Detecting Errors in Automatic Image Captioning by Deep Learning;

dc.authorscopusid16637174900
dc.contributor.authorKarakaya, Kasım Murat
dc.contributor.otherComputer Engineering
dc.date.accessioned2024-07-05T15:46:17Z
dc.date.available2024-07-05T15:46:17Z
dc.date.issued2021
dc.departmentAtılım Universityen_US
dc.department-tempKarakaya M., Computer Engineering Dept., Atilim University, Ankara, Turkeyen_US
dc.description.abstractAutomatic tagging of images is an important researcli topic in tlie field of image processing. Anotlier area similar to this is the automatic generation of picture captions. In this study, a deep learning model that automatically tags the pictures is used to detect errors in image captions. As a result of the initial experiments, it is observed that the proposed system can find up to 80% of the errors in the image captions. © 2021 IEEEen_US
dc.identifier.citation0
dc.identifier.doi10.1109/UBMK52708.2021.9558968
dc.identifier.endpage49en_US
dc.identifier.isbn978-166542908-5
dc.identifier.scopus2-s2.0-85125834374
dc.identifier.startpage46en_US
dc.identifier.urihttps://doi.org/10.1109/UBMK52708.2021.9558968
dc.identifier.urihttps://hdl.handle.net/20.500.14411/4039
dc.institutionauthorKarakaya,M.
dc.language.isotren_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.ispartofProceedings - 6th International Conference on Computer Science and Engineering, UBMK 2021 -- 6th International Conference on Computer Science and Engineering, UBMK 2021 -- 15 September 2021 through 17 September 2021 -- Ankara -- 176826en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectCaptioningen_US
dc.subjectDeep learningen_US
dc.subjectDeep neural networksen_US
dc.subjectError detectionen_US
dc.subjectImage processingen_US
dc.subjectTaggingen_US
dc.titleDetecting Errors in Automatic Image Captioning by Deep Learning;en_US
dc.title.alternativeDerin Ögrenme ile Otomatik Olarak Üretilen Resim Alt Yazismdaki Hatalarm Tespitien_US
dc.typeConference Objecten_US
dspace.entity.typePublication
relation.isAuthorOfPublication93f27ee1-19eb-42dc-b4eb-a3cc7dc4b057
relation.isAuthorOfPublication.latestForDiscovery93f27ee1-19eb-42dc-b4eb-a3cc7dc4b057
relation.isOrgUnitOfPublicatione0809e2c-77a7-4f04-9cb0-4bccec9395fa
relation.isOrgUnitOfPublication.latestForDiscoverye0809e2c-77a7-4f04-9cb0-4bccec9395fa

Files

Collections