Matches in SemOpenAlex for { <https://semopenalex.org/work/W2002135052> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W2002135052 endingPage "90" @default.
- W2002135052 startingPage "79" @default.
- W2002135052 abstract "Abstract Hierarchical classification (HC) is a popular and efficient way for detecting the semantic concepts from the images. The conventional method always selects the branch with the highest classification response. This branch selection strategy has a risk of propagating classification errors from higher levels of the hierarchy to the lower levels. We argue that the local strategy is too arbitrary, because the candidate nodes are considered individually, which ignores the semantic and context relationships among concepts. In this paper, we first propose a novel method for HC, which is able to utilize the semantic relationship among candidate nodes and their children to recover the responses of unreliable classifiers of the candidate nodes. Thus the error is expected to be reduced by a collaborative branch selection scheme. The approach is further extended to enable multiple branch selection, where other relationships (e.g., contextual information) are incorporated, with the hope of providing the branch selection a more globally valid, semantically and contextually consistent view. An extensive set of experiments on three large-scale datasets shows that the proposed methods outperform the conventional HC method, and achieve a satisfactory balance between the effectiveness and efficiency." @default.
- W2002135052 created "2016-06-24" @default.
- W2002135052 creator A5002829835 @default.
- W2002135052 creator A5050416778 @default.
- W2002135052 creator A5064374603 @default.
- W2002135052 date "2014-07-01" @default.
- W2002135052 modified "2023-09-25" @default.
- W2002135052 title "Collaborative error reduction for hierarchical classification" @default.
- W2002135052 cites W1851597118 @default.
- W2002135052 cites W1926323398 @default.
- W2002135052 cites W1968178977 @default.
- W2002135052 cites W1974907760 @default.
- W2002135052 cites W1979495886 @default.
- W2002135052 cites W1992736075 @default.
- W2002135052 cites W1999226794 @default.
- W2002135052 cites W2007972815 @default.
- W2002135052 cites W2023707432 @default.
- W2002135052 cites W2025047573 @default.
- W2002135052 cites W2027922120 @default.
- W2002135052 cites W2030848407 @default.
- W2002135052 cites W2055373780 @default.
- W2002135052 cites W2062903088 @default.
- W2002135052 cites W2063386797 @default.
- W2002135052 cites W2073830447 @default.
- W2002135052 cites W2075760200 @default.
- W2002135052 cites W2103017472 @default.
- W2002135052 cites W2105573333 @default.
- W2002135052 cites W2106097867 @default.
- W2002135052 cites W2108598243 @default.
- W2002135052 cites W2112832339 @default.
- W2002135052 cites W2114369285 @default.
- W2002135052 cites W2123049467 @default.
- W2002135052 cites W2150766729 @default.
- W2002135052 cites W2155440340 @default.
- W2002135052 doi "https://doi.org/10.1016/j.cviu.2014.03.010" @default.
- W2002135052 hasPublicationYear "2014" @default.
- W2002135052 type Work @default.
- W2002135052 sameAs 2002135052 @default.
- W2002135052 citedByCount "6" @default.
- W2002135052 countsByYear W20021350522016 @default.
- W2002135052 countsByYear W20021350522017 @default.
- W2002135052 countsByYear W20021350522019 @default.
- W2002135052 countsByYear W20021350522022 @default.
- W2002135052 crossrefType "journal-article" @default.
- W2002135052 hasAuthorship W2002135052A5002829835 @default.
- W2002135052 hasAuthorship W2002135052A5050416778 @default.
- W2002135052 hasAuthorship W2002135052A5064374603 @default.
- W2002135052 hasBestOaLocation W20021350522 @default.
- W2002135052 hasConcept C111335779 @default.
- W2002135052 hasConcept C119857082 @default.
- W2002135052 hasConcept C153180895 @default.
- W2002135052 hasConcept C154945302 @default.
- W2002135052 hasConcept C2524010 @default.
- W2002135052 hasConcept C33923547 @default.
- W2002135052 hasConcept C41008148 @default.
- W2002135052 hasConcept C70518039 @default.
- W2002135052 hasConceptScore W2002135052C111335779 @default.
- W2002135052 hasConceptScore W2002135052C119857082 @default.
- W2002135052 hasConceptScore W2002135052C153180895 @default.
- W2002135052 hasConceptScore W2002135052C154945302 @default.
- W2002135052 hasConceptScore W2002135052C2524010 @default.
- W2002135052 hasConceptScore W2002135052C33923547 @default.
- W2002135052 hasConceptScore W2002135052C41008148 @default.
- W2002135052 hasConceptScore W2002135052C70518039 @default.
- W2002135052 hasLocation W20021350521 @default.
- W2002135052 hasLocation W20021350522 @default.
- W2002135052 hasOpenAccess W2002135052 @default.
- W2002135052 hasPrimaryLocation W20021350521 @default.
- W2002135052 hasRelatedWork W1523234081 @default.
- W2002135052 hasRelatedWork W1994135600 @default.
- W2002135052 hasRelatedWork W2066259560 @default.
- W2002135052 hasRelatedWork W2090269531 @default.
- W2002135052 hasRelatedWork W2163831990 @default.
- W2002135052 hasRelatedWork W2339674921 @default.
- W2002135052 hasRelatedWork W2355203151 @default.
- W2002135052 hasRelatedWork W3211035526 @default.
- W2002135052 hasRelatedWork W4220663171 @default.
- W2002135052 hasRelatedWork W94476185 @default.
- W2002135052 hasVolume "124" @default.
- W2002135052 isParatext "false" @default.
- W2002135052 isRetracted "false" @default.
- W2002135052 magId "2002135052" @default.
- W2002135052 workType "article" @default.