Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964329030> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2964329030 endingPage "34" @default.
- W2964329030 startingPage "25" @default.
- W2964329030 abstract "Recent random-forest (RF)-based image super-resolution approaches inherit some properties from dictionary-learning-based algorithms, but the effectiveness of the features working in RF is overlooked in the literature. In this paper, we present a novel feature-augmented random forest (FARF) method for image super-resolution, where the conventional gradient-based features are proposed to augment the features used in RF, and different feature recipes are formulated on different processing stages in an RF. The advantages of our method are that, firstly, the dictionary-learning-based features are enhanced by adding gradient magnitudes, based on the observation that the non-linear gradient magnitudes are highly discriminative. Secondly, generalized locality-sensitive hashing (LSH) is used to replace principal component analysis (PCA) for feature dimensionality reduction in constructing the trees, but the original high-dimensional features are employed, instead of the compressed LSH features, for the leaf-nodes’ regressors. With the use of the original higher dimensional features, the regressors can achieve better learning performances. Finally, we present a generalized weighted ridge regression (GWRR) model for the leaf-nodes’ regressors. Experiment results on several public benchmark datasets show that our FARF method can achieve an average gain of about 0.3 dB, compared to traditional RF-based methods. Furthermore, a fine-tuned FARF model can compare to, or (in many cases) outperform, some recent state-of-the-art deep-learning-based algorithms." @default.
- W2964329030 created "2019-07-30" @default.
- W2964329030 creator A5000731922 @default.
- W2964329030 creator A5038928473 @default.
- W2964329030 creator A5080596209 @default.
- W2964329030 date "2019-03-01" @default.
- W2964329030 modified "2023-10-01" @default.
- W2964329030 title "Image super-resolution via feature-augmented random forest" @default.
- W2964329030 cites W1885185971 @default.
- W2964329030 cites W1972499291 @default.
- W2964329030 cites W1974647172 @default.
- W2964329030 cites W2097074225 @default.
- W2964329030 cites W2120240539 @default.
- W2964329030 cites W2121058967 @default.
- W2964329030 cites W2124378283 @default.
- W2964329030 cites W2157190232 @default.
- W2964329030 cites W2167706775 @default.
- W2964329030 cites W2172128189 @default.
- W2964329030 cites W2290061803 @default.
- W2964329030 cites W2509348655 @default.
- W2964329030 cites W2552983394 @default.
- W2964329030 cites W2911964244 @default.
- W2964329030 cites W2963774018 @default.
- W2964329030 cites W3123837026 @default.
- W2964329030 doi "https://doi.org/10.1016/j.image.2018.12.001" @default.
- W2964329030 hasPublicationYear "2019" @default.
- W2964329030 type Work @default.
- W2964329030 sameAs 2964329030 @default.
- W2964329030 citedByCount "10" @default.
- W2964329030 countsByYear W29643290302020 @default.
- W2964329030 countsByYear W29643290302021 @default.
- W2964329030 countsByYear W29643290302022 @default.
- W2964329030 crossrefType "journal-article" @default.
- W2964329030 hasAuthorship W2964329030A5000731922 @default.
- W2964329030 hasAuthorship W2964329030A5038928473 @default.
- W2964329030 hasAuthorship W2964329030A5080596209 @default.
- W2964329030 hasBestOaLocation W29643290302 @default.
- W2964329030 hasConcept C111030470 @default.
- W2964329030 hasConcept C119857082 @default.
- W2964329030 hasConcept C13280743 @default.
- W2964329030 hasConcept C138885662 @default.
- W2964329030 hasConcept C153180895 @default.
- W2964329030 hasConcept C154945302 @default.
- W2964329030 hasConcept C169258074 @default.
- W2964329030 hasConcept C185798385 @default.
- W2964329030 hasConcept C205649164 @default.
- W2964329030 hasConcept C27438332 @default.
- W2964329030 hasConcept C2776401178 @default.
- W2964329030 hasConcept C41008148 @default.
- W2964329030 hasConcept C41895202 @default.
- W2964329030 hasConcept C70518039 @default.
- W2964329030 hasConcept C97931131 @default.
- W2964329030 hasConceptScore W2964329030C111030470 @default.
- W2964329030 hasConceptScore W2964329030C119857082 @default.
- W2964329030 hasConceptScore W2964329030C13280743 @default.
- W2964329030 hasConceptScore W2964329030C138885662 @default.
- W2964329030 hasConceptScore W2964329030C153180895 @default.
- W2964329030 hasConceptScore W2964329030C154945302 @default.
- W2964329030 hasConceptScore W2964329030C169258074 @default.
- W2964329030 hasConceptScore W2964329030C185798385 @default.
- W2964329030 hasConceptScore W2964329030C205649164 @default.
- W2964329030 hasConceptScore W2964329030C27438332 @default.
- W2964329030 hasConceptScore W2964329030C2776401178 @default.
- W2964329030 hasConceptScore W2964329030C41008148 @default.
- W2964329030 hasConceptScore W2964329030C41895202 @default.
- W2964329030 hasConceptScore W2964329030C70518039 @default.
- W2964329030 hasConceptScore W2964329030C97931131 @default.
- W2964329030 hasFunder F4320321001 @default.
- W2964329030 hasFunder F4320325571 @default.
- W2964329030 hasLocation W29643290301 @default.
- W2964329030 hasLocation W29643290302 @default.
- W2964329030 hasOpenAccess W2964329030 @default.
- W2964329030 hasPrimaryLocation W29643290301 @default.
- W2964329030 hasRelatedWork W1510604416 @default.
- W2964329030 hasRelatedWork W1836423264 @default.
- W2964329030 hasRelatedWork W2010514871 @default.
- W2964329030 hasRelatedWork W2082691086 @default.
- W2964329030 hasRelatedWork W2144569930 @default.
- W2964329030 hasRelatedWork W2548999290 @default.
- W2964329030 hasRelatedWork W2790862734 @default.
- W2964329030 hasRelatedWork W2970216048 @default.
- W2964329030 hasRelatedWork W3130603810 @default.
- W2964329030 hasRelatedWork W4384695349 @default.
- W2964329030 hasVolume "72" @default.
- W2964329030 isParatext "false" @default.
- W2964329030 isRetracted "false" @default.
- W2964329030 magId "2964329030" @default.
- W2964329030 workType "article" @default.