FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2990860243> ?p ?o ?g. }

• W2990860243 endingPage "173085" @default.
• W2990860243 startingPage "173076" @default.
• W2990860243 abstract "Filtering has been one of the main approaches to texture analysis since early on. Traditionally, the process involved designing the filters essentially by hand based on some prior knowledge (e.g. perceptual models, optimal mathematical properties, etc.) In this work we propose the use of convolutional networks for refactoring traditional, hand-designed filters. Our method consists of initialising the first convolutional layer of the network with some classic banks of filters, training the network on texture images and retrieve the modified filters. Experimenting with five classes of filters and eight datasets of texture images we show that the refactored filters can be conveniently used `off-the-shelf' to achieve better performance than obtained with the original filters, but at the same computational cost." @default.
• W2990860243 created "2019-12-05" @default.
• W2990860243 creator A5007465292 @default.
• W2990860243 creator A5028039581 @default.
• W2990860243 creator A5053344554 @default.
• W2990860243 creator A5039582068 @default.
• W2990860243 date "2019-01-01" @default.
• W2990860243 modified "2023-09-28" @default.
• W2990860243 title "CNN-Based Refactoring of Hand-Designed Filters for Texture Analysis: A Classic Revisited" @default.
• W2990860243 cites W1556206243 @default.
• W2990860243 cites W1853374870 @default.
• W2990860243 cites W1964010039 @default.
• W2990860243 cites W1966178163 @default.
• W2990860243 cites W1975858517 @default.
• W2990860243 cites W1988805924 @default.
• W2990860243 cites W2006500012 @default.
• W2990860243 cites W2018646465 @default.
• W2990860243 cites W2031614119 @default.
• W2990860243 cites W2054279472 @default.
• W2990860243 cites W2062118960 @default.
• W2990860243 cites W2063681017 @default.
• W2990860243 cites W2087806913 @default.
• W2990860243 cites W2089575713 @default.
• W2990860243 cites W2097946161 @default.
• W2990860243 cites W2098347925 @default.
• W2990860243 cites W2103220603 @default.
• W2990860243 cites W2107167693 @default.
• W2990860243 cites W2109779985 @default.
• W2990860243 cites W2125148312 @default.
• W2990860243 cites W2128880484 @default.
• W2990860243 cites W2152773182 @default.
• W2990860243 cites W2153786187 @default.
• W2990860243 cites W2177274842 @default.
• W2990860243 cites W2190008860 @default.
• W2990860243 cites W2316026218 @default.
• W2990860243 cites W2518260411 @default.
• W2990860243 cites W2576786845 @default.
• W2990860243 cites W2602768560 @default.
• W2990860243 cites W2766899523 @default.
• W2990860243 cites W2772814854 @default.
• W2990860243 cites W2895238724 @default.
• W2990860243 cites W2914464780 @default.
• W2990860243 cites W2915770592 @default.
• W2990860243 cites W2919115771 @default.
• W2990860243 cites W2935653880 @default.
• W2990860243 cites W2963239066 @default.
• W2990860243 cites W2963934397 @default.
• W2990860243 cites W3104037634 @default.
• W2990860243 cites W4230346359 @default.
• W2990860243 cites W4248277245 @default.
• W2990860243 cites W819977924 @default.
• W2990860243 cites W783453938 @default.
• W2990860243 doi "https://doi.org/10.1109/access.2019.2956863" @default.
• W2990860243 hasPublicationYear "2019" @default.
• W2990860243 type Work @default.
• W2990860243 sameAs 2990860243 @default.
• W2990860243 citedByCount "3" @default.
• W2990860243 countsByYear W29908602432021 @default.
• W2990860243 countsByYear W29908602432022 @default.
• W2990860243 crossrefType "journal-article" @default.
• W2990860243 hasAuthorship W2990860243A5007465292 @default.
• W2990860243 hasAuthorship W2990860243A5028039581 @default.
• W2990860243 hasAuthorship W2990860243A5039582068 @default.
• W2990860243 hasAuthorship W2990860243A5053344554 @default.
• W2990860243 hasBestOaLocation W29908602431 @default.
• W2990860243 hasConcept C115961682 @default.
• W2990860243 hasConcept C152752567 @default.
• W2990860243 hasConcept C153180895 @default.
• W2990860243 hasConcept C154945302 @default.
• W2990860243 hasConcept C199360897 @default.
• W2990860243 hasConcept C2777904410 @default.
• W2990860243 hasConcept C2781195486 @default.
• W2990860243 hasConcept C31972630 @default.
• W2990860243 hasConcept C41008148 @default.
• W2990860243 hasConcept C81363708 @default.
• W2990860243 hasConcept C98045186 @default.
• W2990860243 hasConceptScore W2990860243C115961682 @default.
• W2990860243 hasConceptScore W2990860243C152752567 @default.
• W2990860243 hasConceptScore W2990860243C153180895 @default.
• W2990860243 hasConceptScore W2990860243C154945302 @default.
• W2990860243 hasConceptScore W2990860243C199360897 @default.
• W2990860243 hasConceptScore W2990860243C2777904410 @default.
• W2990860243 hasConceptScore W2990860243C2781195486 @default.
• W2990860243 hasConceptScore W2990860243C31972630 @default.
• W2990860243 hasConceptScore W2990860243C41008148 @default.
• W2990860243 hasConceptScore W2990860243C81363708 @default.
• W2990860243 hasConceptScore W2990860243C98045186 @default.
• W2990860243 hasFunder F4320326523 @default.
• W2990860243 hasLocation W29908602431 @default.
• W2990860243 hasLocation W29908602432 @default.
• W2990860243 hasOpenAccess W2990860243 @default.
• W2990860243 hasPrimaryLocation W29908602431 @default.
• W2990860243 hasRelatedWork W1967418220 @default.
• W2990860243 hasRelatedWork W2175746458 @default.
• W2990860243 hasRelatedWork W2732542196 @default.
• W2990860243 hasRelatedWork W2738221750 @default.
• W2990860243 hasRelatedWork W2760085659 @default.
• W2990860243 hasRelatedWork W2883200793 @default.

• next