Matches in SemOpenAlex for { <https://semopenalex.org/work/W2996549879> ?p ?o ?g. }
- W2996549879 endingPage "120" @default.
- W2996549879 startingPage "116" @default.
- W2996549879 abstract "Texture segmentation is about dividing a texture-dominant image into multiple homogeneous texture regions. The existing unsupervised approaches for texture segmentation are annotation-free but often yield unsatisfactory results. In contrast, supervised approaches such as deep learning may have better performance but require a large amount of annotated data. In this letter, we propose a user-interactive approach to win the trade-off between unsupervised approaches and supervised deep approaches. Our approach requires the user to mark one pixel in each texture region, whose label is directly propagated to its neighbor region. Such labeled data are of very small amount and even partially erroneous. To effectively exploit such weakly-labeled data, we construct a weakly-supervised sparse coding model that jointly conducts feature learning and segmentation. In addition, the geometric constraints are developed for the model to exploit the geometric prior on the local connectivity of region boundaries. The experiments on two benchmark datasets have validated the effectiveness of the proposed approach." @default.
- W2996549879 created "2019-12-26" @default.
- W2996549879 creator A5038130835 @default.
- W2996549879 creator A5038244978 @default.
- W2996549879 creator A5053838315 @default.
- W2996549879 creator A5057402960 @default.
- W2996549879 date "2020-01-01" @default.
- W2996549879 modified "2023-10-17" @default.
- W2996549879 title "Weakly-Supervised Sparse Coding With Geometric Prior for Interactive Texture Segmentation" @default.
- W2996549879 cites W1603679155 @default.
- W2996549879 cites W1839839900 @default.
- W2996549879 cites W1963932623 @default.
- W2996549879 cites W1965891643 @default.
- W2996549879 cites W1982513269 @default.
- W2996549879 cites W1993269503 @default.
- W2996549879 cites W2015212546 @default.
- W2996549879 cites W2016838474 @default.
- W2996549879 cites W2027805700 @default.
- W2996549879 cites W2048153049 @default.
- W2996549879 cites W2049694710 @default.
- W2996549879 cites W2054118750 @default.
- W2996549879 cites W2062287009 @default.
- W2996549879 cites W2079502224 @default.
- W2996549879 cites W2100902416 @default.
- W2996549879 cites W2121926901 @default.
- W2996549879 cites W2128659236 @default.
- W2996549879 cites W2136893771 @default.
- W2996549879 cites W2145605942 @default.
- W2996549879 cites W2160547390 @default.
- W2996549879 cites W2168793726 @default.
- W2996549879 cites W2403161956 @default.
- W2996549879 cites W2415447328 @default.
- W2996549879 cites W2793444752 @default.
- W2996549879 cites W2940029407 @default.
- W2996549879 cites W2963428042 @default.
- W2996549879 cites W2963803174 @default.
- W2996549879 cites W3103811167 @default.
- W2996549879 cites W1969993007 @default.
- W2996549879 doi "https://doi.org/10.1109/lsp.2019.2959225" @default.
- W2996549879 hasPublicationYear "2020" @default.
- W2996549879 type Work @default.
- W2996549879 sameAs 2996549879 @default.
- W2996549879 citedByCount "4" @default.
- W2996549879 countsByYear W29965498792021 @default.
- W2996549879 countsByYear W29965498792022 @default.
- W2996549879 crossrefType "journal-article" @default.
- W2996549879 hasAuthorship W2996549879A5038130835 @default.
- W2996549879 hasAuthorship W2996549879A5038244978 @default.
- W2996549879 hasAuthorship W2996549879A5053838315 @default.
- W2996549879 hasAuthorship W2996549879A5057402960 @default.
- W2996549879 hasConcept C105795698 @default.
- W2996549879 hasConcept C124504099 @default.
- W2996549879 hasConcept C13280743 @default.
- W2996549879 hasConcept C138885662 @default.
- W2996549879 hasConcept C153180895 @default.
- W2996549879 hasConcept C154945302 @default.
- W2996549879 hasConcept C165696696 @default.
- W2996549879 hasConcept C179518139 @default.
- W2996549879 hasConcept C185798385 @default.
- W2996549879 hasConcept C205649164 @default.
- W2996549879 hasConcept C2776401178 @default.
- W2996549879 hasConcept C31972630 @default.
- W2996549879 hasConcept C33923547 @default.
- W2996549879 hasConcept C38652104 @default.
- W2996549879 hasConcept C41008148 @default.
- W2996549879 hasConcept C41895202 @default.
- W2996549879 hasConcept C63099799 @default.
- W2996549879 hasConcept C77637269 @default.
- W2996549879 hasConcept C89600930 @default.
- W2996549879 hasConceptScore W2996549879C105795698 @default.
- W2996549879 hasConceptScore W2996549879C124504099 @default.
- W2996549879 hasConceptScore W2996549879C13280743 @default.
- W2996549879 hasConceptScore W2996549879C138885662 @default.
- W2996549879 hasConceptScore W2996549879C153180895 @default.
- W2996549879 hasConceptScore W2996549879C154945302 @default.
- W2996549879 hasConceptScore W2996549879C165696696 @default.
- W2996549879 hasConceptScore W2996549879C179518139 @default.
- W2996549879 hasConceptScore W2996549879C185798385 @default.
- W2996549879 hasConceptScore W2996549879C205649164 @default.
- W2996549879 hasConceptScore W2996549879C2776401178 @default.
- W2996549879 hasConceptScore W2996549879C31972630 @default.
- W2996549879 hasConceptScore W2996549879C33923547 @default.
- W2996549879 hasConceptScore W2996549879C38652104 @default.
- W2996549879 hasConceptScore W2996549879C41008148 @default.
- W2996549879 hasConceptScore W2996549879C41895202 @default.
- W2996549879 hasConceptScore W2996549879C63099799 @default.
- W2996549879 hasConceptScore W2996549879C77637269 @default.
- W2996549879 hasConceptScore W2996549879C89600930 @default.
- W2996549879 hasFunder F4320321001 @default.
- W2996549879 hasFunder F4320321543 @default.
- W2996549879 hasFunder F4320321921 @default.
- W2996549879 hasFunder F4320335787 @default.
- W2996549879 hasLocation W29965498791 @default.
- W2996549879 hasOpenAccess W2996549879 @default.
- W2996549879 hasPrimaryLocation W29965498791 @default.
- W2996549879 hasRelatedWork W10029978 @default.
- W2996549879 hasRelatedWork W106659 @default.
- W2996549879 hasRelatedWork W11341248 @default.