Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890143105> ?p ?o ?g. }
- W2890143105 endingPage "342" @default.
- W2890143105 startingPage "330" @default.
- W2890143105 abstract "This paper presents an interactive image segmentation approach in which we formulate segmentation as a probabilistic estimation problem based on the prior user intention. Instead of directly measuring the relationship between pixels and labels, we first estimate the distances between pixel pairs and label pairs using a probabilistic framework. Then, binary probabilities with label pairs are naturally converted to unary probabilities with labels. The higher order relationship helps improve the robustness to user inputs. To improve segmentation accuracy, a likelihood learning framework is proposed to fuse the region and the boundary information of the image by imposing a smoothing constraint on the unary potentials. Furthermore, we establish an equivalence relationship between likelihood learning and likelihood diffusion and propose an iterative diffusion-based optimization strategy to maintain computational efficiency. Experiments on the Berkeley segmentation data set and Microsoft GrabCut database demonstrate that the proposed method can obtain better performance than the state-of-the-art methods." @default.
- W2890143105 created "2018-09-27" @default.
- W2890143105 creator A5034434932 @default.
- W2890143105 creator A5044758681 @default.
- W2890143105 creator A5062318228 @default.
- W2890143105 creator A5085142676 @default.
- W2890143105 date "2019-01-01" @default.
- W2890143105 modified "2023-10-17" @default.
- W2890143105 title "Probabilistic Diffusion for Interactive Image Segmentation" @default.
- W2890143105 cites W119622245 @default.
- W2890143105 cites W1970018890 @default.
- W2890143105 cites W1973771202 @default.
- W2890143105 cites W2016944307 @default.
- W2890143105 cites W2108424265 @default.
- W2890143105 cites W2114650767 @default.
- W2890143105 cites W2116877738 @default.
- W2890143105 cites W2121189958 @default.
- W2890143105 cites W2124351162 @default.
- W2890143105 cites W2125637308 @default.
- W2890143105 cites W2141729166 @default.
- W2890143105 cites W2147188488 @default.
- W2890143105 cites W2220312492 @default.
- W2890143105 cites W2267158114 @default.
- W2890143105 cites W2279976431 @default.
- W2890143105 cites W2294819727 @default.
- W2890143105 cites W2337570847 @default.
- W2890143105 cites W2395611524 @default.
- W2890143105 cites W2470733339 @default.
- W2890143105 cites W2543959933 @default.
- W2890143105 cites W2552485079 @default.
- W2890143105 cites W2792379357 @default.
- W2890143105 cites W2964234847 @default.
- W2890143105 doi "https://doi.org/10.1109/tip.2018.2867941" @default.
- W2890143105 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30183628" @default.
- W2890143105 hasPublicationYear "2019" @default.
- W2890143105 type Work @default.
- W2890143105 sameAs 2890143105 @default.
- W2890143105 citedByCount "33" @default.
- W2890143105 countsByYear W28901431052019 @default.
- W2890143105 countsByYear W28901431052020 @default.
- W2890143105 countsByYear W28901431052021 @default.
- W2890143105 countsByYear W28901431052022 @default.
- W2890143105 countsByYear W28901431052023 @default.
- W2890143105 crossrefType "journal-article" @default.
- W2890143105 hasAuthorship W2890143105A5034434932 @default.
- W2890143105 hasAuthorship W2890143105A5044758681 @default.
- W2890143105 hasAuthorship W2890143105A5062318228 @default.
- W2890143105 hasAuthorship W2890143105A5085142676 @default.
- W2890143105 hasConcept C104317684 @default.
- W2890143105 hasConcept C114614502 @default.
- W2890143105 hasConcept C124504099 @default.
- W2890143105 hasConcept C153180895 @default.
- W2890143105 hasConcept C154945302 @default.
- W2890143105 hasConcept C160633673 @default.
- W2890143105 hasConcept C185592680 @default.
- W2890143105 hasConcept C25694479 @default.
- W2890143105 hasConcept C31972630 @default.
- W2890143105 hasConcept C33923547 @default.
- W2890143105 hasConcept C41008148 @default.
- W2890143105 hasConcept C49937458 @default.
- W2890143105 hasConcept C55493867 @default.
- W2890143105 hasConcept C63479239 @default.
- W2890143105 hasConcept C65885262 @default.
- W2890143105 hasConcept C78023250 @default.
- W2890143105 hasConcept C89600930 @default.
- W2890143105 hasConceptScore W2890143105C104317684 @default.
- W2890143105 hasConceptScore W2890143105C114614502 @default.
- W2890143105 hasConceptScore W2890143105C124504099 @default.
- W2890143105 hasConceptScore W2890143105C153180895 @default.
- W2890143105 hasConceptScore W2890143105C154945302 @default.
- W2890143105 hasConceptScore W2890143105C160633673 @default.
- W2890143105 hasConceptScore W2890143105C185592680 @default.
- W2890143105 hasConceptScore W2890143105C25694479 @default.
- W2890143105 hasConceptScore W2890143105C31972630 @default.
- W2890143105 hasConceptScore W2890143105C33923547 @default.
- W2890143105 hasConceptScore W2890143105C41008148 @default.
- W2890143105 hasConceptScore W2890143105C49937458 @default.
- W2890143105 hasConceptScore W2890143105C55493867 @default.
- W2890143105 hasConceptScore W2890143105C63479239 @default.
- W2890143105 hasConceptScore W2890143105C65885262 @default.
- W2890143105 hasConceptScore W2890143105C78023250 @default.
- W2890143105 hasConceptScore W2890143105C89600930 @default.
- W2890143105 hasFunder F4320321001 @default.
- W2890143105 hasFunder F4320321543 @default.
- W2890143105 hasFunder F4320322769 @default.
- W2890143105 hasFunder F4320335777 @default.
- W2890143105 hasIssue "1" @default.
- W2890143105 hasLocation W28901431051 @default.
- W2890143105 hasLocation W28901431052 @default.
- W2890143105 hasOpenAccess W2890143105 @default.
- W2890143105 hasPrimaryLocation W28901431051 @default.
- W2890143105 hasRelatedWork W1507266234 @default.
- W2890143105 hasRelatedWork W1669643531 @default.
- W2890143105 hasRelatedWork W2069711651 @default.
- W2890143105 hasRelatedWork W2117664411 @default.
- W2890143105 hasRelatedWork W2117933325 @default.
- W2890143105 hasRelatedWork W2549936415 @default.
- W2890143105 hasRelatedWork W2558375057 @default.