Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896838691> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W2896838691 abstract "Kinship verification based on facial images is one of the popular research topic in the field of face recognition. It's still a challenging problem due to many inevitable factors, such as varying illumination, poses, and expressions. And traditional handcrafted features are usually not robust enough. For the above reasons, in this paper, we extract kernel features by Convolutional Kernel Networks (CKN), which are invariant to particular transformations. After extracting the CKN features, we use feature bagging to classify. It's an ensemble learning method that attempts to reduce the correlation between estimators in an ensemble by training them on random samples of features instead of the entire feature set. Specifically, the CKN features are randomly sampled to train an SVM classifier each time, and then multiple SVM classifiers are combined by majority voting to make prediction. In addition, we collect a large kinship face dataset named LarG-KinFace from Internet search under uncontrolled conditions. The proposed method is evaluated on three datasets KinFaceW-I, KinFaceW-II, and LarG-KinFace. Experimental results demonstrate the efficacy of the proposed method." @default.
- W2896838691 created "2018-10-26" @default.
- W2896838691 creator A5024892154 @default.
- W2896838691 creator A5088132899 @default.
- W2896838691 creator A5091577686 @default.
- W2896838691 date "2018-07-01" @default.
- W2896838691 modified "2023-10-16" @default.
- W2896838691 title "Ensemble Learning Based on Convolutional Kernel Networks Features for Kinship Verification" @default.
- W2896838691 cites W1572187623 @default.
- W2896838691 cites W1906145078 @default.
- W2896838691 cites W1996337501 @default.
- W2896838691 cites W2007972795 @default.
- W2896838691 cites W2012783213 @default.
- W2896838691 cites W2079742827 @default.
- W2896838691 cites W2108909793 @default.
- W2896838691 cites W2112999064 @default.
- W2896838691 cites W2130073327 @default.
- W2896838691 cites W2132886138 @default.
- W2896838691 cites W2145773134 @default.
- W2896838691 cites W2164322079 @default.
- W2896838691 cites W2679426462 @default.
- W2896838691 cites W3035305153 @default.
- W2896838691 cites W4212883601 @default.
- W2896838691 doi "https://doi.org/10.1109/icme.2018.8486585" @default.
- W2896838691 hasPublicationYear "2018" @default.
- W2896838691 type Work @default.
- W2896838691 sameAs 2896838691 @default.
- W2896838691 citedByCount "2" @default.
- W2896838691 countsByYear W28968386912019 @default.
- W2896838691 countsByYear W28968386912022 @default.
- W2896838691 crossrefType "proceedings-article" @default.
- W2896838691 hasAuthorship W2896838691A5024892154 @default.
- W2896838691 hasAuthorship W2896838691A5088132899 @default.
- W2896838691 hasAuthorship W2896838691A5091577686 @default.
- W2896838691 hasConcept C114614502 @default.
- W2896838691 hasConcept C119857082 @default.
- W2896838691 hasConcept C144348335 @default.
- W2896838691 hasConcept C154945302 @default.
- W2896838691 hasConcept C17744445 @default.
- W2896838691 hasConcept C199539241 @default.
- W2896838691 hasConcept C33923547 @default.
- W2896838691 hasConcept C41008148 @default.
- W2896838691 hasConcept C45942800 @default.
- W2896838691 hasConcept C74193536 @default.
- W2896838691 hasConceptScore W2896838691C114614502 @default.
- W2896838691 hasConceptScore W2896838691C119857082 @default.
- W2896838691 hasConceptScore W2896838691C144348335 @default.
- W2896838691 hasConceptScore W2896838691C154945302 @default.
- W2896838691 hasConceptScore W2896838691C17744445 @default.
- W2896838691 hasConceptScore W2896838691C199539241 @default.
- W2896838691 hasConceptScore W2896838691C33923547 @default.
- W2896838691 hasConceptScore W2896838691C41008148 @default.
- W2896838691 hasConceptScore W2896838691C45942800 @default.
- W2896838691 hasConceptScore W2896838691C74193536 @default.
- W2896838691 hasLocation W28968386911 @default.
- W2896838691 hasOpenAccess W2896838691 @default.
- W2896838691 hasPrimaryLocation W28968386911 @default.
- W2896838691 hasRelatedWork W2810053714 @default.
- W2896838691 hasRelatedWork W2883828728 @default.
- W2896838691 hasRelatedWork W2941606940 @default.
- W2896838691 hasRelatedWork W3005055299 @default.
- W2896838691 hasRelatedWork W4200126462 @default.
- W2896838691 hasRelatedWork W4200409985 @default.
- W2896838691 hasRelatedWork W4281560664 @default.
- W2896838691 hasRelatedWork W4281757034 @default.
- W2896838691 hasRelatedWork W4285741730 @default.
- W2896838691 hasRelatedWork W4292969247 @default.
- W2896838691 isParatext "false" @default.
- W2896838691 isRetracted "false" @default.
- W2896838691 magId "2896838691" @default.
- W2896838691 workType "article" @default.