Matches in SemOpenAlex for { <https://semopenalex.org/work/W2169807144> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2169807144 abstract "Abstract. It has been shown previously that systems based on local features and relatively complexgenerative models, namely 1D Hidden Markov Models (HMMs) and pseudo-2D HMMs, are suitable forface recognition (here we mean both identification and verification). Recently a simpler generative model,namely the Gaussian Mixture Model (GMM), was also shown to perform well. In this paper we first proposeto increase the performance of the GMM approach (without sacrificing its simplicity) through the use oflocal features with embedded positional information; we show that the performance obtained is comparableto 1D HMMs. Secondly, we evaluate different training techniques for both GMM and HMM based systems.We show that the traditionally used Maximum Likelihood (ML) training approach has problems estimatingrobust model parameters when there is only a few training images available; we propose to tackle thisproblem through the use of Maximum a Posteriori (MAP) training, where the lack of data problem canbe effectively circumvented; we show that models estimated with MAP are significantly more robust and areable to generalize to adverse conditions present in the BANCA database." @default.
- W2169807144 created "2016-06-24" @default.
- W2169807144 creator A5017529415 @default.
- W2169807144 creator A5054815937 @default.
- W2169807144 creator A5056623642 @default.
- W2169807144 date "2003-01-01" @default.
- W2169807144 modified "2023-09-24" @default.
- W2169807144 title "ADAPTED GENERATIVE MODELS FOR FACE VERIFICATION" @default.
- W2169807144 cites W1480865305 @default.
- W2169807144 cites W1579299427 @default.
- W2169807144 cites W1596028639 @default.
- W2169807144 cites W1852256319 @default.
- W2169807144 cites W2033341974 @default.
- W2169807144 cites W2049633694 @default.
- W2169807144 cites W2097021277 @default.
- W2169807144 cites W2100969003 @default.
- W2169807144 cites W2125838338 @default.
- W2169807144 cites W2138243884 @default.
- W2169807144 cites W2146824864 @default.
- W2169807144 cites W2156404139 @default.
- W2169807144 cites W2799061466 @default.
- W2169807144 hasPublicationYear "2003" @default.
- W2169807144 type Work @default.
- W2169807144 sameAs 2169807144 @default.
- W2169807144 citedByCount "3" @default.
- W2169807144 crossrefType "journal-article" @default.
- W2169807144 hasAuthorship W2169807144A5017529415 @default.
- W2169807144 hasAuthorship W2169807144A5054815937 @default.
- W2169807144 hasAuthorship W2169807144A5056623642 @default.
- W2169807144 hasConcept C105795698 @default.
- W2169807144 hasConcept C111472728 @default.
- W2169807144 hasConcept C119857082 @default.
- W2169807144 hasConcept C121332964 @default.
- W2169807144 hasConcept C138885662 @default.
- W2169807144 hasConcept C153180895 @default.
- W2169807144 hasConcept C154945302 @default.
- W2169807144 hasConcept C163716315 @default.
- W2169807144 hasConcept C167966045 @default.
- W2169807144 hasConcept C23224414 @default.
- W2169807144 hasConcept C28490314 @default.
- W2169807144 hasConcept C33923547 @default.
- W2169807144 hasConcept C39890363 @default.
- W2169807144 hasConcept C41008148 @default.
- W2169807144 hasConcept C49781872 @default.
- W2169807144 hasConcept C61224824 @default.
- W2169807144 hasConcept C62520636 @default.
- W2169807144 hasConcept C75553542 @default.
- W2169807144 hasConcept C9810830 @default.
- W2169807144 hasConceptScore W2169807144C105795698 @default.
- W2169807144 hasConceptScore W2169807144C111472728 @default.
- W2169807144 hasConceptScore W2169807144C119857082 @default.
- W2169807144 hasConceptScore W2169807144C121332964 @default.
- W2169807144 hasConceptScore W2169807144C138885662 @default.
- W2169807144 hasConceptScore W2169807144C153180895 @default.
- W2169807144 hasConceptScore W2169807144C154945302 @default.
- W2169807144 hasConceptScore W2169807144C163716315 @default.
- W2169807144 hasConceptScore W2169807144C167966045 @default.
- W2169807144 hasConceptScore W2169807144C23224414 @default.
- W2169807144 hasConceptScore W2169807144C28490314 @default.
- W2169807144 hasConceptScore W2169807144C33923547 @default.
- W2169807144 hasConceptScore W2169807144C39890363 @default.
- W2169807144 hasConceptScore W2169807144C41008148 @default.
- W2169807144 hasConceptScore W2169807144C49781872 @default.
- W2169807144 hasConceptScore W2169807144C61224824 @default.
- W2169807144 hasConceptScore W2169807144C62520636 @default.
- W2169807144 hasConceptScore W2169807144C75553542 @default.
- W2169807144 hasConceptScore W2169807144C9810830 @default.
- W2169807144 hasLocation W21698071441 @default.
- W2169807144 hasOpenAccess W2169807144 @default.
- W2169807144 hasPrimaryLocation W21698071441 @default.
- W2169807144 hasRelatedWork W1003237493 @default.
- W2169807144 hasRelatedWork W1491106928 @default.
- W2169807144 hasRelatedWork W1941791870 @default.
- W2169807144 hasRelatedWork W2018630598 @default.
- W2169807144 hasRelatedWork W2037429745 @default.
- W2169807144 hasRelatedWork W2075546197 @default.
- W2169807144 hasRelatedWork W2082346139 @default.
- W2169807144 hasRelatedWork W2115387603 @default.
- W2169807144 hasRelatedWork W2116257577 @default.
- W2169807144 hasRelatedWork W2117325244 @default.
- W2169807144 hasRelatedWork W2123638790 @default.
- W2169807144 hasRelatedWork W2147722939 @default.
- W2169807144 hasRelatedWork W2153281657 @default.
- W2169807144 hasRelatedWork W2155089829 @default.
- W2169807144 hasRelatedWork W2166993553 @default.
- W2169807144 hasRelatedWork W2170563926 @default.
- W2169807144 hasRelatedWork W2912975777 @default.
- W2169807144 hasRelatedWork W3117828977 @default.
- W2169807144 hasRelatedWork W3166668000 @default.
- W2169807144 hasRelatedWork W3178047715 @default.
- W2169807144 isParatext "false" @default.
- W2169807144 isRetracted "false" @default.
- W2169807144 magId "2169807144" @default.
- W2169807144 workType "article" @default.