FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950867030> ?p ?o ?g. }

• W2950867030 abstract "Image saliency detection has recently witnessed rapid progress due to deep convolutional neural networks. However, none of the existing methods is able to identify object instances in the detected salient regions. In this paper, we present a salient instance segmentation method that produces a saliency mask with distinct object instance labels for an input image. Our method consists of three steps, estimating saliency map, detecting salient object contours and identifying salient object instances. For the first two steps, we propose a multiscale saliency refinement network, which generates high-quality salient region masks and salient object contours. Once integrated with multiscale combinatorial grouping and a MAP-based subset optimization framework, our method can generate very promising salient object instance segmentation results. To promote further research and evaluation of salient instance segmentation, we also construct a new database of 1000 images and their pixelwise salient instance annotations. Experimental results demonstrate that our proposed method is capable of achieving state-of-the-art performance on all public benchmarks for salient region detection as well as on our new dataset for salient instance segmentation." @default.
• W2950867030 created "2019-06-27" @default.
• W2950867030 creator A5042965510 @default.
• W2950867030 creator A5058965019 @default.
• W2950867030 creator A5071959906 @default.
• W2950867030 creator A5082076121 @default.
• W2950867030 date "2017-04-11" @default.
• W2950867030 modified "2023-10-16" @default.
• W2950867030 title "Instance-Level Salient Object Segmentation" @default.
• W2950867030 cites W1483870316 @default.
• W2950867030 cites W1567302070 @default.
• W2950867030 cites W1850742715 @default.
• W2950867030 cites W1905882502 @default.
• W2950867030 cites W1930528368 @default.
• W2950867030 cites W1942214758 @default.
• W2950867030 cites W1947031653 @default.
• W2950867030 cites W1991367009 @default.
• W2950867030 cites W1996326832 @default.
• W2950867030 cites W2002781701 @default.
• W2950867030 cites W2006180404 @default.
• W2950867030 cites W2018377917 @default.
• W2950867030 cites W2022508996 @default.
• W2950867030 cites W2037954058 @default.
• W2950867030 cites W2039313011 @default.
• W2950867030 cites W2041719651 @default.
• W2950867030 cites W2065372998 @default.
• W2950867030 cites W2086791339 @default.
• W2950867030 cites W2090463878 @default.
• W2950867030 cites W2100470808 @default.
• W2950867030 cites W2110158442 @default.
• W2950867030 cites W2121927366 @default.
• W2950867030 cites W2129305389 @default.
• W2950867030 cites W2145227859 @default.
• W2950867030 cites W2158865742 @default.
• W2950867030 cites W2158983298 @default.
• W2950867030 cites W2161185676 @default.
• W2950867030 cites W2175975598 @default.
• W2950867030 cites W2194775991 @default.
• W2950867030 cites W2422471819 @default.
• W2950867030 cites W2461475918 @default.
• W2950867030 cites W2474876375 @default.
• W2950867030 cites W2519528544 @default.
• W2950867030 cites W2607333215 @default.
• W2950867030 cites W2888232411 @default.
• W2950867030 cites W2949295283 @default.
• W2950867030 cites W2949370174 @default.
• W2950867030 cites W2950094539 @default.
• W2950867030 cites W2950622378 @default.
• W2950867030 cites W2950931866 @default.
• W2950867030 cites W2950981687 @default.
• W2950867030 cites W2951120635 @default.
• W2950867030 cites W2951548327 @default.
• W2950867030 cites W2951713345 @default.
• W2950867030 cites W2952632681 @default.
• W2950867030 cites W2952793010 @default.
• W2950867030 cites W2952856735 @default.
• W2950867030 cites W2963563573 @default.
• W2950867030 cites W2964288706 @default.
• W2950867030 cites W7746136 @default.
• W2950867030 doi "https://doi.org/10.48550/arxiv.1704.03604" @default.
• W2950867030 hasPublicationYear "2017" @default.
• W2950867030 type Work @default.
• W2950867030 sameAs 2950867030 @default.
• W2950867030 citedByCount "1" @default.
• W2950867030 countsByYear W29508670302017 @default.
• W2950867030 crossrefType "posted-content" @default.
• W2950867030 hasAuthorship W2950867030A5042965510 @default.
• W2950867030 hasAuthorship W2950867030A5058965019 @default.
• W2950867030 hasAuthorship W2950867030A5071959906 @default.
• W2950867030 hasAuthorship W2950867030A5082076121 @default.
• W2950867030 hasBestOaLocation W29508670301 @default.
• W2950867030 hasConcept C115961682 @default.
• W2950867030 hasConcept C124504099 @default.
• W2950867030 hasConcept C153180895 @default.
• W2950867030 hasConcept C154945302 @default.
• W2950867030 hasConcept C199360897 @default.
• W2950867030 hasConcept C2780719617 @default.
• W2950867030 hasConcept C2780801425 @default.
• W2950867030 hasConcept C2781238097 @default.
• W2950867030 hasConcept C31972630 @default.
• W2950867030 hasConcept C41008148 @default.
• W2950867030 hasConcept C81363708 @default.
• W2950867030 hasConcept C89600930 @default.
• W2950867030 hasConceptScore W2950867030C115961682 @default.
• W2950867030 hasConceptScore W2950867030C124504099 @default.
• W2950867030 hasConceptScore W2950867030C153180895 @default.
• W2950867030 hasConceptScore W2950867030C154945302 @default.
• W2950867030 hasConceptScore W2950867030C199360897 @default.
• W2950867030 hasConceptScore W2950867030C2780719617 @default.
• W2950867030 hasConceptScore W2950867030C2780801425 @default.
• W2950867030 hasConceptScore W2950867030C2781238097 @default.
• W2950867030 hasConceptScore W2950867030C31972630 @default.
• W2950867030 hasConceptScore W2950867030C41008148 @default.
• W2950867030 hasConceptScore W2950867030C81363708 @default.
• W2950867030 hasConceptScore W2950867030C89600930 @default.
• W2950867030 hasLocation W29508670301 @default.
• W2950867030 hasLocation W29508670302 @default.
• W2950867030 hasOpenAccess W2950867030 @default.
• W2950867030 hasPrimaryLocation W29508670301 @default.
• W2950867030 hasRelatedWork W1669643531 @default.

• next