FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3160499679> ?p ?o ?g. }

• W3160499679 endingPage "1284" @default.
• W3160499679 startingPage "1273" @default.
• W3160499679 abstract "In recent years, with the rapid development of deep learning, super-resolution methods based on convolutional neural networks (CNNs) have made great progress. However, the parameters and the required consumption of computing resources of these methods are also increasing to the point that such methods are difficult to implement on devices with low computing power. To address this issue, we propose a lightweight single image super-resolution network with an expectation-maximization attention mechanism (EMASRN) for better balancing performance and applicability. Specifically, a progressive multi-scale feature extraction block (PMSFE) is proposed to extract feature maps of different sizes. Furthermore, we propose an HR-size expectation-maximization attention block (HREMAB) that directly captures the long-range dependencies of HR-size feature maps. We also utilize a feedback network to feed the high-level features of each generation into the next generation&#x2019;s shallow network. Compared with the existing lightweight single image super-resolution (SISR) methods, our EMASRN reduces the number of parameters by almost one-third. The experimental results demonstrate the superiority of our EMASRN over state-of-the-art lightweight SISR methods in terms of both quantitative metrics and visual quality. The source code can be downloaded at <uri>https://github.com/xyzhu1/EMASRN</uri>." @default.
• W3160499679 created "2021-05-24" @default.
• W3160499679 creator A5035867023 @default.
• W3160499679 creator A5038696152 @default.
• W3160499679 creator A5046565976 @default.
• W3160499679 creator A5060879177 @default.
• W3160499679 creator A5083510126 @default.
• W3160499679 creator A5083529162 @default.
• W3160499679 date "2022-03-01" @default.
• W3160499679 modified "2023-10-16" @default.
• W3160499679 title "Lightweight Image Super-Resolution With Expectation-Maximization Attention Mechanism" @default.
• W3160499679 cites W1885185971 @default.
• W3160499679 cites W1985806826 @default.
• W3160499679 cites W2016598597 @default.
• W3160499679 cites W2088869937 @default.
• W3160499679 cites W2096455981 @default.
• W3160499679 cites W2107461197 @default.
• W3160499679 cites W2138714160 @default.
• W3160499679 cites W2194775991 @default.
• W3160499679 cites W2214802144 @default.
• W3160499679 cites W2242218935 @default.
• W3160499679 cites W2263468737 @default.
• W3160499679 cites W2476548250 @default.
• W3160499679 cites W2503458650 @default.
• W3160499679 cites W2607041014 @default.
• W3160499679 cites W2739815012 @default.
• W3160499679 cites W2740139074 @default.
• W3160499679 cites W2741137940 @default.
• W3160499679 cites W2747898905 @default.
• W3160499679 cites W2752782242 @default.
• W3160499679 cites W2780544323 @default.
• W3160499679 cites W2789370848 @default.
• W3160499679 cites W2795024892 @default.
• W3160499679 cites W2795087793 @default.
• W3160499679 cites W2804708059 @default.
• W3160499679 cites W2896155169 @default.
• W3160499679 cites W2903417465 @default.
• W3160499679 cites W2907226170 @default.
• W3160499679 cites W2923898639 @default.
• W3160499679 cites W2954930822 @default.
• W3160499679 cites W2956891660 @default.
• W3160499679 cites W2962818016 @default.
• W3160499679 cites W2963091558 @default.
• W3160499679 cites W2963372104 @default.
• W3160499679 cites W2963610452 @default.
• W3160499679 cites W2963729050 @default.
• W3160499679 cites W2963782415 @default.
• W3160499679 cites W2963986095 @default.
• W3160499679 cites W2964101377 @default.
• W3160499679 cites W2964125708 @default.
• W3160499679 cites W2964277374 @default.
• W3160499679 cites W2964309882 @default.
• W3160499679 cites W2986556279 @default.
• W3160499679 cites W2993235622 @default.
• W3160499679 cites W2998341422 @default.
• W3160499679 cites W3018586778 @default.
• W3160499679 cites W3035280441 @default.
• W3160499679 cites W3035750285 @default.
• W3160499679 cites W3092031931 @default.
• W3160499679 cites W4255779515 @default.
• W3160499679 doi "https://doi.org/10.1109/tcsvt.2021.3078436" @default.
• W3160499679 hasPublicationYear "2022" @default.
• W3160499679 type Work @default.
• W3160499679 sameAs 3160499679 @default.
• W3160499679 citedByCount "50" @default.
• W3160499679 countsByYear W31604996792021 @default.
• W3160499679 countsByYear W31604996792022 @default.
• W3160499679 countsByYear W31604996792023 @default.
• W3160499679 crossrefType "journal-article" @default.
• W3160499679 hasAuthorship W3160499679A5035867023 @default.
• W3160499679 hasAuthorship W3160499679A5038696152 @default.
• W3160499679 hasAuthorship W3160499679A5046565976 @default.
• W3160499679 hasAuthorship W3160499679A5060879177 @default.
• W3160499679 hasAuthorship W3160499679A5083510126 @default.
• W3160499679 hasAuthorship W3160499679A5083529162 @default.
• W3160499679 hasBestOaLocation W31604996792 @default.
• W3160499679 hasConcept C105795698 @default.
• W3160499679 hasConcept C108583219 @default.
• W3160499679 hasConcept C111919701 @default.
• W3160499679 hasConcept C115961682 @default.
• W3160499679 hasConcept C124101348 @default.
• W3160499679 hasConcept C138885662 @default.
• W3160499679 hasConcept C153180895 @default.
• W3160499679 hasConcept C154945302 @default.
• W3160499679 hasConcept C162324750 @default.
• W3160499679 hasConcept C175444787 @default.
• W3160499679 hasConcept C177264268 @default.
• W3160499679 hasConcept C182081679 @default.
• W3160499679 hasConcept C199360897 @default.
• W3160499679 hasConcept C205372480 @default.
• W3160499679 hasConcept C2524010 @default.
• W3160499679 hasConcept C2776330181 @default.
• W3160499679 hasConcept C2776401178 @default.
• W3160499679 hasConcept C2776760102 @default.
• W3160499679 hasConcept C2777210771 @default.
• W3160499679 hasConcept C33923547 @default.
• W3160499679 hasConcept C41008148 @default.
• W3160499679 hasConcept C41895202 @default.

• next