Matches in SemOpenAlex for { <https://semopenalex.org/work/W3087865810> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W3087865810 abstract "High-energy physics detectors, images, and point clouds share many similarities in terms of object detection. However, while detecting an unknown number of objects in an image is well established in computer vision, even machine learning assisted object reconstruction algorithms in particle physics almost exclusively predict properties on an object-by-object basis. Traditional approaches from computer vision either impose implicit constraints on the object size or density and are not well suited for sparse detector data or rely on objects being dense and solid. The object condensation method proposed here is independent of assumptions on object size, sorting or object density, and further generalises to non-image-like data structures, such as graphs and point clouds, which are more suitable to represent detector signals. The pixels or vertices themselves serve as representations of the entire object, and a combination of learnable local clustering in a latent space and confidence assignment allows one to collect condensates of the predicted object properties with a simple algorithm. As proof of concept, the object condensation method is applied to a simple object classification problem in images and used to reconstruct multiple particles from detector signals. The latter results are also compared to a classic particle flow approach." @default.
- W3087865810 created "2020-10-01" @default.
- W3087865810 creator A5041953297 @default.
- W3087865810 date "2020-09-01" @default.
- W3087865810 modified "2023-09-27" @default.
- W3087865810 title "Object condensation: one-stage grid-free multi-object reconstruction in physics detectors, graph, and image data" @default.
- W3087865810 cites W2000004838 @default.
- W3087865810 cites W2015159529 @default.
- W3087865810 cites W2116341502 @default.
- W3087865810 cites W2116624643 @default.
- W3087865810 cites W2128158076 @default.
- W3087865810 cites W2151512268 @default.
- W3087865810 cites W2159744192 @default.
- W3087865810 cites W2169365476 @default.
- W3087865810 cites W2570343428 @default.
- W3087865810 cites W2604487509 @default.
- W3087865810 cites W2617066340 @default.
- W3087865810 cites W2624881227 @default.
- W3087865810 cites W2741476055 @default.
- W3087865810 cites W2743374906 @default.
- W3087865810 cites W2808572053 @default.
- W3087865810 cites W2810437889 @default.
- W3087865810 cites W2915621743 @default.
- W3087865810 cites W2916639378 @default.
- W3087865810 cites W2949708697 @default.
- W3087865810 cites W2963037989 @default.
- W3087865810 cites W2963113370 @default.
- W3087865810 cites W2963150697 @default.
- W3087865810 cites W2963299996 @default.
- W3087865810 cites W2963351448 @default.
- W3087865810 cites W2963775509 @default.
- W3087865810 cites W2964121718 @default.
- W3087865810 cites W2982770724 @default.
- W3087865810 cites W3002851826 @default.
- W3087865810 cites W3104690326 @default.
- W3087865810 cites W3105195264 @default.
- W3087865810 cites W3106250896 @default.
- W3087865810 cites W3127669268 @default.
- W3087865810 cites W3200934665 @default.
- W3087865810 cites W4232091795 @default.
- W3087865810 doi "https://doi.org/10.1140/epjc/s10052-020-08461-2" @default.
- W3087865810 hasPublicationYear "2020" @default.
- W3087865810 type Work @default.
- W3087865810 sameAs 3087865810 @default.
- W3087865810 citedByCount "18" @default.
- W3087865810 countsByYear W30878658102020 @default.
- W3087865810 countsByYear W30878658102021 @default.
- W3087865810 countsByYear W30878658102022 @default.
- W3087865810 countsByYear W30878658102023 @default.
- W3087865810 crossrefType "journal-article" @default.
- W3087865810 hasAuthorship W3087865810A5041953297 @default.
- W3087865810 hasBestOaLocation W30878658101 @default.
- W3087865810 hasConcept C120665830 @default.
- W3087865810 hasConcept C121332964 @default.
- W3087865810 hasConcept C141379421 @default.
- W3087865810 hasConcept C154945302 @default.
- W3087865810 hasConcept C160633673 @default.
- W3087865810 hasConcept C20894473 @default.
- W3087865810 hasConcept C2781238097 @default.
- W3087865810 hasConcept C31972630 @default.
- W3087865810 hasConcept C41008148 @default.
- W3087865810 hasConcept C94915269 @default.
- W3087865810 hasConceptScore W3087865810C120665830 @default.
- W3087865810 hasConceptScore W3087865810C121332964 @default.
- W3087865810 hasConceptScore W3087865810C141379421 @default.
- W3087865810 hasConceptScore W3087865810C154945302 @default.
- W3087865810 hasConceptScore W3087865810C160633673 @default.
- W3087865810 hasConceptScore W3087865810C20894473 @default.
- W3087865810 hasConceptScore W3087865810C2781238097 @default.
- W3087865810 hasConceptScore W3087865810C31972630 @default.
- W3087865810 hasConceptScore W3087865810C41008148 @default.
- W3087865810 hasConceptScore W3087865810C94915269 @default.
- W3087865810 hasIssue "9" @default.
- W3087865810 hasLocation W30878658101 @default.
- W3087865810 hasLocation W30878658102 @default.
- W3087865810 hasLocation W30878658103 @default.
- W3087865810 hasLocation W30878658104 @default.
- W3087865810 hasLocation W30878658105 @default.
- W3087865810 hasOpenAccess W3087865810 @default.
- W3087865810 hasPrimaryLocation W30878658101 @default.
- W3087865810 hasRelatedWork W1537622850 @default.
- W3087865810 hasRelatedWork W1988485990 @default.
- W3087865810 hasRelatedWork W2007544051 @default.
- W3087865810 hasRelatedWork W2030539674 @default.
- W3087865810 hasRelatedWork W2169256201 @default.
- W3087865810 hasRelatedWork W2337415362 @default.
- W3087865810 hasRelatedWork W2613077666 @default.
- W3087865810 hasRelatedWork W2789220062 @default.
- W3087865810 hasRelatedWork W2975200075 @default.
- W3087865810 hasRelatedWork W4312857205 @default.
- W3087865810 hasVolume "80" @default.
- W3087865810 isParatext "false" @default.
- W3087865810 isRetracted "false" @default.
- W3087865810 magId "3087865810" @default.
- W3087865810 workType "article" @default.