Matches in SemOpenAlex for { <https://semopenalex.org/work/W2913460068> ?p ?o ?g. }
- W2913460068 endingPage "258" @default.
- W2913460068 startingPage "249" @default.
- W2913460068 abstract "Most facial verification methods assume that training and testing sets contain independent and identically distributed samples, although, in many real applications, this assumption does not hold. Whenever gathering a representative dataset in the target domain is unfeasible, it is necessary to choose one of the already available (source domain) datasets. Here, a study was performed over the differences among six public datasets, and how this impacts on the performance of the learned methods. In the considered scenario of mobile devices, the individual of interest is enrolled using a few facial images taken in the operational domain, while training impostors are drawn from one of the public available datasets. This work tried to shed light on the inherent differences among the datasets, and potential harms that should be considered when they are combined for training and testing. Results indicate that a drop in performance occurs whenever training and testing are done on different datasets compared to the case of using the same dataset in both phases. However, the decay strongly depends on the kind of features. Besides, the representation of samples in the feature space reveals insights into what extent bias is an endogenous or an exogenous factor." @default.
- W2913460068 created "2019-02-21" @default.
- W2913460068 creator A5007784230 @default.
- W2913460068 creator A5045280371 @default.
- W2913460068 creator A5072735859 @default.
- W2913460068 creator A5079260249 @default.
- W2913460068 creator A5086413658 @default.
- W2913460068 date "2019-02-20" @default.
- W2913460068 modified "2023-09-27" @default.
- W2913460068 title "Dataset bias exposed in face verification" @default.
- W2913460068 cites W170472577 @default.
- W2913460068 cites W1722318740 @default.
- W2913460068 cites W1852255964 @default.
- W2913460068 cites W1916406603 @default.
- W2913460068 cites W1949778830 @default.
- W2913460068 cites W1950843348 @default.
- W2913460068 cites W1975056068 @default.
- W2913460068 cites W1997011019 @default.
- W2913460068 cites W2024922353 @default.
- W2913460068 cites W2031342017 @default.
- W2913460068 cites W2087681821 @default.
- W2913460068 cites W2104068492 @default.
- W2913460068 cites W2108598243 @default.
- W2913460068 cites W2136863438 @default.
- W2913460068 cites W2148350243 @default.
- W2913460068 cites W2163352848 @default.
- W2913460068 cites W2194775991 @default.
- W2913460068 cites W2311523351 @default.
- W2913460068 cites W2325939864 @default.
- W2913460068 cites W2344769595 @default.
- W2913460068 cites W2526851297 @default.
- W2913460068 cites W2539476124 @default.
- W2913460068 cites W2593768305 @default.
- W2913460068 cites W2735096401 @default.
- W2913460068 cites W2736633948 @default.
- W2913460068 cites W2757251151 @default.
- W2913460068 cites W2767339058 @default.
- W2913460068 cites W2786185081 @default.
- W2913460068 cites W2790791591 @default.
- W2913460068 cites W2806655962 @default.
- W2913460068 cites W2919115771 @default.
- W2913460068 cites W2962997291 @default.
- W2913460068 cites W2963495263 @default.
- W2913460068 cites W2964228922 @default.
- W2913460068 cites W2964288524 @default.
- W2913460068 cites W3099206234 @default.
- W2913460068 doi "https://doi.org/10.1049/iet-bmt.2018.5224" @default.
- W2913460068 hasPublicationYear "2019" @default.
- W2913460068 type Work @default.
- W2913460068 sameAs 2913460068 @default.
- W2913460068 citedByCount "10" @default.
- W2913460068 countsByYear W29134600682019 @default.
- W2913460068 countsByYear W29134600682020 @default.
- W2913460068 countsByYear W29134600682021 @default.
- W2913460068 countsByYear W29134600682022 @default.
- W2913460068 crossrefType "journal-article" @default.
- W2913460068 hasAuthorship W2913460068A5007784230 @default.
- W2913460068 hasAuthorship W2913460068A5045280371 @default.
- W2913460068 hasAuthorship W2913460068A5072735859 @default.
- W2913460068 hasAuthorship W2913460068A5079260249 @default.
- W2913460068 hasAuthorship W2913460068A5086413658 @default.
- W2913460068 hasBestOaLocation W29134600682 @default.
- W2913460068 hasConcept C119857082 @default.
- W2913460068 hasConcept C124101348 @default.
- W2913460068 hasConcept C134306372 @default.
- W2913460068 hasConcept C138885662 @default.
- W2913460068 hasConcept C144024400 @default.
- W2913460068 hasConcept C153180895 @default.
- W2913460068 hasConcept C154945302 @default.
- W2913460068 hasConcept C17744445 @default.
- W2913460068 hasConcept C199539241 @default.
- W2913460068 hasConcept C27206212 @default.
- W2913460068 hasConcept C2776145971 @default.
- W2913460068 hasConcept C2776359362 @default.
- W2913460068 hasConcept C2776401178 @default.
- W2913460068 hasConcept C2779304628 @default.
- W2913460068 hasConcept C33923547 @default.
- W2913460068 hasConcept C36289849 @default.
- W2913460068 hasConcept C36503486 @default.
- W2913460068 hasConcept C41008148 @default.
- W2913460068 hasConcept C41895202 @default.
- W2913460068 hasConcept C512654426 @default.
- W2913460068 hasConcept C51632099 @default.
- W2913460068 hasConcept C83665646 @default.
- W2913460068 hasConcept C94625758 @default.
- W2913460068 hasConceptScore W2913460068C119857082 @default.
- W2913460068 hasConceptScore W2913460068C124101348 @default.
- W2913460068 hasConceptScore W2913460068C134306372 @default.
- W2913460068 hasConceptScore W2913460068C138885662 @default.
- W2913460068 hasConceptScore W2913460068C144024400 @default.
- W2913460068 hasConceptScore W2913460068C153180895 @default.
- W2913460068 hasConceptScore W2913460068C154945302 @default.
- W2913460068 hasConceptScore W2913460068C17744445 @default.
- W2913460068 hasConceptScore W2913460068C199539241 @default.
- W2913460068 hasConceptScore W2913460068C27206212 @default.
- W2913460068 hasConceptScore W2913460068C2776145971 @default.
- W2913460068 hasConceptScore W2913460068C2776359362 @default.
- W2913460068 hasConceptScore W2913460068C2776401178 @default.