FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3000283449> ?p ?o ?g. }

• W3000283449 endingPage "4115" @default.
• W3000283449 startingPage "4099" @default.
• W3000283449 abstract "Remote-sensing images (RSIs) generally have strong spatial characteristics for surface features. Various ground objects, such as residential areas, roads, forests, and rivers, differ substantially. According to this visual attention characteristic, regions with complicated texture features require more realistic details to reflect a better description of the topography, while regions such as farmlands should be smooth and have less noise. However, most existing single-image superresolution (SISR) methods fail to fully utilize these properties and therefore apply a uniform reconstruction strategy to the whole image. In this article, we propose a novel saliency-driven unequal single-image reconstruction network in which the demands of various regions in the superresolution (SR) process are distinguished by saliency maps. First, we design a new gradient-based saliency analysis method to produce more accurate saliency maps with imagewise annotations. The method utilizes the superiority of a multireception field to extract both high-level features and low-level features. Second, we propose a novel saliency-driven gate conditional generative adversarial network, where the saliency map is regarded as a medium during the training procedure of the whole network. The saliency map is regarded as a pixelwise condition in a generator to enhance the training capability of the network. Additionally, we design a new loss function that combines normalized content loss, saliency-driven perceptual loss, and gate-control adversarial loss to further refine details of texture-complex areas for RSIs. We evaluate the performance of our algorithm and compare it with many other state-of-the-art SR methods using a remote-sensing data set. The experimental results show that our approach achieves the optimal outcome in salient areas. Our method attains the best effect on global quality and visual performance." @default.
• W3000283449 created "2020-01-23" @default.
• W3000283449 creator A5047572962 @default.
• W3000283449 creator A5054549272 @default.
• W3000283449 creator A5059828502 @default.
• W3000283449 creator A5087779583 @default.
• W3000283449 date "2020-06-01" @default.
• W3000283449 modified "2023-10-17" @default.
• W3000283449 title "Remote-Sensing Image Superresolution Based on Visual Saliency Analysis and Unequal Reconstruction Networks" @default.
• W3000283449 cites W135113724 @default.
• W3000283449 cites W1885185971 @default.
• W3000283449 cites W1923749858 @default.
• W3000283449 cites W1930824406 @default.
• W3000283449 cites W1934184906 @default.
• W3000283449 cites W1990690548 @default.
• W3000283449 cites W2011503804 @default.
• W3000283449 cites W2023075239 @default.
• W3000283449 cites W2036477522 @default.
• W3000283449 cites W2049352069 @default.
• W3000283449 cites W2058523468 @default.
• W3000283449 cites W2087380704 @default.
• W3000283449 cites W2096455981 @default.
• W3000283449 cites W2097074225 @default.
• W3000283449 cites W2102605133 @default.
• W3000283449 cites W2106913527 @default.
• W3000283449 cites W2115548755 @default.
• W3000283449 cites W2117998419 @default.
• W3000283449 cites W2121058967 @default.
• W3000283449 cites W2123886106 @default.
• W3000283449 cites W2128272608 @default.
• W3000283449 cites W2131659181 @default.
• W3000283449 cites W2141066969 @default.
• W3000283449 cites W2149669120 @default.
• W3000283449 cites W2151789205 @default.
• W3000283449 cites W2167635673 @default.
• W3000283449 cites W2194775991 @default.
• W3000283449 cites W2214802144 @default.
• W3000283449 cites W2242218935 @default.
• W3000283449 cites W2331128040 @default.
• W3000283449 cites W2331427273 @default.
• W3000283449 cites W2395611524 @default.
• W3000283449 cites W2476548250 @default.
• W3000283449 cites W2503140068 @default.
• W3000283449 cites W2538244214 @default.
• W3000283449 cites W2552955500 @default.
• W3000283449 cites W2588000623 @default.
• W3000283449 cites W2597117158 @default.
• W3000283449 cites W2618530766 @default.
• W3000283449 cites W2621121458 @default.
• W3000283449 cites W2626606351 @default.
• W3000283449 cites W2664380602 @default.
• W3000283449 cites W2735165202 @default.
• W3000283449 cites W2744690378 @default.
• W3000283449 cites W2753754894 @default.
• W3000283449 cites W2768814045 @default.
• W3000283449 cites W2770525455 @default.
• W3000283449 cites W2774112877 @default.
• W3000283449 cites W2793613573 @default.
• W3000283449 cites W2793865950 @default.
• W3000283449 cites W2794531502 @default.
• W3000283449 cites W2808442315 @default.
• W3000283449 cites W2963037581 @default.
• W3000283449 cites W2963470893 @default.
• W3000283449 cites W2964114039 @default.
• W3000283449 doi "https://doi.org/10.1109/tgrs.2019.2960781" @default.
• W3000283449 hasPublicationYear "2020" @default.
• W3000283449 type Work @default.
• W3000283449 sameAs 3000283449 @default.
• W3000283449 citedByCount "8" @default.
• W3000283449 countsByYear W30002834492021 @default.
• W3000283449 countsByYear W30002834492022 @default.
• W3000283449 crossrefType "journal-article" @default.
• W3000283449 hasAuthorship W3000283449A5047572962 @default.
• W3000283449 hasAuthorship W3000283449A5054549272 @default.
• W3000283449 hasAuthorship W3000283449A5059828502 @default.
• W3000283449 hasAuthorship W3000283449A5087779583 @default.
• W3000283449 hasConcept C111919701 @default.
• W3000283449 hasConcept C115961682 @default.
• W3000283449 hasConcept C121332964 @default.
• W3000283449 hasConcept C127313418 @default.
• W3000283449 hasConcept C153180895 @default.
• W3000283449 hasConcept C154945302 @default.
• W3000283449 hasConcept C163258240 @default.
• W3000283449 hasConcept C205372480 @default.
• W3000283449 hasConcept C2780992000 @default.
• W3000283449 hasConcept C31972630 @default.
• W3000283449 hasConcept C36464697 @default.
• W3000283449 hasConcept C41008148 @default.
• W3000283449 hasConcept C62520636 @default.
• W3000283449 hasConcept C62649853 @default.
• W3000283449 hasConcept C98045186 @default.
• W3000283449 hasConcept C99498987 @default.
• W3000283449 hasConceptScore W3000283449C111919701 @default.
• W3000283449 hasConceptScore W3000283449C115961682 @default.
• W3000283449 hasConceptScore W3000283449C121332964 @default.
• W3000283449 hasConceptScore W3000283449C127313418 @default.
• W3000283449 hasConceptScore W3000283449C153180895 @default.
• W3000283449 hasConceptScore W3000283449C154945302 @default.

• next