FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4297985324> ?p ?o ?g. }

• W4297985324 abstract "Recent advances have shown that latent representations of pre-trained Deep Convolutional Neural Networks (DCNNs) for classification can be modelled to generate scores that are well correlated with human perceptual judgement. In this paper we seek to extend the use of perceptually relevant losses in training a DCNN for video compression artefact removal. We will use internal representations of a pre-trained classification network as the basis of the loss functions. Specifically, the LPIPS metric and a perceptual discriminator will be responsible for low-level and high-level features respectively. The perceptual discriminator uses differing internal feature representations of the VGG network as its first stage of feature extraction. Initial results shows an increase in performance in perceptually based metrics such VMAF, LPIPS and BRISQUE, while showing a decrease in performance in PSNR." @default.
• W4297985324 created "2022-10-01" @default.
• W4297985324 creator A5038678615 @default.
• W4297985324 creator A5060507975 @default.
• W4297985324 creator A5073540444 @default.
• W4297985324 creator A5084295171 @default.
• W4297985324 creator A5090695020 @default.
• W4297985324 date "2022-10-03" @default.
• W4297985324 modified "2023-10-14" @default.
• W4297985324 title "Perceptually motivated deep neural network for video compression artifact removal" @default.
• W4297985324 cites W1567645745 @default.
• W4297985324 cites W1578985305 @default.
• W4297985324 cites W1580389772 @default.
• W4297985324 cites W2060131032 @default.
• W4297985324 cites W2096867028 @default.
• W4297985324 cites W2133665775 @default.
• W4297985324 cites W2161927477 @default.
• W4297985324 cites W2562637781 @default.
• W4297985324 cites W2921022248 @default.
• W4297985324 cites W2939995367 @default.
• W4297985324 cites W2963073614 @default.
• W4297985324 cites W3000775737 @default.
• W4297985324 cites W3014641072 @default.
• W4297985324 cites W3046220160 @default.
• W4297985324 cites W3085180753 @default.
• W4297985324 cites W3191755940 @default.
• W4297985324 cites W4200399832 @default.
• W4297985324 cites W4212991200 @default.
• W4297985324 cites W4250685322 @default.
• W4297985324 cites W4286696412 @default.
• W4297985324 doi "https://doi.org/10.1117/12.2633552" @default.
• W4297985324 hasPublicationYear "2022" @default.
• W4297985324 type Work @default.
• W4297985324 citedByCount "0" @default.
• W4297985324 crossrefType "proceedings-article" @default.
• W4297985324 hasAuthorship W4297985324A5038678615 @default.
• W4297985324 hasAuthorship W4297985324A5060507975 @default.
• W4297985324 hasAuthorship W4297985324A5073540444 @default.
• W4297985324 hasAuthorship W4297985324A5084295171 @default.
• W4297985324 hasAuthorship W4297985324A5090695020 @default.
• W4297985324 hasConcept C108583219 @default.
• W4297985324 hasConcept C115961682 @default.
• W4297985324 hasConcept C127413603 @default.
• W4297985324 hasConcept C13481523 @default.
• W4297985324 hasConcept C138885662 @default.
• W4297985324 hasConcept C153180895 @default.
• W4297985324 hasConcept C154945302 @default.
• W4297985324 hasConcept C169760540 @default.
• W4297985324 hasConcept C176217482 @default.
• W4297985324 hasConcept C21547014 @default.
• W4297985324 hasConcept C26760741 @default.
• W4297985324 hasConcept C2776401178 @default.
• W4297985324 hasConcept C2779010991 @default.
• W4297985324 hasConcept C2779803651 @default.
• W4297985324 hasConcept C28490314 @default.
• W4297985324 hasConcept C41008148 @default.
• W4297985324 hasConcept C41895202 @default.
• W4297985324 hasConcept C52622490 @default.
• W4297985324 hasConcept C57654395 @default.
• W4297985324 hasConcept C76155785 @default.
• W4297985324 hasConcept C81363708 @default.
• W4297985324 hasConcept C86803240 @default.
• W4297985324 hasConcept C9417928 @default.
• W4297985324 hasConcept C94915269 @default.
• W4297985324 hasConceptScore W4297985324C108583219 @default.
• W4297985324 hasConceptScore W4297985324C115961682 @default.
• W4297985324 hasConceptScore W4297985324C127413603 @default.
• W4297985324 hasConceptScore W4297985324C13481523 @default.
• W4297985324 hasConceptScore W4297985324C138885662 @default.
• W4297985324 hasConceptScore W4297985324C153180895 @default.
• W4297985324 hasConceptScore W4297985324C154945302 @default.
• W4297985324 hasConceptScore W4297985324C169760540 @default.
• W4297985324 hasConceptScore W4297985324C176217482 @default.
• W4297985324 hasConceptScore W4297985324C21547014 @default.
• W4297985324 hasConceptScore W4297985324C26760741 @default.
• W4297985324 hasConceptScore W4297985324C2776401178 @default.
• W4297985324 hasConceptScore W4297985324C2779010991 @default.
• W4297985324 hasConceptScore W4297985324C2779803651 @default.
• W4297985324 hasConceptScore W4297985324C28490314 @default.
• W4297985324 hasConceptScore W4297985324C41008148 @default.
• W4297985324 hasConceptScore W4297985324C41895202 @default.
• W4297985324 hasConceptScore W4297985324C52622490 @default.
• W4297985324 hasConceptScore W4297985324C57654395 @default.
• W4297985324 hasConceptScore W4297985324C76155785 @default.
• W4297985324 hasConceptScore W4297985324C81363708 @default.
• W4297985324 hasConceptScore W4297985324C86803240 @default.
• W4297985324 hasConceptScore W4297985324C9417928 @default.
• W4297985324 hasConceptScore W4297985324C94915269 @default.
• W4297985324 hasLocation W42979853241 @default.
• W4297985324 hasOpenAccess W4297985324 @default.
• W4297985324 hasPrimaryLocation W42979853241 @default.
• W4297985324 hasRelatedWork W2279398222 @default.
• W4297985324 hasRelatedWork W2546942002 @default.
• W4297985324 hasRelatedWork W2731899572 @default.
• W4297985324 hasRelatedWork W3133861977 @default.
• W4297985324 hasRelatedWork W3156786002 @default.
• W4297985324 hasRelatedWork W4200173597 @default.
• W4297985324 hasRelatedWork W4299822940 @default.
• W4297985324 hasRelatedWork W4312417841 @default.
• W4297985324 hasRelatedWork W4321369474 @default.

• next