Matches in SemOpenAlex for { <https://semopenalex.org/work/W2380782110> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W2380782110 abstract "Recently,there have been increasing interests in semantic scene parsing,which are mainly based on prior models.However,as prior models only consider the common merits within objects,they ignore the inner color coherence lied in the single object and suffer from detail loss.In this paper,we utilize color cue as the inner information,and present an approach to incorporating local color model with prior models under a two-level conditional random field to preserve scene parsing details.More specially,objects of the scene are first roughly extracted using prior models within a superpixel-based conditional random field,in which prior models are acquired by supervised learning using color,gradient,texture and geometric cues,and then a local color model is built for each object based on the initial parsing result.Combining the local color model and prior models,we employ an EM(Expectation-Maximization)scheme for iterative refinement within a pixel-based conditional random field.Experimental evaluations with state-of-the-art methods verify that our approach is able to preserve details and achieve better performance." @default.
- W2380782110 created "2016-06-24" @default.
- W2380782110 creator A5078200798 @default.
- W2380782110 date "2013-01-01" @default.
- W2380782110 modified "2023-09-23" @default.
- W2380782110 title "Scene Parsing Based on A Two-Level Conditional Random Field" @default.
- W2380782110 hasPublicationYear "2013" @default.
- W2380782110 type Work @default.
- W2380782110 sameAs 2380782110 @default.
- W2380782110 citedByCount "0" @default.
- W2380782110 crossrefType "journal-article" @default.
- W2380782110 hasAuthorship W2380782110A5078200798 @default.
- W2380782110 hasConcept C105795698 @default.
- W2380782110 hasConcept C119857082 @default.
- W2380782110 hasConcept C126255220 @default.
- W2380782110 hasConcept C130402806 @default.
- W2380782110 hasConcept C152565575 @default.
- W2380782110 hasConcept C153180895 @default.
- W2380782110 hasConcept C154945302 @default.
- W2380782110 hasConcept C160633673 @default.
- W2380782110 hasConcept C186644900 @default.
- W2380782110 hasConcept C202444582 @default.
- W2380782110 hasConcept C2776330181 @default.
- W2380782110 hasConcept C2779255053 @default.
- W2380782110 hasConcept C2781181686 @default.
- W2380782110 hasConcept C2781238097 @default.
- W2380782110 hasConcept C31972630 @default.
- W2380782110 hasConcept C33923547 @default.
- W2380782110 hasConcept C41008148 @default.
- W2380782110 hasConcept C9652623 @default.
- W2380782110 hasConceptScore W2380782110C105795698 @default.
- W2380782110 hasConceptScore W2380782110C119857082 @default.
- W2380782110 hasConceptScore W2380782110C126255220 @default.
- W2380782110 hasConceptScore W2380782110C130402806 @default.
- W2380782110 hasConceptScore W2380782110C152565575 @default.
- W2380782110 hasConceptScore W2380782110C153180895 @default.
- W2380782110 hasConceptScore W2380782110C154945302 @default.
- W2380782110 hasConceptScore W2380782110C160633673 @default.
- W2380782110 hasConceptScore W2380782110C186644900 @default.
- W2380782110 hasConceptScore W2380782110C202444582 @default.
- W2380782110 hasConceptScore W2380782110C2776330181 @default.
- W2380782110 hasConceptScore W2380782110C2779255053 @default.
- W2380782110 hasConceptScore W2380782110C2781181686 @default.
- W2380782110 hasConceptScore W2380782110C2781238097 @default.
- W2380782110 hasConceptScore W2380782110C31972630 @default.
- W2380782110 hasConceptScore W2380782110C33923547 @default.
- W2380782110 hasConceptScore W2380782110C41008148 @default.
- W2380782110 hasConceptScore W2380782110C9652623 @default.
- W2380782110 hasLocation W23807821101 @default.
- W2380782110 hasOpenAccess W2380782110 @default.
- W2380782110 hasPrimaryLocation W23807821101 @default.
- W2380782110 hasRelatedWork W2056860348 @default.
- W2380782110 hasRelatedWork W2058536148 @default.
- W2380782110 hasRelatedWork W2066154710 @default.
- W2380782110 hasRelatedWork W2129287605 @default.
- W2380782110 hasRelatedWork W2152513128 @default.
- W2380782110 hasRelatedWork W2163766261 @default.
- W2380782110 hasRelatedWork W2275078158 @default.
- W2380782110 hasRelatedWork W2289333783 @default.
- W2380782110 hasRelatedWork W2341589144 @default.
- W2380782110 hasRelatedWork W2378615232 @default.
- W2380782110 hasRelatedWork W2384250327 @default.
- W2380782110 hasRelatedWork W2390308378 @default.
- W2380782110 hasRelatedWork W2470200161 @default.
- W2380782110 hasRelatedWork W2777356020 @default.
- W2380782110 hasRelatedWork W2885364117 @default.
- W2380782110 hasRelatedWork W2955098027 @default.
- W2380782110 hasRelatedWork W3105308185 @default.
- W2380782110 hasRelatedWork W3129840128 @default.
- W2380782110 hasRelatedWork W832272354 @default.
- W2380782110 hasRelatedWork W103299903 @default.
- W2380782110 isParatext "false" @default.
- W2380782110 isRetracted "false" @default.
- W2380782110 magId "2380782110" @default.
- W2380782110 workType "article" @default.