Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382393357> ?p ?o ?g. }
- W4382393357 endingPage "46003" @default.
- W4382393357 startingPage "45989" @default.
- W4382393357 abstract "Recent research on image and video processing using convolutional neural networks has shown remarkable improvements, especially in the area of single image super-resolution(SISR). The primary target of SISR is to recover the visually appealing high-resolution (HR) output image from the original degraded low-resolution (LR) input image. However, most recent convolutional neural networks (CNNs)-based image super-resolution frameworks often used a deeper and broader network architecture that requires a sizeable computational resource, risk of overfitting, increases computational complexity, and more memory consumption, as well as takes more processing time during the evaluations. To address these issues, we have presented a Squeeze-and-ExcitationNext for Single Image Super-Resolution approach, known as SENext. In brief, the squeeze-and-excitation blocks (SEB) are used in our network architecture with a view to reduce the computational cost and adopt the channel-wise feature mappings to recalibrate the features adaptively. Furthermore, local, sub-local, and global skip connections are employed between each SEB to enable the feature reusability and stabilize training convergence smoothly. Instead of hand-designed bicubic upsampling at pre-processing step, we have performed post-upsampling at the later stage to reconstruct the high-resolution image. Extensive quantitative and qualitative experiments are performed on the benchmark test dataset, including Set5, Set14, BSDS100, Urban100, and Manga109. These experimental evaluations validate the superiority of the SENext over other deep CNN image SR methods in terms of PSNR/SSIM, FLOPs, Number of parameters, processing speed, and visually pleasing effect." @default.
- W4382393357 created "2023-06-29" @default.
- W4382393357 creator A5011130748 @default.
- W4382393357 creator A5061693379 @default.
- W4382393357 creator A5069698375 @default.
- W4382393357 date "2023-01-01" @default.
- W4382393357 modified "2023-10-01" @default.
- W4382393357 title "SENext: Squeeze-and-ExcitationNext for Single Image Super-Resolution" @default.
- W4382393357 cites W1677182931 @default.
- W4382393357 cites W1885185971 @default.
- W4382393357 cites W1919542679 @default.
- W4382393357 cites W1930824406 @default.
- W4382393357 cites W1950594372 @default.
- W4382393357 cites W2047920195 @default.
- W4382393357 cites W2097117768 @default.
- W4382393357 cites W2098506229 @default.
- W4382393357 cites W2110158442 @default.
- W4382393357 cites W2121058967 @default.
- W4382393357 cites W2192954843 @default.
- W4382393357 cites W2194775991 @default.
- W4382393357 cites W2214802144 @default.
- W4382393357 cites W2242218935 @default.
- W4382393357 cites W2417716951 @default.
- W4382393357 cites W2476548250 @default.
- W4382393357 cites W2503339013 @default.
- W4382393357 cites W2508457857 @default.
- W4382393357 cites W2607041014 @default.
- W4382393357 cites W2741137940 @default.
- W4382393357 cites W2747898905 @default.
- W4382393357 cites W2752782242 @default.
- W4382393357 cites W2767022844 @default.
- W4382393357 cites W2795024892 @default.
- W4382393357 cites W2799120945 @default.
- W4382393357 cites W2866634454 @default.
- W4382393357 cites W2895598217 @default.
- W4382393357 cites W2914107945 @default.
- W4382393357 cites W2917154014 @default.
- W4382393357 cites W2944845825 @default.
- W4382393357 cites W2962595906 @default.
- W4382393357 cites W2963103155 @default.
- W4382393357 cites W2963372104 @default.
- W4382393357 cites W2963470893 @default.
- W4382393357 cites W2963620158 @default.
- W4382393357 cites W2963645458 @default.
- W4382393357 cites W2963966343 @default.
- W4382393357 cites W2964125708 @default.
- W4382393357 cites W2964277374 @default.
- W4382393357 cites W2967788068 @default.
- W4382393357 cites W2968222299 @default.
- W4382393357 cites W2974942297 @default.
- W4382393357 cites W2974995978 @default.
- W4382393357 cites W2980464766 @default.
- W4382393357 cites W2998879648 @default.
- W4382393357 cites W3010092235 @default.
- W4382393357 cites W3040726448 @default.
- W4382393357 cites W3091809802 @default.
- W4382393357 cites W3105328221 @default.
- W4382393357 cites W3195836789 @default.
- W4382393357 cites W4210813666 @default.
- W4382393357 cites W4280527875 @default.
- W4382393357 cites W4281670300 @default.
- W4382393357 cites W4281758536 @default.
- W4382393357 cites W4299396942 @default.
- W4382393357 cites W4313546871 @default.
- W4382393357 doi "https://doi.org/10.1109/access.2023.3274679" @default.
- W4382393357 hasPublicationYear "2023" @default.
- W4382393357 type Work @default.
- W4382393357 citedByCount "1" @default.
- W4382393357 countsByYear W43823933572023 @default.
- W4382393357 crossrefType "journal-article" @default.
- W4382393357 hasAuthorship W4382393357A5011130748 @default.
- W4382393357 hasAuthorship W4382393357A5061693379 @default.
- W4382393357 hasAuthorship W4382393357A5069698375 @default.
- W4382393357 hasBestOaLocation W43823933571 @default.
- W4382393357 hasConcept C110384440 @default.
- W4382393357 hasConcept C11413529 @default.
- W4382393357 hasConcept C115961682 @default.
- W4382393357 hasConcept C13280743 @default.
- W4382393357 hasConcept C138885662 @default.
- W4382393357 hasConcept C153180895 @default.
- W4382393357 hasConcept C154945302 @default.
- W4382393357 hasConcept C171836373 @default.
- W4382393357 hasConcept C179799912 @default.
- W4382393357 hasConcept C185798385 @default.
- W4382393357 hasConcept C205372480 @default.
- W4382393357 hasConcept C205649164 @default.
- W4382393357 hasConcept C22019652 @default.
- W4382393357 hasConcept C2776401178 @default.
- W4382393357 hasConcept C31972630 @default.
- W4382393357 hasConcept C41008148 @default.
- W4382393357 hasConcept C41895202 @default.
- W4382393357 hasConcept C45347329 @default.
- W4382393357 hasConcept C49608258 @default.
- W4382393357 hasConcept C50644808 @default.
- W4382393357 hasConcept C81363708 @default.
- W4382393357 hasConcept C9417928 @default.
- W4382393357 hasConceptScore W4382393357C110384440 @default.
- W4382393357 hasConceptScore W4382393357C11413529 @default.