Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380928635> ?p ?o ?g. }
- W4380928635 endingPage "102736" @default.
- W4380928635 startingPage "102736" @default.
- W4380928635 abstract "The Walter Havighurst Special Collections from University Archives & Preservation at Miami University's King Library has a growing collection of over 600,000 historical postcards, with approximately 30,000 digitized, primarily from the Midwest during 1890–1919. This collection supports various lines of inquiry from users, such as analyzing the evolution of gender portrayal in popular media in the United States. However, manually separating the collection into postcards of males and females would take thousands of hours, which prevents the library from supporting sociological analyses at scale. After assembling an open postcard dataset, we trained deep neural networks (i.e., YOLOv5x object detection models) to automatically detect people and classify them as male or female. Our approach limited biases in favor of one outcome by balancing the number of males and females via multi-label stratified 10-fold cross-validation. We showed that this approach can accurately detect and classify females and confidently detect and label males for the library's collection of historical postcards. Our precision of 94.9 % and recall of 33.0 % from 1890 to 1919 on male gender detection exceed the performances of 94.7 % and 31 % respectively for recognition on World War I postcards in past studies. By employing our trained deep neural networks, the library can enhance its metadata within hours and support new research inquiries at scale." @default.
- W4380928635 created "2023-06-17" @default.
- W4380928635 creator A5007766930 @default.
- W4380928635 creator A5023496425 @default.
- W4380928635 creator A5031126502 @default.
- W4380928635 creator A5092187347 @default.
- W4380928635 creator A5092187348 @default.
- W4380928635 date "2023-07-01" @default.
- W4380928635 modified "2023-09-25" @default.
- W4380928635 title "Enabling new interactions with library digital collections: automatic gender recognition in historical postcards via deep learning" @default.
- W4380928635 cites W1141054642 @default.
- W4380928635 cites W1941659294 @default.
- W4380928635 cites W2034328419 @default.
- W4380928635 cites W2043184227 @default.
- W4380928635 cites W2075295687 @default.
- W4380928635 cites W2184867623 @default.
- W4380928635 cites W2342249984 @default.
- W4380928635 cites W2395579298 @default.
- W4380928635 cites W2398891160 @default.
- W4380928635 cites W2731793484 @default.
- W4380928635 cites W2765669831 @default.
- W4380928635 cites W2796310778 @default.
- W4380928635 cites W2805194238 @default.
- W4380928635 cites W2954996726 @default.
- W4380928635 cites W2962949934 @default.
- W4380928635 cites W2976494420 @default.
- W4380928635 cites W2992511782 @default.
- W4380928635 cites W3041970497 @default.
- W4380928635 cites W3042131069 @default.
- W4380928635 cites W3083469718 @default.
- W4380928635 cites W3098609640 @default.
- W4380928635 cites W3099319035 @default.
- W4380928635 cites W3099878876 @default.
- W4380928635 cites W3118170868 @default.
- W4380928635 cites W3118218411 @default.
- W4380928635 cites W3152939161 @default.
- W4380928635 cites W3168997536 @default.
- W4380928635 cites W3171873561 @default.
- W4380928635 cites W3206004017 @default.
- W4380928635 cites W4210598935 @default.
- W4380928635 cites W4248083651 @default.
- W4380928635 cites W4293353514 @default.
- W4380928635 cites W4311524776 @default.
- W4380928635 doi "https://doi.org/10.1016/j.acalib.2023.102736" @default.
- W4380928635 hasPublicationYear "2023" @default.
- W4380928635 type Work @default.
- W4380928635 citedByCount "0" @default.
- W4380928635 crossrefType "journal-article" @default.
- W4380928635 hasAuthorship W4380928635A5007766930 @default.
- W4380928635 hasAuthorship W4380928635A5023496425 @default.
- W4380928635 hasAuthorship W4380928635A5031126502 @default.
- W4380928635 hasAuthorship W4380928635A5092187347 @default.
- W4380928635 hasAuthorship W4380928635A5092187348 @default.
- W4380928635 hasConcept C108583219 @default.
- W4380928635 hasConcept C124952713 @default.
- W4380928635 hasConcept C136764020 @default.
- W4380928635 hasConcept C142362112 @default.
- W4380928635 hasConcept C154945302 @default.
- W4380928635 hasConcept C159390177 @default.
- W4380928635 hasConcept C161191863 @default.
- W4380928635 hasConcept C164913051 @default.
- W4380928635 hasConcept C205649164 @default.
- W4380928635 hasConcept C23123220 @default.
- W4380928635 hasConcept C2606647 @default.
- W4380928635 hasConcept C2778755073 @default.
- W4380928635 hasConcept C2781238097 @default.
- W4380928635 hasConcept C2781293084 @default.
- W4380928635 hasConcept C39432304 @default.
- W4380928635 hasConcept C41008148 @default.
- W4380928635 hasConcept C513874922 @default.
- W4380928635 hasConcept C58640448 @default.
- W4380928635 hasConcept C93518851 @default.
- W4380928635 hasConceptScore W4380928635C108583219 @default.
- W4380928635 hasConceptScore W4380928635C124952713 @default.
- W4380928635 hasConceptScore W4380928635C136764020 @default.
- W4380928635 hasConceptScore W4380928635C142362112 @default.
- W4380928635 hasConceptScore W4380928635C154945302 @default.
- W4380928635 hasConceptScore W4380928635C159390177 @default.
- W4380928635 hasConceptScore W4380928635C161191863 @default.
- W4380928635 hasConceptScore W4380928635C164913051 @default.
- W4380928635 hasConceptScore W4380928635C205649164 @default.
- W4380928635 hasConceptScore W4380928635C23123220 @default.
- W4380928635 hasConceptScore W4380928635C2606647 @default.
- W4380928635 hasConceptScore W4380928635C2778755073 @default.
- W4380928635 hasConceptScore W4380928635C2781238097 @default.
- W4380928635 hasConceptScore W4380928635C2781293084 @default.
- W4380928635 hasConceptScore W4380928635C39432304 @default.
- W4380928635 hasConceptScore W4380928635C41008148 @default.
- W4380928635 hasConceptScore W4380928635C513874922 @default.
- W4380928635 hasConceptScore W4380928635C58640448 @default.
- W4380928635 hasConceptScore W4380928635C93518851 @default.
- W4380928635 hasIssue "4" @default.
- W4380928635 hasLocation W43809286351 @default.
- W4380928635 hasOpenAccess W4380928635 @default.
- W4380928635 hasPrimaryLocation W43809286351 @default.
- W4380928635 hasRelatedWork W1894445701 @default.
- W4380928635 hasRelatedWork W1965294778 @default.
- W4380928635 hasRelatedWork W2001774700 @default.