Matches in SemOpenAlex for { <https://semopenalex.org/work/W4284694798> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W4284694798 endingPage "186" @default.
- W4284694798 startingPage "186" @default.
- W4284694798 abstract "Material classification is similar to texture classification and consists in predicting the material class of a surface in a color image, such as wood, metal, water, wool, or ceramic. It is very challenging because of the intra-class variability. Indeed, the visual appearance of a material is very sensitive to the acquisition conditions such as viewpoint or lighting conditions. Recent studies show that deep convolutional neural networks (CNNs) clearly outperform hand-crafted features in this context but suffer from a lack of data for training the models. In this paper, we propose two contributions to cope with this problem. First, we provide a new material dataset with a large range of acquisition conditions so that CNNs trained on these data can provide features that can adapt to the diverse appearances of the material samples encountered in real-world. Second, we leverage recent advances in multi-view learning methods to propose an original architecture designed to extract and combine features from several views of a single sample. We show that such multi-view CNNs significantly improve the performance of the classical alternatives for material classification." @default.
- W4284694798 created "2022-07-08" @default.
- W4284694798 creator A5005318650 @default.
- W4284694798 creator A5025451778 @default.
- W4284694798 creator A5041689611 @default.
- W4284694798 creator A5083014017 @default.
- W4284694798 date "2022-07-07" @default.
- W4284694798 modified "2023-09-26" @default.
- W4284694798 title "Multi-View Learning for Material Classification" @default.
- W4284694798 cites W1484228140 @default.
- W4284694798 cites W1499486838 @default.
- W4284694798 cites W2000123870 @default.
- W4284694798 cites W2020459435 @default.
- W4284694798 cites W2032533296 @default.
- W4284694798 cites W2049694710 @default.
- W4284694798 cites W2055302526 @default.
- W4284694798 cites W2059552065 @default.
- W4284694798 cites W2125148312 @default.
- W4284694798 cites W2153786187 @default.
- W4284694798 cites W2168239404 @default.
- W4284694798 cites W2171181782 @default.
- W4284694798 cites W2209359034 @default.
- W4284694798 cites W2524399695 @default.
- W4284694798 cites W2607603241 @default.
- W4284694798 cites W2731821979 @default.
- W4284694798 cites W2762701251 @default.
- W4284694798 cites W2811490555 @default.
- W4284694798 cites W2895238724 @default.
- W4284694798 cites W2897746180 @default.
- W4284694798 cites W2911315776 @default.
- W4284694798 cites W2915770592 @default.
- W4284694798 cites W3022018869 @default.
- W4284694798 cites W3088053178 @default.
- W4284694798 cites W3148388528 @default.
- W4284694798 cites W3195048299 @default.
- W4284694798 cites W3209967521 @default.
- W4284694798 cites W4213000285 @default.
- W4284694798 cites W4281631859 @default.
- W4284694798 doi "https://doi.org/10.3390/jimaging8070186" @default.
- W4284694798 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35877631" @default.
- W4284694798 hasPublicationYear "2022" @default.
- W4284694798 type Work @default.
- W4284694798 citedByCount "0" @default.
- W4284694798 crossrefType "journal-article" @default.
- W4284694798 hasAuthorship W4284694798A5005318650 @default.
- W4284694798 hasAuthorship W4284694798A5025451778 @default.
- W4284694798 hasAuthorship W4284694798A5041689611 @default.
- W4284694798 hasAuthorship W4284694798A5083014017 @default.
- W4284694798 hasBestOaLocation W42846947981 @default.
- W4284694798 hasConcept C108583219 @default.
- W4284694798 hasConcept C115961682 @default.
- W4284694798 hasConcept C119857082 @default.
- W4284694798 hasConcept C151730666 @default.
- W4284694798 hasConcept C153083717 @default.
- W4284694798 hasConcept C153180895 @default.
- W4284694798 hasConcept C154945302 @default.
- W4284694798 hasConcept C2777212361 @default.
- W4284694798 hasConcept C2779343474 @default.
- W4284694798 hasConcept C41008148 @default.
- W4284694798 hasConcept C75294576 @default.
- W4284694798 hasConcept C81363708 @default.
- W4284694798 hasConcept C86803240 @default.
- W4284694798 hasConceptScore W4284694798C108583219 @default.
- W4284694798 hasConceptScore W4284694798C115961682 @default.
- W4284694798 hasConceptScore W4284694798C119857082 @default.
- W4284694798 hasConceptScore W4284694798C151730666 @default.
- W4284694798 hasConceptScore W4284694798C153083717 @default.
- W4284694798 hasConceptScore W4284694798C153180895 @default.
- W4284694798 hasConceptScore W4284694798C154945302 @default.
- W4284694798 hasConceptScore W4284694798C2777212361 @default.
- W4284694798 hasConceptScore W4284694798C2779343474 @default.
- W4284694798 hasConceptScore W4284694798C41008148 @default.
- W4284694798 hasConceptScore W4284694798C75294576 @default.
- W4284694798 hasConceptScore W4284694798C81363708 @default.
- W4284694798 hasConceptScore W4284694798C86803240 @default.
- W4284694798 hasIssue "7" @default.
- W4284694798 hasLocation W42846947981 @default.
- W4284694798 hasLocation W42846947982 @default.
- W4284694798 hasLocation W42846947983 @default.
- W4284694798 hasLocation W42846947984 @default.
- W4284694798 hasOpenAccess W4284694798 @default.
- W4284694798 hasPrimaryLocation W42846947981 @default.
- W4284694798 hasRelatedWork W2470368200 @default.
- W4284694798 hasRelatedWork W2766604260 @default.
- W4284694798 hasRelatedWork W2912288872 @default.
- W4284694798 hasRelatedWork W2986507176 @default.
- W4284694798 hasRelatedWork W2996856019 @default.
- W4284694798 hasRelatedWork W3018421652 @default.
- W4284694798 hasRelatedWork W3160224718 @default.
- W4284694798 hasRelatedWork W3160711233 @default.
- W4284694798 hasRelatedWork W4220996320 @default.
- W4284694798 hasRelatedWork W4281780675 @default.
- W4284694798 hasVolume "8" @default.
- W4284694798 isParatext "false" @default.
- W4284694798 isRetracted "false" @default.
- W4284694798 workType "article" @default.