Matches in SemOpenAlex for { <https://semopenalex.org/work/W2028860304> ?p ?o ?g. }
- W2028860304 abstract "The framework based on the Bag-of-Visual-Words (BoVW) feature representation and SVM classification is popularly used for generic content-based concept detection or visual categorization. However, visual vocabulary (VV) size, one important factor in this framework, is always chosen differently and arbitrarily in previous work. In this paper, we focus on investigating the optimal VV sizes depending on other components of this framework which also govern the performance. This is useful as a default VV size for reducing the computation cost. By unsupervised clustering, a series of VVs covering a wide range of sizes are evaluated under two popular local features, three assignment modes, and four kernels on two different-scale benchmarking datasets respectively. These factors are also evaluated. Experimental results show that best VV sizes vary as these factors change. However, the concept detection performance usually improves as the VV size increases initially, and then gains less, or even deteriorates if larger VVs are used since overfitting occurs. Overall, VVs with sizes ranging from 1024 to 4096 achieve best performance with higher probability when compared with other-size VVs. With regard to the other factors, experimental results show that the OpponentSIFT descriptor outperforms the SURF feature, and soft assignment mode yields better performance than binary and hard assignment. In addition, generalized RBF kernels such as X <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>2</sup> and Laplace RBF kernels are more appropriate for semantic concept detection with SVM classification." @default.
- W2028860304 created "2016-06-24" @default.
- W2028860304 creator A5014224452 @default.
- W2028860304 creator A5029569657 @default.
- W2028860304 creator A5037886027 @default.
- W2028860304 date "2013-06-01" @default.
- W2028860304 modified "2023-09-28" @default.
- W2028860304 title "Exploring the optimal visual vocabulary sizes for semantic concept detection" @default.
- W2028860304 cites W1625255723 @default.
- W2028860304 cites W1967879792 @default.
- W2028860304 cites W1976921161 @default.
- W2028860304 cites W2062903088 @default.
- W2028860304 cites W2092798093 @default.
- W2028860304 cites W2112020727 @default.
- W2028860304 cites W2119605622 @default.
- W2028860304 cites W2127513583 @default.
- W2028860304 cites W2128017662 @default.
- W2028860304 cites W2131846894 @default.
- W2028860304 cites W2148809503 @default.
- W2028860304 cites W2155803963 @default.
- W2028860304 cites W2158226832 @default.
- W2028860304 cites W2162762921 @default.
- W2028860304 cites W2162915993 @default.
- W2028860304 cites W2171896402 @default.
- W2028860304 doi "https://doi.org/10.1109/cbmi.2013.6576565" @default.
- W2028860304 hasPublicationYear "2013" @default.
- W2028860304 type Work @default.
- W2028860304 sameAs 2028860304 @default.
- W2028860304 citedByCount "5" @default.
- W2028860304 countsByYear W20288603042014 @default.
- W2028860304 countsByYear W20288603042015 @default.
- W2028860304 countsByYear W20288603042017 @default.
- W2028860304 countsByYear W20288603042019 @default.
- W2028860304 crossrefType "proceedings-article" @default.
- W2028860304 hasAuthorship W2028860304A5014224452 @default.
- W2028860304 hasAuthorship W2028860304A5029569657 @default.
- W2028860304 hasAuthorship W2028860304A5037886027 @default.
- W2028860304 hasBestOaLocation W20288603042 @default.
- W2028860304 hasConcept C11413529 @default.
- W2028860304 hasConcept C119857082 @default.
- W2028860304 hasConcept C12267149 @default.
- W2028860304 hasConcept C138885662 @default.
- W2028860304 hasConcept C144133560 @default.
- W2028860304 hasConcept C153180895 @default.
- W2028860304 hasConcept C154945302 @default.
- W2028860304 hasConcept C162853370 @default.
- W2028860304 hasConcept C17744445 @default.
- W2028860304 hasConcept C199539241 @default.
- W2028860304 hasConcept C22019652 @default.
- W2028860304 hasConcept C2776359362 @default.
- W2028860304 hasConcept C2776401178 @default.
- W2028860304 hasConcept C2777601683 @default.
- W2028860304 hasConcept C41008148 @default.
- W2028860304 hasConcept C41895202 @default.
- W2028860304 hasConcept C45374587 @default.
- W2028860304 hasConcept C50644808 @default.
- W2028860304 hasConcept C73555534 @default.
- W2028860304 hasConcept C86251818 @default.
- W2028860304 hasConcept C94124525 @default.
- W2028860304 hasConcept C94625758 @default.
- W2028860304 hasConceptScore W2028860304C11413529 @default.
- W2028860304 hasConceptScore W2028860304C119857082 @default.
- W2028860304 hasConceptScore W2028860304C12267149 @default.
- W2028860304 hasConceptScore W2028860304C138885662 @default.
- W2028860304 hasConceptScore W2028860304C144133560 @default.
- W2028860304 hasConceptScore W2028860304C153180895 @default.
- W2028860304 hasConceptScore W2028860304C154945302 @default.
- W2028860304 hasConceptScore W2028860304C162853370 @default.
- W2028860304 hasConceptScore W2028860304C17744445 @default.
- W2028860304 hasConceptScore W2028860304C199539241 @default.
- W2028860304 hasConceptScore W2028860304C22019652 @default.
- W2028860304 hasConceptScore W2028860304C2776359362 @default.
- W2028860304 hasConceptScore W2028860304C2776401178 @default.
- W2028860304 hasConceptScore W2028860304C2777601683 @default.
- W2028860304 hasConceptScore W2028860304C41008148 @default.
- W2028860304 hasConceptScore W2028860304C41895202 @default.
- W2028860304 hasConceptScore W2028860304C45374587 @default.
- W2028860304 hasConceptScore W2028860304C50644808 @default.
- W2028860304 hasConceptScore W2028860304C73555534 @default.
- W2028860304 hasConceptScore W2028860304C86251818 @default.
- W2028860304 hasConceptScore W2028860304C94124525 @default.
- W2028860304 hasConceptScore W2028860304C94625758 @default.
- W2028860304 hasLocation W20288603041 @default.
- W2028860304 hasLocation W20288603042 @default.
- W2028860304 hasOpenAccess W2028860304 @default.
- W2028860304 hasPrimaryLocation W20288603041 @default.
- W2028860304 hasRelatedWork W1915943666 @default.
- W2028860304 hasRelatedWork W1975653181 @default.
- W2028860304 hasRelatedWork W1981008538 @default.
- W2028860304 hasRelatedWork W2000021714 @default.
- W2028860304 hasRelatedWork W2005779801 @default.
- W2028860304 hasRelatedWork W2009184008 @default.
- W2028860304 hasRelatedWork W2011085767 @default.
- W2028860304 hasRelatedWork W2012268188 @default.
- W2028860304 hasRelatedWork W2030946033 @default.
- W2028860304 hasRelatedWork W2099279702 @default.
- W2028860304 hasRelatedWork W2113393607 @default.
- W2028860304 hasRelatedWork W2124209734 @default.
- W2028860304 hasRelatedWork W2126227692 @default.
- W2028860304 hasRelatedWork W2160483151 @default.