Matches in SemOpenAlex for { <https://semopenalex.org/work/W2056526820> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W2056526820 abstract "We present a learning method for classification using multiple manifold-valued features. Manifold techniques are becoming increasingly popular in computer vision since Riemannian geometry often comes up as a natural model for many descriptors encountered in different branches of computer vision. We propose a feature combination and selection method that optimally combines descriptors lying on different manifolds while respecting the Riemannian geometry of each underlying manifold. We use our method to improve object recognition by combining HOG~cite{Dalal05Hog} and Region Covariance~cite{Tuzel06} descriptors that reside on two different manifolds. To this end, we propose a kernel on the $n$-dimensional unit sphere and prove its positive definiteness. Our experimental evaluation shows that combining these two powerful descriptors using our method results in significant improvements in recognition accuracy." @default.
- W2056526820 created "2016-06-24" @default.
- W2056526820 creator A5020216442 @default.
- W2056526820 creator A5021790939 @default.
- W2056526820 creator A5049300388 @default.
- W2056526820 creator A5061507436 @default.
- W2056526820 creator A5075594276 @default.
- W2056526820 date "2013-11-01" @default.
- W2056526820 modified "2023-10-17" @default.
- W2056526820 title "Combining Multiple Manifold-Valued Descriptors for Improved Object Recognition" @default.
- W2056526820 cites W1510073064 @default.
- W2056526820 cites W157436748 @default.
- W2056526820 cites W179694669 @default.
- W2056526820 cites W1983496390 @default.
- W2056526820 cites W1998167411 @default.
- W2056526820 cites W2033819227 @default.
- W2056526820 cites W2048192550 @default.
- W2056526820 cites W2088449330 @default.
- W2056526820 cites W2112074816 @default.
- W2056526820 cites W2116022929 @default.
- W2056526820 cites W2122808326 @default.
- W2056526820 cites W2126017757 @default.
- W2056526820 cites W2127069950 @default.
- W2056526820 cites W2137401668 @default.
- W2056526820 cites W2149338181 @default.
- W2056526820 cites W2149652297 @default.
- W2056526820 cites W2151103935 @default.
- W2056526820 cites W2161969291 @default.
- W2056526820 cites W2163352848 @default.
- W2056526820 cites W2168002178 @default.
- W2056526820 doi "https://doi.org/10.1109/dicta.2013.6691493" @default.
- W2056526820 hasPublicationYear "2013" @default.
- W2056526820 type Work @default.
- W2056526820 sameAs 2056526820 @default.
- W2056526820 citedByCount "20" @default.
- W2056526820 countsByYear W20565268202014 @default.
- W2056526820 countsByYear W20565268202015 @default.
- W2056526820 countsByYear W20565268202016 @default.
- W2056526820 countsByYear W20565268202017 @default.
- W2056526820 countsByYear W20565268202018 @default.
- W2056526820 countsByYear W20565268202019 @default.
- W2056526820 countsByYear W20565268202020 @default.
- W2056526820 countsByYear W20565268202021 @default.
- W2056526820 countsByYear W20565268202022 @default.
- W2056526820 crossrefType "proceedings-article" @default.
- W2056526820 hasAuthorship W2056526820A5020216442 @default.
- W2056526820 hasAuthorship W2056526820A5021790939 @default.
- W2056526820 hasAuthorship W2056526820A5049300388 @default.
- W2056526820 hasAuthorship W2056526820A5061507436 @default.
- W2056526820 hasAuthorship W2056526820A5075594276 @default.
- W2056526820 hasConcept C127413603 @default.
- W2056526820 hasConcept C153180895 @default.
- W2056526820 hasConcept C154945302 @default.
- W2056526820 hasConcept C2781238097 @default.
- W2056526820 hasConcept C31972630 @default.
- W2056526820 hasConcept C41008148 @default.
- W2056526820 hasConcept C529865628 @default.
- W2056526820 hasConcept C64876066 @default.
- W2056526820 hasConcept C78519656 @default.
- W2056526820 hasConceptScore W2056526820C127413603 @default.
- W2056526820 hasConceptScore W2056526820C153180895 @default.
- W2056526820 hasConceptScore W2056526820C154945302 @default.
- W2056526820 hasConceptScore W2056526820C2781238097 @default.
- W2056526820 hasConceptScore W2056526820C31972630 @default.
- W2056526820 hasConceptScore W2056526820C41008148 @default.
- W2056526820 hasConceptScore W2056526820C529865628 @default.
- W2056526820 hasConceptScore W2056526820C64876066 @default.
- W2056526820 hasConceptScore W2056526820C78519656 @default.
- W2056526820 hasLocation W20565268201 @default.
- W2056526820 hasOpenAccess W2056526820 @default.
- W2056526820 hasPrimaryLocation W20565268201 @default.
- W2056526820 hasRelatedWork W1528044252 @default.
- W2056526820 hasRelatedWork W1531683208 @default.
- W2056526820 hasRelatedWork W2009052148 @default.
- W2056526820 hasRelatedWork W2200925278 @default.
- W2056526820 hasRelatedWork W2328068029 @default.
- W2056526820 hasRelatedWork W2330829846 @default.
- W2056526820 hasRelatedWork W2350353705 @default.
- W2056526820 hasRelatedWork W2363840281 @default.
- W2056526820 hasRelatedWork W2372904789 @default.
- W2056526820 hasRelatedWork W2536452361 @default.
- W2056526820 isParatext "false" @default.
- W2056526820 isRetracted "false" @default.
- W2056526820 magId "2056526820" @default.
- W2056526820 workType "article" @default.