Matches in SemOpenAlex for { <https://semopenalex.org/work/W3160555381> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3160555381 abstract "An increasing share of image and video content is analyzed by machines rather than viewed by humans, and therefore it becomes relevant to optimize codecs for such applications where the analysis is performed remotely. Unfortunately, conventional coding tools are challenging to specialize for machine tasks as they were originally designed for human perception. However, neural network based codecs can be jointly trained end-to-end with any convolutional neural network (CNN)-based task model. In this paper, we propose to study an end-to-end framework enabling efficient image compression for remote machine task analysis, using a chain composed of a compression module and a task algorithm that can be optimized end-to-end. We show that it is possible to significantly improve the task accuracy when fine-tuning jointly the codec and the task networks, especially at low bitrates. Depending on training or deployment constraints, selective fine-tuning can be applied only on the encoder, decoder or task network and still achieve rate-accuracy improvements over an off-the-shelf codec and task network. Our results also demonstrate the flexibility of end-to-end pipelines for practical applications." @default.
- W3160555381 created "2021-05-24" @default.
- W3160555381 creator A5002800911 @default.
- W3160555381 creator A5012532575 @default.
- W3160555381 creator A5039141095 @default.
- W3160555381 creator A5062226930 @default.
- W3160555381 creator A5073743402 @default.
- W3160555381 date "2021-03-01" @default.
- W3160555381 modified "2023-09-25" @default.
- W3160555381 title "End-to-End optimized image compression for machines, a study" @default.
- W3160555381 cites W2140196014 @default.
- W3160555381 cites W2146395539 @default.
- W3160555381 cites W2891639355 @default.
- W3160555381 cites W2965248168 @default.
- W3160555381 cites W2982083293 @default.
- W3160555381 cites W3034469748 @default.
- W3160555381 cites W3082548248 @default.
- W3160555381 cites W3090392341 @default.
- W3160555381 cites W3091266734 @default.
- W3160555381 doi "https://doi.org/10.1109/dcc50243.2021.00024" @default.
- W3160555381 hasPublicationYear "2021" @default.
- W3160555381 type Work @default.
- W3160555381 sameAs 3160555381 @default.
- W3160555381 citedByCount "18" @default.
- W3160555381 countsByYear W31605553812021 @default.
- W3160555381 countsByYear W31605553812022 @default.
- W3160555381 countsByYear W31605553812023 @default.
- W3160555381 crossrefType "proceedings-article" @default.
- W3160555381 hasAuthorship W3160555381A5002800911 @default.
- W3160555381 hasAuthorship W3160555381A5012532575 @default.
- W3160555381 hasAuthorship W3160555381A5039141095 @default.
- W3160555381 hasAuthorship W3160555381A5062226930 @default.
- W3160555381 hasAuthorship W3160555381A5073743402 @default.
- W3160555381 hasBestOaLocation W31605553812 @default.
- W3160555381 hasConcept C105795698 @default.
- W3160555381 hasConcept C111919701 @default.
- W3160555381 hasConcept C11413529 @default.
- W3160555381 hasConcept C115961682 @default.
- W3160555381 hasConcept C118505674 @default.
- W3160555381 hasConcept C13481523 @default.
- W3160555381 hasConcept C154945302 @default.
- W3160555381 hasConcept C161765866 @default.
- W3160555381 hasConcept C162324750 @default.
- W3160555381 hasConcept C179518139 @default.
- W3160555381 hasConcept C187736073 @default.
- W3160555381 hasConcept C2780451532 @default.
- W3160555381 hasConcept C33923547 @default.
- W3160555381 hasConcept C41008148 @default.
- W3160555381 hasConcept C57273362 @default.
- W3160555381 hasConcept C74296488 @default.
- W3160555381 hasConcept C78548338 @default.
- W3160555381 hasConcept C81363708 @default.
- W3160555381 hasConcept C9390403 @default.
- W3160555381 hasConcept C9417928 @default.
- W3160555381 hasConceptScore W3160555381C105795698 @default.
- W3160555381 hasConceptScore W3160555381C111919701 @default.
- W3160555381 hasConceptScore W3160555381C11413529 @default.
- W3160555381 hasConceptScore W3160555381C115961682 @default.
- W3160555381 hasConceptScore W3160555381C118505674 @default.
- W3160555381 hasConceptScore W3160555381C13481523 @default.
- W3160555381 hasConceptScore W3160555381C154945302 @default.
- W3160555381 hasConceptScore W3160555381C161765866 @default.
- W3160555381 hasConceptScore W3160555381C162324750 @default.
- W3160555381 hasConceptScore W3160555381C179518139 @default.
- W3160555381 hasConceptScore W3160555381C187736073 @default.
- W3160555381 hasConceptScore W3160555381C2780451532 @default.
- W3160555381 hasConceptScore W3160555381C33923547 @default.
- W3160555381 hasConceptScore W3160555381C41008148 @default.
- W3160555381 hasConceptScore W3160555381C57273362 @default.
- W3160555381 hasConceptScore W3160555381C74296488 @default.
- W3160555381 hasConceptScore W3160555381C78548338 @default.
- W3160555381 hasConceptScore W3160555381C81363708 @default.
- W3160555381 hasConceptScore W3160555381C9390403 @default.
- W3160555381 hasConceptScore W3160555381C9417928 @default.
- W3160555381 hasLocation W31605553811 @default.
- W3160555381 hasLocation W31605553812 @default.
- W3160555381 hasOpenAccess W3160555381 @default.
- W3160555381 hasPrimaryLocation W31605553811 @default.
- W3160555381 hasRelatedWork W1982504210 @default.
- W3160555381 hasRelatedWork W2158681771 @default.
- W3160555381 hasRelatedWork W2264127496 @default.
- W3160555381 hasRelatedWork W2335610473 @default.
- W3160555381 hasRelatedWork W2371987643 @default.
- W3160555381 hasRelatedWork W2383319832 @default.
- W3160555381 hasRelatedWork W4205961410 @default.
- W3160555381 hasRelatedWork W4283699800 @default.
- W3160555381 hasRelatedWork W4308238081 @default.
- W3160555381 hasRelatedWork W4312959332 @default.
- W3160555381 isParatext "false" @default.
- W3160555381 isRetracted "false" @default.
- W3160555381 magId "3160555381" @default.
- W3160555381 workType "article" @default.