Matches in SemOpenAlex for { <https://semopenalex.org/work/W4297659253> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4297659253 abstract "A large fraction of Internet traffic is now driven by requests from mobile devices with relatively small screens and often stringent bandwidth requirements. Due to these factors, it has become the norm for modern graphics-heavy websites to transmit low-resolution, low-bytecount image previews (thumbnails) as part of the initial page load process to improve apparent page responsiveness. Increasing thumbnail compression beyond the capabilities of existing codecs is therefore a current research focus, as any byte savings will significantly enhance the experience of mobile device users. Toward this end, we propose a general framework for variable-rate image compression and a novel architecture based on convolutional and deconvolutional LSTM recurrent networks. Our models address the main issues that have prevented autoencoder neural networks from competing with existing image compression algorithms: (1) our networks only need to be trained once (not per-image), regardless of input image dimensions and the desired compression rate; (2) our networks are progressive, meaning that the more bits are sent, the more accurate the image reconstruction; and (3) the proposed architecture is at least as efficient as a standard purpose-trained autoencoder for a given number of bits. On a large-scale benchmark of 32$times$32 thumbnails, our LSTM-based approaches provide better visual quality than (headerless) JPEG, JPEG2000 and WebP, with a storage size that is reduced by 10% or more." @default.
- W4297659253 created "2022-09-30" @default.
- W4297659253 creator A5034317020 @default.
- W4297659253 creator A5039047872 @default.
- W4297659253 creator A5054902123 @default.
- W4297659253 creator A5058616625 @default.
- W4297659253 creator A5066107323 @default.
- W4297659253 creator A5074753447 @default.
- W4297659253 creator A5078347851 @default.
- W4297659253 creator A5085643229 @default.
- W4297659253 date "2015-11-19" @default.
- W4297659253 modified "2023-10-14" @default.
- W4297659253 title "Variable Rate Image Compression with Recurrent Neural Networks" @default.
- W4297659253 doi "https://doi.org/10.48550/arxiv.1511.06085" @default.
- W4297659253 hasPublicationYear "2015" @default.
- W4297659253 type Work @default.
- W4297659253 citedByCount "2" @default.
- W4297659253 countsByYear W42976592532022 @default.
- W4297659253 countsByYear W42976592532023 @default.
- W4297659253 crossrefType "posted-content" @default.
- W4297659253 hasAuthorship W4297659253A5034317020 @default.
- W4297659253 hasAuthorship W4297659253A5039047872 @default.
- W4297659253 hasAuthorship W4297659253A5054902123 @default.
- W4297659253 hasAuthorship W4297659253A5058616625 @default.
- W4297659253 hasAuthorship W4297659253A5066107323 @default.
- W4297659253 hasAuthorship W4297659253A5074753447 @default.
- W4297659253 hasAuthorship W4297659253A5078347851 @default.
- W4297659253 hasAuthorship W4297659253A5085643229 @default.
- W4297659253 hasBestOaLocation W42976592531 @default.
- W4297659253 hasConcept C101738243 @default.
- W4297659253 hasConcept C113775141 @default.
- W4297659253 hasConcept C115961682 @default.
- W4297659253 hasConcept C13481523 @default.
- W4297659253 hasConcept C154945302 @default.
- W4297659253 hasConcept C160174412 @default.
- W4297659253 hasConcept C198751489 @default.
- W4297659253 hasConcept C31972630 @default.
- W4297659253 hasConcept C41008148 @default.
- W4297659253 hasConcept C50644808 @default.
- W4297659253 hasConcept C55020928 @default.
- W4297659253 hasConcept C69216139 @default.
- W4297659253 hasConcept C78548338 @default.
- W4297659253 hasConcept C81363708 @default.
- W4297659253 hasConcept C9417928 @default.
- W4297659253 hasConceptScore W4297659253C101738243 @default.
- W4297659253 hasConceptScore W4297659253C113775141 @default.
- W4297659253 hasConceptScore W4297659253C115961682 @default.
- W4297659253 hasConceptScore W4297659253C13481523 @default.
- W4297659253 hasConceptScore W4297659253C154945302 @default.
- W4297659253 hasConceptScore W4297659253C160174412 @default.
- W4297659253 hasConceptScore W4297659253C198751489 @default.
- W4297659253 hasConceptScore W4297659253C31972630 @default.
- W4297659253 hasConceptScore W4297659253C41008148 @default.
- W4297659253 hasConceptScore W4297659253C50644808 @default.
- W4297659253 hasConceptScore W4297659253C55020928 @default.
- W4297659253 hasConceptScore W4297659253C69216139 @default.
- W4297659253 hasConceptScore W4297659253C78548338 @default.
- W4297659253 hasConceptScore W4297659253C81363708 @default.
- W4297659253 hasConceptScore W4297659253C9417928 @default.
- W4297659253 hasLocation W42976592531 @default.
- W4297659253 hasOpenAccess W4297659253 @default.
- W4297659253 hasPrimaryLocation W42976592531 @default.
- W4297659253 hasRelatedWork W1997826598 @default.
- W4297659253 hasRelatedWork W2019741823 @default.
- W4297659253 hasRelatedWork W2137460601 @default.
- W4297659253 hasRelatedWork W2276024283 @default.
- W4297659253 hasRelatedWork W2548843363 @default.
- W4297659253 hasRelatedWork W2805485104 @default.
- W4297659253 hasRelatedWork W2919720707 @default.
- W4297659253 hasRelatedWork W2943316151 @default.
- W4297659253 hasRelatedWork W2962790638 @default.
- W4297659253 hasRelatedWork W3115334197 @default.
- W4297659253 isParatext "false" @default.
- W4297659253 isRetracted "false" @default.
- W4297659253 workType "article" @default.