Matches in SemOpenAlex for { <https://semopenalex.org/work/W3019578801> ?p ?o ?g. }
- W3019578801 abstract "It plays a fundamental role to compactly represent the visual information towards the optimization of the ultimate utility in myriad visual data centered applications. With numerous approaches proposed to efficiently compress the texture and visual features serving human visual perception and machine intelligence respectively, much less work has been dedicated to studying the interactions between them. Here we investigate the integration of feature and texture compression, and show that a universal and collaborative visual information representation can be achieved in a hierarchical way. In particular, we study the feature and texture compression in a scalable coding framework, where the base layer serves as the deep learning feature and enhancement layer targets to perfectly reconstruct the texture. Based on the strong generative capability of deep neural networks, the gap between the base feature layer and enhancement layer is further filled with the feature level texture reconstruction, aiming to further construct texture representation from feature. As such, the residuals between the original and reconstructed texture could be further conveyed in the enhancement layer. To improve the efficiency of the proposed framework, the base layer neural network is trained in a multi-task manner such that the learned features enjoy both high quality reconstruction and high accuracy analysis. We further demonstrate the framework and optimization strategies in face image compression, and promising coding performance has been achieved in terms of both rate-fidelity and rate-accuracy." @default.
- W3019578801 created "2020-05-01" @default.
- W3019578801 creator A5001392803 @default.
- W3019578801 creator A5018478553 @default.
- W3019578801 creator A5039832462 @default.
- W3019578801 creator A5042401810 @default.
- W3019578801 creator A5055937409 @default.
- W3019578801 creator A5070884682 @default.
- W3019578801 date "2020-04-21" @default.
- W3019578801 modified "2023-09-28" @default.
- W3019578801 title "Towards Analysis-friendly Face Representation with Scalable Feature and Texture Compression" @default.
- W3019578801 cites W1533861849 @default.
- W3019578801 cites W1782590233 @default.
- W3019578801 cites W1992371516 @default.
- W3019578801 cites W2015328715 @default.
- W3019578801 cites W2048820076 @default.
- W3019578801 cites W2050043425 @default.
- W3019578801 cites W2051836535 @default.
- W3019578801 cites W2060658301 @default.
- W3019578801 cites W2069463273 @default.
- W3019578801 cites W2070455027 @default.
- W3019578801 cites W2077815765 @default.
- W3019578801 cites W2118217749 @default.
- W3019578801 cites W2124509324 @default.
- W3019578801 cites W2132216194 @default.
- W3019578801 cites W2140196014 @default.
- W3019578801 cites W2140199336 @default.
- W3019578801 cites W2146395539 @default.
- W3019578801 cites W2163605009 @default.
- W3019578801 cites W2167534083 @default.
- W3019578801 cites W2172073677 @default.
- W3019578801 cites W2186356322 @default.
- W3019578801 cites W2187089797 @default.
- W3019578801 cites W2243883016 @default.
- W3019578801 cites W2407574721 @default.
- W3019578801 cites W2464915613 @default.
- W3019578801 cites W2497836941 @default.
- W3019578801 cites W2508837377 @default.
- W3019578801 cites W2511925907 @default.
- W3019578801 cites W2566588379 @default.
- W3019578801 cites W2758733702 @default.
- W3019578801 cites W2783569857 @default.
- W3019578801 cites W2896841716 @default.
- W3019578801 cites W2935381027 @default.
- W3019578801 cites W2946536378 @default.
- W3019578801 cites W2962676454 @default.
- W3019578801 cites W2962790638 @default.
- W3019578801 cites W2962835968 @default.
- W3019578801 cites W2963620157 @default.
- W3019578801 cites W2963839617 @default.
- W3019578801 cites W2964098744 @default.
- W3019578801 cites W2964121744 @default.
- W3019578801 cites W2964191079 @default.
- W3019578801 cites W2964350391 @default.
- W3019578801 cites W2969260367 @default.
- W3019578801 cites W2970339328 @default.
- W3019578801 cites W2975749976 @default.
- W3019578801 cites W2991630191 @default.
- W3019578801 cites W3000419664 @default.
- W3019578801 cites W3000470288 @default.
- W3019578801 cites W3000726408 @default.
- W3019578801 cites W3004695517 @default.
- W3019578801 cites W3099206234 @default.
- W3019578801 cites W3101998545 @default.
- W3019578801 cites W3135530072 @default.
- W3019578801 cites W3140272129 @default.
- W3019578801 doi "https://doi.org/10.48550/arxiv.2004.10043" @default.
- W3019578801 hasPublicationYear "2020" @default.
- W3019578801 type Work @default.
- W3019578801 sameAs 3019578801 @default.
- W3019578801 citedByCount "1" @default.
- W3019578801 countsByYear W30195788012021 @default.
- W3019578801 crossrefType "posted-content" @default.
- W3019578801 hasAuthorship W3019578801A5001392803 @default.
- W3019578801 hasAuthorship W3019578801A5018478553 @default.
- W3019578801 hasAuthorship W3019578801A5039832462 @default.
- W3019578801 hasAuthorship W3019578801A5042401810 @default.
- W3019578801 hasAuthorship W3019578801A5055937409 @default.
- W3019578801 hasAuthorship W3019578801A5070884682 @default.
- W3019578801 hasBestOaLocation W30195788011 @default.
- W3019578801 hasConcept C105795698 @default.
- W3019578801 hasConcept C115961682 @default.
- W3019578801 hasConcept C13481523 @default.
- W3019578801 hasConcept C138885662 @default.
- W3019578801 hasConcept C153180895 @default.
- W3019578801 hasConcept C154945302 @default.
- W3019578801 hasConcept C179518139 @default.
- W3019578801 hasConcept C2776401178 @default.
- W3019578801 hasConcept C2781195486 @default.
- W3019578801 hasConcept C31510193 @default.
- W3019578801 hasConcept C31972630 @default.
- W3019578801 hasConcept C33923547 @default.
- W3019578801 hasConcept C41008148 @default.
- W3019578801 hasConcept C41895202 @default.
- W3019578801 hasConcept C54243161 @default.
- W3019578801 hasConcept C9417928 @default.
- W3019578801 hasConceptScore W3019578801C105795698 @default.
- W3019578801 hasConceptScore W3019578801C115961682 @default.
- W3019578801 hasConceptScore W3019578801C13481523 @default.
- W3019578801 hasConceptScore W3019578801C138885662 @default.