Matches in SemOpenAlex for { <https://semopenalex.org/work/W2980581567> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2980581567 endingPage "243" @default.
- W2980581567 startingPage "232" @default.
- W2980581567 abstract "Abstract Low-rank matrix recovery (LRMR) has recently been applied to saliency detection by decomposing image features into a low-rank component associated with background and a sparse component associated with visual salient regions. Despite its great potential, existing LRMR-based saliency detection methods seldom consider the inter-relationship among elements within these two components, thus are prone to generating scattered or incomplete saliency maps. In this paper, we introduce a novel and efficient LRMR-based saliency detection model under a coarse-to-fine framework to circumvent this limitation. First, we roughly measure the saliency of image regions with a baseline LRMR model that integrates a l1-norm sparsity constraint and a Laplacian regularization smooth term. Given samples from the coarse saliency map, we then learn a projection that maps image features to refined saliency values, to significantly sharpen the object boundaries and to preserve the object entirety. We evaluate our framework against existing LRMR-based methods on three benchmark datasets. Experimental results validate the superiority of our method as well as the effectiveness of our suggested coarse-to-fine framework, especially for images containing multiple objects. MATLAB code for implementing our method is available at https://github.com/qizhust/HLRSaliency ." @default.
- W2980581567 created "2019-10-25" @default.
- W2980581567 creator A5031064868 @default.
- W2980581567 creator A5041358503 @default.
- W2980581567 creator A5057095711 @default.
- W2980581567 date "2020-02-01" @default.
- W2980581567 modified "2023-09-24" @default.
- W2980581567 title "Coarse-to-fine salient object detection with low-rank matrix recovery" @default.
- W2980581567 cites W1978904636 @default.
- W2980581567 cites W2037328649 @default.
- W2980581567 cites W2039920533 @default.
- W2980581567 cites W2041719651 @default.
- W2980581567 cites W2087509227 @default.
- W2980581567 cites W2108564850 @default.
- W2980581567 cites W2109200236 @default.
- W2980581567 cites W2114542651 @default.
- W2980581567 cites W2118246710 @default.
- W2980581567 cites W2128272608 @default.
- W2980581567 cites W2142470670 @default.
- W2980581567 cites W2145962650 @default.
- W2980581567 cites W2152233525 @default.
- W2980581567 cites W2156686129 @default.
- W2980581567 cites W2160398355 @default.
- W2980581567 cites W2164084182 @default.
- W2980581567 cites W2176101330 @default.
- W2980581567 cites W2346506533 @default.
- W2980581567 cites W2610921592 @default.
- W2980581567 cites W2745691012 @default.
- W2980581567 cites W2765161239 @default.
- W2980581567 cites W2855111893 @default.
- W2980581567 cites W2897432612 @default.
- W2980581567 cites W3104979525 @default.
- W2980581567 cites W3125520697 @default.
- W2980581567 cites W4239147634 @default.
- W2980581567 doi "https://doi.org/10.1016/j.neucom.2019.08.091" @default.
- W2980581567 hasPublicationYear "2020" @default.
- W2980581567 type Work @default.
- W2980581567 sameAs 2980581567 @default.
- W2980581567 citedByCount "7" @default.
- W2980581567 countsByYear W29805815672020 @default.
- W2980581567 countsByYear W29805815672021 @default.
- W2980581567 crossrefType "journal-article" @default.
- W2980581567 hasAuthorship W2980581567A5031064868 @default.
- W2980581567 hasAuthorship W2980581567A5041358503 @default.
- W2980581567 hasAuthorship W2980581567A5057095711 @default.
- W2980581567 hasBestOaLocation W29805815672 @default.
- W2980581567 hasConcept C106487976 @default.
- W2980581567 hasConcept C114614502 @default.
- W2980581567 hasConcept C153180895 @default.
- W2980581567 hasConcept C154945302 @default.
- W2980581567 hasConcept C164226766 @default.
- W2980581567 hasConcept C185592680 @default.
- W2980581567 hasConcept C2780719617 @default.
- W2980581567 hasConcept C2781238097 @default.
- W2980581567 hasConcept C31972630 @default.
- W2980581567 hasConcept C33923547 @default.
- W2980581567 hasConcept C41008148 @default.
- W2980581567 hasConcept C43617362 @default.
- W2980581567 hasConceptScore W2980581567C106487976 @default.
- W2980581567 hasConceptScore W2980581567C114614502 @default.
- W2980581567 hasConceptScore W2980581567C153180895 @default.
- W2980581567 hasConceptScore W2980581567C154945302 @default.
- W2980581567 hasConceptScore W2980581567C164226766 @default.
- W2980581567 hasConceptScore W2980581567C185592680 @default.
- W2980581567 hasConceptScore W2980581567C2780719617 @default.
- W2980581567 hasConceptScore W2980581567C2781238097 @default.
- W2980581567 hasConceptScore W2980581567C31972630 @default.
- W2980581567 hasConceptScore W2980581567C33923547 @default.
- W2980581567 hasConceptScore W2980581567C41008148 @default.
- W2980581567 hasConceptScore W2980581567C43617362 @default.
- W2980581567 hasFunder F4320321001 @default.
- W2980581567 hasLocation W29805815671 @default.
- W2980581567 hasLocation W29805815672 @default.
- W2980581567 hasOpenAccess W2980581567 @default.
- W2980581567 hasPrimaryLocation W29805815671 @default.
- W2980581567 hasRelatedWork W1632853819 @default.
- W2980581567 hasRelatedWork W1837097281 @default.
- W2980581567 hasRelatedWork W1966410754 @default.
- W2980581567 hasRelatedWork W2007544051 @default.
- W2980581567 hasRelatedWork W2016398835 @default.
- W2980581567 hasRelatedWork W2328068029 @default.
- W2980581567 hasRelatedWork W2363840281 @default.
- W2980581567 hasRelatedWork W2536452361 @default.
- W2980581567 hasRelatedWork W2607572884 @default.
- W2980581567 hasRelatedWork W2975200075 @default.
- W2980581567 hasVolume "376" @default.
- W2980581567 isParatext "false" @default.
- W2980581567 isRetracted "false" @default.
- W2980581567 magId "2980581567" @default.
- W2980581567 workType "article" @default.