A complete human verified Turkish caption dataset for MS COCO and performance evaluation with well-known image caption models trained against it

Basit Öğe Kaydı
dc.authorscopusid58069064700
dc.authorscopusid58068924000
dc.authorscopusid36782998200
dc.authorscopusid46061213000
dc.contributor.authorGolech, S.B.
dc.contributor.authorKaracan, S.B.
dc.contributor.authorSönmez, E.B.
dc.contributor.authorAyral, H.
dc.date.accessioned2024-07-18T20:17:05Z
dc.date.available2024-07-18T20:17:05Z
dc.date.issued2022
dc.description2022 International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2022 -- 16 November 2022 through 18 November 2022 -- -- 185686en_US
dc.description.abstractThe procedure of generating natural language captions for an image is known as image captioning. Automatic image captioning is a particularly challenging task that stands at the junction of Computer Vision and Natural Language Processing. It has a variety of applications, including text-based image retrieval, assisting visually impaired users, and human-robot interaction. The majority of publications on the subject focus on the English language, which is an analytical language with characteristics differing from the agglutinative Turkish language. This work introduces the Turkish MS COCO dataset that extends the original MS COCO collection with captions in the Turkish language; experimental results surpass the current state-of-the-art for the Turkish image captioning field. Furthermore, the newly introduced database is also applicable for the study of machine translation. On the Turkish MS COCO dataset, the best performance has been achieved with the Meshed Memory Transformers with a Bleu-1 score of 0.72. The database is publicly available at https://github.com/BilgiAILAB/TurkishImageCaptioning. It is desired that the Turkish MS COCO dataset with the proposed benchmark will be an excellent resource for future studies on Turkish image captioning. © 2022 IEEE.en_US
dc.description.sponsorshipWe thanks Istanbul Bilgi university for funding this project and Mr. Arda Sarıdog?an, Mr. Murat Emre Sancaklı, Mr. Samet C¸ elik, and undergraduate students of Istanbul Bilgi university, for their contribution in this work.en_US
dc.description.sponsorshipThanks for Istanbul Bilgi Univerity BAP commission for funding this project.en_US
dc.identifier.doi10.1109/ICECCME55909.2022.9988025
dc.identifier.isbn9781665470957
dc.identifier.scopus2-s2.0-85146415457en_US
dc.identifier.scopusqualityN/Aen_US
dc.identifier.urihttps://doi.org/10.1109/ICECCME55909.2022.9988025
dc.identifier.urihttps://hdl.handle.net/11411/6403
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.ispartofInternational Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2022en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectCnnen_US
dc.subjectComputer Visionen_US
dc.subjectDeep Neural Networksen_US
dc.subjectLstmen_US
dc.subjectNatural Language Processingen_US
dc.subjectRnnen_US
dc.subjectTransformersen_US
dc.subjectTurkish İmage Captioningen_US
dc.subjectTurkish Ms Coco Databaseen_US
dc.subjectComputer Visionen_US
dc.subjectDatabase Systemsen_US
dc.subjectHuman Robot İnteractionen_US
dc.subjectLong Short-Term Memoryen_US
dc.subjectNatural Language Processing Systemsen_US
dc.subjectPetroleum Reservoir Evaluationen_US
dc.subjectImage Captioningen_US
dc.subjectLanguage Processingen_US
dc.subjectLstmen_US
dc.subjectNatural Language Processingen_US
dc.subjectNatural Languagesen_US
dc.subjectRnnen_US
dc.subjectTransformeren_US
dc.subjectTurkish İmage Captioningen_US
dc.subjectTurkish Ms Coco Databaseen_US
dc.subjectTurkishsen_US
dc.subjectDeep Neural Networksen_US
dc.titleA complete human verified Turkish caption dataset for MS COCO and performance evaluation with well-known image caption models trained against it
dc.typeConference Object

Dosyalar

Koleksiyon

Scopus Indexed Publications