Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311485087> ?p ?o ?g. }
- W4311485087 endingPage "103730" @default.
- W4311485087 startingPage "103730" @default.
- W4311485087 abstract "Recently, Convolutional Neural Networks (CNNs) have achieved great success in Single Image Super-Resolution (SISR). In particular, the recursive networks are now widely used. However, existing recursion-based SISR networks can only make use of multi-scale features in a layer-wise manner. In this paper, a Deep Recursive Multi-Scale Feature Fusion Network (DRMSFFN) is proposed to address this issue. Specifically, we propose a Recursive Multi-Scale Feature Fusion Block (RMSFFB) to make full use of multi-scale features. Besides, a Progressive Feature Fusion (PFF) technique is proposed to take advantage of the hierarchical features from the RMSFFB in a global manner. At the reconstruction stage, we use a deconvolutional layer to upscale the feature maps to the desired size. Extensive experimental results on benchmark datasets demonstrate the superiority of the proposed DRMSFFN in comparison with the state-of-the-art methods in both quantitative and qualitative evaluations." @default.
- W4311485087 created "2022-12-26" @default.
- W4311485087 creator A5012437460 @default.
- W4311485087 creator A5046813662 @default.
- W4311485087 creator A5060431284 @default.
- W4311485087 date "2023-02-01" @default.
- W4311485087 modified "2023-10-17" @default.
- W4311485087 title "A deep recursive multi-scale feature fusion network for image super-resolution" @default.
- W4311485087 cites W1677182931 @default.
- W4311485087 cites W1885185971 @default.
- W4311485087 cites W1903029394 @default.
- W4311485087 cites W1930824406 @default.
- W4311485087 cites W1992408872 @default.
- W4311485087 cites W2044011870 @default.
- W4311485087 cites W2047920195 @default.
- W4311485087 cites W2097117768 @default.
- W4311485087 cites W2108598243 @default.
- W4311485087 cites W2121058967 @default.
- W4311485087 cites W2133665775 @default.
- W4311485087 cites W2150081556 @default.
- W4311485087 cites W2157190232 @default.
- W4311485087 cites W2183341477 @default.
- W4311485087 cites W2192954843 @default.
- W4311485087 cites W2194775991 @default.
- W4311485087 cites W2214802144 @default.
- W4311485087 cites W2242218935 @default.
- W4311485087 cites W2476548250 @default.
- W4311485087 cites W2565639579 @default.
- W4311485087 cites W2607041014 @default.
- W4311485087 cites W2741137940 @default.
- W4311485087 cites W2747898905 @default.
- W4311485087 cites W2795024892 @default.
- W4311485087 cites W2799120945 @default.
- W4311485087 cites W2866634454 @default.
- W4311485087 cites W2895420332 @default.
- W4311485087 cites W2895598217 @default.
- W4311485087 cites W2901534369 @default.
- W4311485087 cites W2912849458 @default.
- W4311485087 cites W2928165649 @default.
- W4311485087 cites W2941260331 @default.
- W4311485087 cites W2954930822 @default.
- W4311485087 cites W2963136578 @default.
- W4311485087 cites W2963372104 @default.
- W4311485087 cites W2963470893 @default.
- W4311485087 cites W2963610452 @default.
- W4311485087 cites W2963729050 @default.
- W4311485087 cites W2964101377 @default.
- W4311485087 cites W2964277374 @default.
- W4311485087 cites W2998349962 @default.
- W4311485087 cites W3034247386 @default.
- W4311485087 cites W3104792420 @default.
- W4311485087 cites W3129838834 @default.
- W4311485087 doi "https://doi.org/10.1016/j.jvcir.2022.103730" @default.
- W4311485087 hasPublicationYear "2023" @default.
- W4311485087 type Work @default.
- W4311485087 citedByCount "3" @default.
- W4311485087 countsByYear W43114850872023 @default.
- W4311485087 crossrefType "journal-article" @default.
- W4311485087 hasAuthorship W4311485087A5012437460 @default.
- W4311485087 hasAuthorship W4311485087A5046813662 @default.
- W4311485087 hasAuthorship W4311485087A5060431284 @default.
- W4311485087 hasConcept C11413529 @default.
- W4311485087 hasConcept C115961682 @default.
- W4311485087 hasConcept C121332964 @default.
- W4311485087 hasConcept C13280743 @default.
- W4311485087 hasConcept C138885662 @default.
- W4311485087 hasConcept C153180895 @default.
- W4311485087 hasConcept C154945302 @default.
- W4311485087 hasConcept C158525013 @default.
- W4311485087 hasConcept C168773036 @default.
- W4311485087 hasConcept C178790620 @default.
- W4311485087 hasConcept C185592680 @default.
- W4311485087 hasConcept C185798385 @default.
- W4311485087 hasConcept C205649164 @default.
- W4311485087 hasConcept C2524010 @default.
- W4311485087 hasConcept C2776401178 @default.
- W4311485087 hasConcept C2777210771 @default.
- W4311485087 hasConcept C2778755073 @default.
- W4311485087 hasConcept C2779227376 @default.
- W4311485087 hasConcept C33923547 @default.
- W4311485087 hasConcept C41008148 @default.
- W4311485087 hasConcept C41895202 @default.
- W4311485087 hasConcept C62520636 @default.
- W4311485087 hasConcept C81363708 @default.
- W4311485087 hasConceptScore W4311485087C11413529 @default.
- W4311485087 hasConceptScore W4311485087C115961682 @default.
- W4311485087 hasConceptScore W4311485087C121332964 @default.
- W4311485087 hasConceptScore W4311485087C13280743 @default.
- W4311485087 hasConceptScore W4311485087C138885662 @default.
- W4311485087 hasConceptScore W4311485087C153180895 @default.
- W4311485087 hasConceptScore W4311485087C154945302 @default.
- W4311485087 hasConceptScore W4311485087C158525013 @default.
- W4311485087 hasConceptScore W4311485087C168773036 @default.
- W4311485087 hasConceptScore W4311485087C178790620 @default.
- W4311485087 hasConceptScore W4311485087C185592680 @default.
- W4311485087 hasConceptScore W4311485087C185798385 @default.
- W4311485087 hasConceptScore W4311485087C205649164 @default.
- W4311485087 hasConceptScore W4311485087C2524010 @default.