Matches in SemOpenAlex for { <https://semopenalex.org/work/W139598979> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W139598979 endingPage "92" @default.
- W139598979 startingPage "84" @default.
- W139598979 abstract "AbstractWe propose a novel algorithm to segment objects from the existed segmentation results of the co-segmentation algorithms [1]. Previous co-segmentation algorithms work well when the main regions of the images contain only the target objects; however, their performances degenerate significantly when multi-category objects appear in the images. In contrast, our method adopts mask transformation from multiple images and discriminatively enhancement from multiple object categories, which can effectively ensure a good performance in both scenarios. We propose to use sift-flow [2] between pre-segmented source images and target image, and transform the source images’ segmentation mask to fit the target testing image by the flow vectors. Then we use all the transformed masks to vote the testing image mask and get the initial segmentation results. We also propose to use the ratio between the target category and the other categories to eliminate the side effects from other objects that might appeared in the initial segmentation. We conduct our experiment on internet images collected by Rubinstein .etc [1]. We also do additional experiment to study the multi-object conjunction cases. Our algorithm is effective in computation complexity and able to achieve a better performance than the state-of-the-art algorithm.KeywordsTarget ObjectLabel PropagationPositive RatioSegmentation MaskSemantic RegionThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves." @default.
- W139598979 created "2016-06-24" @default.
- W139598979 creator A5023274785 @default.
- W139598979 creator A5044689489 @default.
- W139598979 creator A5053313013 @default.
- W139598979 date "2014-01-01" @default.
- W139598979 modified "2023-09-27" @default.
- W139598979 title "Using Label Propagation to Get Confidence Map for Segmentation" @default.
- W139598979 cites W143551758 @default.
- W139598979 cites W1996140089 @default.
- W139598979 cites W2037954058 @default.
- W139598979 cites W2052598438 @default.
- W139598979 cites W2090518410 @default.
- W139598979 cites W2124351162 @default.
- W139598979 cites W2151103935 @default.
- W139598979 cites W2295160225 @default.
- W139598979 doi "https://doi.org/10.1007/978-3-319-13168-9_9" @default.
- W139598979 hasPublicationYear "2014" @default.
- W139598979 type Work @default.
- W139598979 sameAs 139598979 @default.
- W139598979 citedByCount "0" @default.
- W139598979 crossrefType "book-chapter" @default.
- W139598979 hasAuthorship W139598979A5023274785 @default.
- W139598979 hasAuthorship W139598979A5044689489 @default.
- W139598979 hasAuthorship W139598979A5053313013 @default.
- W139598979 hasConcept C104317684 @default.
- W139598979 hasConcept C11413529 @default.
- W139598979 hasConcept C115961682 @default.
- W139598979 hasConcept C124504099 @default.
- W139598979 hasConcept C153180895 @default.
- W139598979 hasConcept C154945302 @default.
- W139598979 hasConcept C185592680 @default.
- W139598979 hasConcept C204241405 @default.
- W139598979 hasConcept C25694479 @default.
- W139598979 hasConcept C2781238097 @default.
- W139598979 hasConcept C31972630 @default.
- W139598979 hasConcept C41008148 @default.
- W139598979 hasConcept C45374587 @default.
- W139598979 hasConcept C55493867 @default.
- W139598979 hasConcept C61265191 @default.
- W139598979 hasConcept C65885262 @default.
- W139598979 hasConcept C89600930 @default.
- W139598979 hasConceptScore W139598979C104317684 @default.
- W139598979 hasConceptScore W139598979C11413529 @default.
- W139598979 hasConceptScore W139598979C115961682 @default.
- W139598979 hasConceptScore W139598979C124504099 @default.
- W139598979 hasConceptScore W139598979C153180895 @default.
- W139598979 hasConceptScore W139598979C154945302 @default.
- W139598979 hasConceptScore W139598979C185592680 @default.
- W139598979 hasConceptScore W139598979C204241405 @default.
- W139598979 hasConceptScore W139598979C25694479 @default.
- W139598979 hasConceptScore W139598979C2781238097 @default.
- W139598979 hasConceptScore W139598979C31972630 @default.
- W139598979 hasConceptScore W139598979C41008148 @default.
- W139598979 hasConceptScore W139598979C45374587 @default.
- W139598979 hasConceptScore W139598979C55493867 @default.
- W139598979 hasConceptScore W139598979C61265191 @default.
- W139598979 hasConceptScore W139598979C65885262 @default.
- W139598979 hasConceptScore W139598979C89600930 @default.
- W139598979 hasLocation W1395989791 @default.
- W139598979 hasOpenAccess W139598979 @default.
- W139598979 hasPrimaryLocation W1395989791 @default.
- W139598979 hasRelatedWork W1092731009 @default.
- W139598979 hasRelatedWork W1762516944 @default.
- W139598979 hasRelatedWork W1861910958 @default.
- W139598979 hasRelatedWork W1985981811 @default.
- W139598979 hasRelatedWork W1988276889 @default.
- W139598979 hasRelatedWork W2042095678 @default.
- W139598979 hasRelatedWork W2055942866 @default.
- W139598979 hasRelatedWork W2118124367 @default.
- W139598979 hasRelatedWork W2135378878 @default.
- W139598979 hasRelatedWork W2156709493 @default.
- W139598979 hasRelatedWork W2252585081 @default.
- W139598979 hasRelatedWork W2381149064 @default.
- W139598979 hasRelatedWork W2594032178 @default.
- W139598979 hasRelatedWork W2940683962 @default.
- W139598979 hasRelatedWork W2953812324 @default.
- W139598979 hasRelatedWork W2981545510 @default.
- W139598979 hasRelatedWork W2993810500 @default.
- W139598979 hasRelatedWork W3104686576 @default.
- W139598979 hasRelatedWork W3201767287 @default.
- W139598979 hasRelatedWork W2872585932 @default.
- W139598979 isParatext "false" @default.
- W139598979 isRetracted "false" @default.
- W139598979 magId "139598979" @default.
- W139598979 workType "book-chapter" @default.