047110 @default.
- W3005383687 cites W2140196014 @default.
- W3005383687 cites W2166816543 @default.
- W3005383687 cites W2168203147 @default.
- W3005383687 cites W2276024283 @default.
- W3005383687 cites W2795709826 @default.
- W3005383687 cites W2798309714 @default.
- W3005383687 cites W2891212213 @default.
- W3005383687 cites W2891810238 @default.
- W3005383687 cites W2893920456 @default.
- W3005383687 cites W2948654165 @default.
- W3005383687 cites W2952830092 @default.
- W3005383687 cites W2963149687 @default.
- W3005383687 cites W2963449488 @default.
- W3005383687 cites W2963636093 @default.
- W3005383687 cites W2964122153 @default.
- W3005383687 cites W2965631471 @default.
- W3005383687 cites W2971989714 @default.
- W3005383687 cites W2114061905 @default.
- W3005383687 doi "https://doi.org/10.48550/arxiv.2002.01657" @default.
- W3005383687 hasPublicationYear "2020" @default.
- W3005383687 type Work @default.
- W3005383687 sameAs 3005383687 @default.
- W3005383687 citedByCount "0" @default.
- W3005383687 crossrefType "posted-content" @default.
- W3005383687 hasAuthorship W3005383687A5002294739 @default.
- W3005383687 hasAuthorship W3005383687A5045478397 @default.
- W3005383687 hasAuthorship W3005383687A5071945287 @default.
- W3005383687 hasAuthorship W3005383687A5089205282 @default.
- W3005383687 hasBestOaLocation W30053836871 @default.
- W3005383687 hasConcept C11413529 @default.
- W3005383687 hasConcept C115961682 @default.
- W3005383687 hasConcept C13481523 @default.
- W3005383687 hasConcept C154945302 @default.
- W3005383687 hasConcept C165021410 @default.
- W3005383687 hasConcept C31972630 @default.
- W3005383687 hasConcept C41008148 @default.
- W3005383687 hasConcept C78548338 @default.
- W3005383687 hasConcept C81081738 @default.
- W3005383687 hasConcept C9417928 @default.
- W3005383687 hasConcept C94835093 @default.
- W3005383687 hasConceptScore W3005383687C11413529 @default.
- W3005383687 hasConceptScore W3005383687C115961682 @default.
- W3005383687 hasConceptScore W3005383687C13481523 @default.
- W3005383687 hasConceptScore W3005383687C154945302 @default.
- W3005383687 hasConceptScore W3005383687C165021410 @default.
- W3005383687 hasConceptScore W3005383687C31972630 @default.
- W3005383687 hasConceptScore W3005383687C41008148 @default.
- W3005383687 hasConceptScore W3005383687C78548338 @default.
- W3005383687 hasConceptScore W3005383687C81081738 @default.
- W3005383687 hasConceptScore W3005383687C9417928 @default.
- W3005383687 hasConceptScore W3005383687C94835093 @default.
- W3005383687 hasLocation W30053836871 @default.
- W3005383687 hasOpenAccess W3005383687 @default.
- W3005383687 hasPrimaryLocation W30053836871 @default.
- W3005383687 hasRelatedWork W1278318 @default.
- W3005383687 hasRelatedWork W13035954 @default.
- W3005383687 hasRelatedWork W1489137 @default.
- W3005383687 hasRelatedWork W2494974 @default.
- W3005383687 hasRelatedWork W3836740 @default.
- W3005383687 hasRelatedWork W5523032 @default.
- W3005383687 hasRelatedWork W7232811 @default.
- W3005383687 hasRelatedWork W8020063 @default.
- W3005383687 hasRelatedWork W8143495 @default.
- W3005383687 hasRelatedWork W9581839 @default.
- W3005383687 isParatext "false" @default.
- W3005383687 isRetracted "false" @default.
- W3005383687 magId "3005383687" @default.
- W3005383687 workType "article" @default.