Matches in SemOpenAlex for { <https://semopenalex.org/work/W4316660658> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4316660658 abstract "During the last four years, we have witnessed the success of end-to-end trainable models for image compression. Compared to decades of incremental work, these machine learning (ML) techniques learn all the components of the compression technique, which explains their actual superiority. However, end-to-end ML models have not yet reached the performance of traditional video codecs such as VVC. Possible explanations can be put forward: lack of data to account for the temporal redundancy, or inefficiency of latent's density estimation in the neural model. The latter problem can be defined by the discrepancy between the latent's marginal distribution and the learned prior distribution. This mismatch, known as amortization gap of entropy model, enlarges the file size of compressed data. In this paper, we propose to evaluate the amortization gap for three state-of-the-art ML video compression methods. Second, we propose an efficient and generic method to solve the amortization gap and show that it leads to an improvement between 2% to 5 % without impacting reconstruction quality." @default.
- W4316660658 created "2023-01-17" @default.
- W4316660658 creator A5020394666 @default.
- W4316660658 creator A5026443898 @default.
- W4316660658 creator A5041269156 @default.
- W4316660658 date "2022-12-13" @default.
- W4316660658 modified "2023-09-25" @default.
- W4316660658 title "Reducing The Mismatch Between Marginal and Learned Distributions in Neural Video Compression" @default.
- W4316660658 cites W2146395539 @default.
- W4316660658 cites W2969260367 @default.
- W4316660658 cites W3031546776 @default.
- W4316660658 cites W3034469748 @default.
- W4316660658 cites W3035195755 @default.
- W4316660658 cites W3135530072 @default.
- W4316660658 cites W3201765774 @default.
- W4316660658 cites W4214761665 @default.
- W4316660658 cites W4283377204 @default.
- W4316660658 cites W4317555471 @default.
- W4316660658 doi "https://doi.org/10.1109/vcip56404.2022.10008819" @default.
- W4316660658 hasPublicationYear "2022" @default.
- W4316660658 type Work @default.
- W4316660658 citedByCount "0" @default.
- W4316660658 crossrefType "proceedings-article" @default.
- W4316660658 hasAuthorship W4316660658A5020394666 @default.
- W4316660658 hasAuthorship W4316660658A5026443898 @default.
- W4316660658 hasAuthorship W4316660658A5041269156 @default.
- W4316660658 hasBestOaLocation W43166606582 @default.
- W4316660658 hasConcept C10138342 @default.
- W4316660658 hasConcept C106301342 @default.
- W4316660658 hasConcept C107673813 @default.
- W4316660658 hasConcept C111919701 @default.
- W4316660658 hasConcept C119857082 @default.
- W4316660658 hasConcept C121332964 @default.
- W4316660658 hasConcept C152124472 @default.
- W4316660658 hasConcept C154945302 @default.
- W4316660658 hasConcept C159985019 @default.
- W4316660658 hasConcept C161765866 @default.
- W4316660658 hasConcept C162324750 @default.
- W4316660658 hasConcept C177769412 @default.
- W4316660658 hasConcept C180016635 @default.
- W4316660658 hasConcept C192562407 @default.
- W4316660658 hasConcept C2777764128 @default.
- W4316660658 hasConcept C2781198434 @default.
- W4316660658 hasConcept C41008148 @default.
- W4316660658 hasConcept C62520636 @default.
- W4316660658 hasConcept C78548338 @default.
- W4316660658 hasConcept C9390403 @default.
- W4316660658 hasConceptScore W4316660658C10138342 @default.
- W4316660658 hasConceptScore W4316660658C106301342 @default.
- W4316660658 hasConceptScore W4316660658C107673813 @default.
- W4316660658 hasConceptScore W4316660658C111919701 @default.
- W4316660658 hasConceptScore W4316660658C119857082 @default.
- W4316660658 hasConceptScore W4316660658C121332964 @default.
- W4316660658 hasConceptScore W4316660658C152124472 @default.
- W4316660658 hasConceptScore W4316660658C154945302 @default.
- W4316660658 hasConceptScore W4316660658C159985019 @default.
- W4316660658 hasConceptScore W4316660658C161765866 @default.
- W4316660658 hasConceptScore W4316660658C162324750 @default.
- W4316660658 hasConceptScore W4316660658C177769412 @default.
- W4316660658 hasConceptScore W4316660658C180016635 @default.
- W4316660658 hasConceptScore W4316660658C192562407 @default.
- W4316660658 hasConceptScore W4316660658C2777764128 @default.
- W4316660658 hasConceptScore W4316660658C2781198434 @default.
- W4316660658 hasConceptScore W4316660658C41008148 @default.
- W4316660658 hasConceptScore W4316660658C62520636 @default.
- W4316660658 hasConceptScore W4316660658C78548338 @default.
- W4316660658 hasConceptScore W4316660658C9390403 @default.
- W4316660658 hasLocation W43166606581 @default.
- W4316660658 hasLocation W43166606582 @default.
- W4316660658 hasOpenAccess W4316660658 @default.
- W4316660658 hasPrimaryLocation W43166606581 @default.
- W4316660658 hasRelatedWork W1536392060 @default.
- W4316660658 hasRelatedWork W1670812416 @default.
- W4316660658 hasRelatedWork W1992113831 @default.
- W4316660658 hasRelatedWork W2126922921 @default.
- W4316660658 hasRelatedWork W2378514695 @default.
- W4316660658 hasRelatedWork W2801465073 @default.
- W4316660658 hasRelatedWork W2936485217 @default.
- W4316660658 hasRelatedWork W2997572967 @default.
- W4316660658 hasRelatedWork W3035638508 @default.
- W4316660658 hasRelatedWork W74596110 @default.
- W4316660658 isParatext "false" @default.
- W4316660658 isRetracted "false" @default.
- W4316660658 workType "article" @default.