Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035280441> ?p ?o ?g. }
- W3035280441 abstract "Deep convolution-based single image super-resolution (SISR) networks embrace the benefits of learning from large-scale external image resources for local recovery, yet most existing works have ignored the long-range feature-wise similarities in natural images. Some recent works have successfully leveraged this intrinsic feature correlation by exploring non-local attention modules. However, none of the current deep models have studied another inherent property of images: cross-scale feature correlation. In this paper, we propose the first Cross-Scale Non-Local (CS-NL) attention module with integration into a recurrent neural network. By combining the new CS-NL prior with local and in-scale non-local priors in a powerful recurrent fusion cell, we can find more cross-scale feature correlations within a single low-resolution (LR) image. The performance of SISR is significantly improved by exhaustively integrating all possible priors. Extensive experiments demonstrate the effectiveness of the proposed CS-NL module by setting new state-of-the-arts on multiple SISR benchmarks." @default.
- W3035280441 created "2020-06-19" @default.
- W3035280441 creator A5008831111 @default.
- W3035280441 creator A5039532295 @default.
- W3035280441 creator A5051800592 @default.
- W3035280441 creator A5063728407 @default.
- W3035280441 creator A5070527811 @default.
- W3035280441 creator A5084047903 @default.
- W3035280441 date "2020-06-01" @default.
- W3035280441 modified "2023-10-13" @default.
- W3035280441 title "Image Super-Resolution With Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining" @default.
- W3035280441 cites W1930824406 @default.
- W3035280441 cites W1976416062 @default.
- W3035280441 cites W1983781364 @default.
- W3035280441 cites W1992408872 @default.
- W3035280441 cites W2047920195 @default.
- W3035280441 cites W2062811295 @default.
- W3035280441 cites W2097074225 @default.
- W3035280441 cites W2121927366 @default.
- W3035280441 cites W2122632184 @default.
- W3035280441 cites W2133665775 @default.
- W3035280441 cites W2137290314 @default.
- W3035280441 cites W2164551808 @default.
- W3035280441 cites W2167191464 @default.
- W3035280441 cites W2192954843 @default.
- W3035280441 cites W2242218935 @default.
- W3035280441 cites W2534320940 @default.
- W3035280441 cites W2607041014 @default.
- W3035280441 cites W2618530766 @default.
- W3035280441 cites W2739757502 @default.
- W3035280441 cites W2739815012 @default.
- W3035280441 cites W2789370848 @default.
- W3035280441 cites W2947156405 @default.
- W3035280441 cites W2954930822 @default.
- W3035280441 cites W2963091558 @default.
- W3035280441 cites W2963372104 @default.
- W3035280441 cites W2963610452 @default.
- W3035280441 cites W2963661166 @default.
- W3035280441 cites W2963704386 @default.
- W3035280441 cites W2963729050 @default.
- W3035280441 cites W2964101377 @default.
- W3035280441 cites W2964277374 @default.
- W3035280441 cites W968293391 @default.
- W3035280441 doi "https://doi.org/10.1109/cvpr42600.2020.00573" @default.
- W3035280441 hasPublicationYear "2020" @default.
- W3035280441 type Work @default.
- W3035280441 sameAs 3035280441 @default.
- W3035280441 citedByCount "171" @default.
- W3035280441 countsByYear W30352804412019 @default.
- W3035280441 countsByYear W30352804412020 @default.
- W3035280441 countsByYear W30352804412021 @default.
- W3035280441 countsByYear W30352804412022 @default.
- W3035280441 countsByYear W30352804412023 @default.
- W3035280441 crossrefType "proceedings-article" @default.
- W3035280441 hasAuthorship W3035280441A5008831111 @default.
- W3035280441 hasAuthorship W3035280441A5039532295 @default.
- W3035280441 hasAuthorship W3035280441A5051800592 @default.
- W3035280441 hasAuthorship W3035280441A5063728407 @default.
- W3035280441 hasAuthorship W3035280441A5070527811 @default.
- W3035280441 hasAuthorship W3035280441A5084047903 @default.
- W3035280441 hasBestOaLocation W30352804412 @default.
- W3035280441 hasConcept C107673813 @default.
- W3035280441 hasConcept C115961682 @default.
- W3035280441 hasConcept C138885662 @default.
- W3035280441 hasConcept C153180895 @default.
- W3035280441 hasConcept C154945302 @default.
- W3035280441 hasConcept C177769412 @default.
- W3035280441 hasConcept C205372480 @default.
- W3035280441 hasConcept C205649164 @default.
- W3035280441 hasConcept C2776401178 @default.
- W3035280441 hasConcept C2778755073 @default.
- W3035280441 hasConcept C41008148 @default.
- W3035280441 hasConcept C41895202 @default.
- W3035280441 hasConcept C45347329 @default.
- W3035280441 hasConcept C50644808 @default.
- W3035280441 hasConcept C58640448 @default.
- W3035280441 hasConcept C81363708 @default.
- W3035280441 hasConceptScore W3035280441C107673813 @default.
- W3035280441 hasConceptScore W3035280441C115961682 @default.
- W3035280441 hasConceptScore W3035280441C138885662 @default.
- W3035280441 hasConceptScore W3035280441C153180895 @default.
- W3035280441 hasConceptScore W3035280441C154945302 @default.
- W3035280441 hasConceptScore W3035280441C177769412 @default.
- W3035280441 hasConceptScore W3035280441C205372480 @default.
- W3035280441 hasConceptScore W3035280441C205649164 @default.
- W3035280441 hasConceptScore W3035280441C2776401178 @default.
- W3035280441 hasConceptScore W3035280441C2778755073 @default.
- W3035280441 hasConceptScore W3035280441C41008148 @default.
- W3035280441 hasConceptScore W3035280441C41895202 @default.
- W3035280441 hasConceptScore W3035280441C45347329 @default.
- W3035280441 hasConceptScore W3035280441C50644808 @default.
- W3035280441 hasConceptScore W3035280441C58640448 @default.
- W3035280441 hasConceptScore W3035280441C81363708 @default.
- W3035280441 hasLocation W30352804411 @default.
- W3035280441 hasLocation W30352804412 @default.
- W3035280441 hasOpenAccess W3035280441 @default.
- W3035280441 hasPrimaryLocation W30352804411 @default.
- W3035280441 hasRelatedWork W2295021132 @default.
- W3035280441 hasRelatedWork W2760085659 @default.
- W3035280441 hasRelatedWork W2810384904 @default.