Matches in SemOpenAlex for { <https://semopenalex.org/work/W2023161323> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W2023161323 endingPage "41" @default.
- W2023161323 startingPage "35" @default.
- W2023161323 abstract "The application of learning algorithms to big datasets has been identified for a long time as an effective way to attack important tasks in pattern recognition, but the generation of large annotated datasets has a significant cost. We present a simple and effective method to generate a classifier of face images, by training a linear classification algorithm on a massive dataset entirely assembled and labelled by automated means. In doing so, we perform the largest experiment on face gender recognition so far published, reporting the highest performance yet. Four million images and more than 60,000 features are used to train online classifiers. By using an ensemble of linear classifiers, we achieve an accuracy of 96.86% on the most challenging public database, labelled faces in the wild (LFW), 2.05% higher than the previous best result on the same dataset (Shan, 2012). This result is relevant both for the machine learning community, addressing the role of large datasets, and the computer vision community, providing a way to make high quality face gender classifiers. Furthermore, we propose a general way to generate and exploit massive data without human annotation. Finally, we demonstrate a simple and effective adaptation of the Pegasos that makes it more robust." @default.
- W2023161323 created "2016-06-24" @default.
- W2023161323 creator A5032465079 @default.
- W2023161323 creator A5083307694 @default.
- W2023161323 date "2015-06-01" @default.
- W2023161323 modified "2023-10-13" @default.
- W2023161323 title "Learning to classify gender from four million images" @default.
- W2023161323 cites W1997011019 @default.
- W2023161323 cites W2020944503 @default.
- W2023161323 cites W2101392314 @default.
- W2023161323 cites W2103018059 @default.
- W2023161323 cites W2119486225 @default.
- W2023161323 cites W2149494055 @default.
- W2023161323 cites W2158617780 @default.
- W2023161323 cites W2163352848 @default.
- W2023161323 cites W3097096317 @default.
- W2023161323 cites W33524118 @default.
- W2023161323 doi "https://doi.org/10.1016/j.patrec.2015.02.006" @default.
- W2023161323 hasPublicationYear "2015" @default.
- W2023161323 type Work @default.
- W2023161323 sameAs 2023161323 @default.
- W2023161323 citedByCount "59" @default.
- W2023161323 countsByYear W20231613232015 @default.
- W2023161323 countsByYear W20231613232016 @default.
- W2023161323 countsByYear W20231613232017 @default.
- W2023161323 countsByYear W20231613232018 @default.
- W2023161323 countsByYear W20231613232019 @default.
- W2023161323 countsByYear W20231613232020 @default.
- W2023161323 countsByYear W20231613232021 @default.
- W2023161323 countsByYear W20231613232022 @default.
- W2023161323 countsByYear W20231613232023 @default.
- W2023161323 crossrefType "journal-article" @default.
- W2023161323 hasAuthorship W2023161323A5032465079 @default.
- W2023161323 hasAuthorship W2023161323A5083307694 @default.
- W2023161323 hasConcept C119857082 @default.
- W2023161323 hasConcept C144024400 @default.
- W2023161323 hasConcept C153180895 @default.
- W2023161323 hasConcept C154945302 @default.
- W2023161323 hasConcept C165696696 @default.
- W2023161323 hasConcept C2776321320 @default.
- W2023161323 hasConcept C2779304628 @default.
- W2023161323 hasConcept C31510193 @default.
- W2023161323 hasConcept C36289849 @default.
- W2023161323 hasConcept C38652104 @default.
- W2023161323 hasConcept C41008148 @default.
- W2023161323 hasConcept C95623464 @default.
- W2023161323 hasConceptScore W2023161323C119857082 @default.
- W2023161323 hasConceptScore W2023161323C144024400 @default.
- W2023161323 hasConceptScore W2023161323C153180895 @default.
- W2023161323 hasConceptScore W2023161323C154945302 @default.
- W2023161323 hasConceptScore W2023161323C165696696 @default.
- W2023161323 hasConceptScore W2023161323C2776321320 @default.
- W2023161323 hasConceptScore W2023161323C2779304628 @default.
- W2023161323 hasConceptScore W2023161323C31510193 @default.
- W2023161323 hasConceptScore W2023161323C36289849 @default.
- W2023161323 hasConceptScore W2023161323C38652104 @default.
- W2023161323 hasConceptScore W2023161323C41008148 @default.
- W2023161323 hasConceptScore W2023161323C95623464 @default.
- W2023161323 hasLocation W20231613231 @default.
- W2023161323 hasOpenAccess W2023161323 @default.
- W2023161323 hasPrimaryLocation W20231613231 @default.
- W2023161323 hasRelatedWork W1496222301 @default.
- W2023161323 hasRelatedWork W1590307681 @default.
- W2023161323 hasRelatedWork W2098693229 @default.
- W2023161323 hasRelatedWork W2353836703 @default.
- W2023161323 hasRelatedWork W2358353312 @default.
- W2023161323 hasRelatedWork W2384651879 @default.
- W2023161323 hasRelatedWork W3207760230 @default.
- W2023161323 hasRelatedWork W41015297 @default.
- W2023161323 hasRelatedWork W4285370786 @default.
- W2023161323 hasRelatedWork W4312814274 @default.
- W2023161323 hasVolume "58" @default.
- W2023161323 isParatext "false" @default.
- W2023161323 isRetracted "false" @default.
- W2023161323 magId "2023161323" @default.
- W2023161323 workType "article" @default.