Multitype Learning via Multimodal Data Embedding

dc.authorscopusid57289197300
dc.authorscopusid57288694000
dc.authorscopusid58353740700
dc.authorscopusid55364564400
dc.authorscopusid6506505859
dc.contributor.authorArsan, Taner
dc.contributor.authorSafdil, E.B.
dc.contributor.authorArslan, F.
dc.contributor.authorAlsan, H.F.
dc.contributor.authorArsan, T.
dc.date.accessioned2023-10-19T15:05:37Z
dc.date.available2023-10-19T15:05:37Z
dc.date.issued2021
dc.department-tempYildiz, E., Kadir Has University, Department of Computer Engineering, Istanbul, Turkey; Safdil, E.B., Kadir Has University, Department of Computer Engineering, Istanbul, Turkey; Arslan, F., Kadir Has University, Department of Computer Engineering, Istanbul, Turkey; Alsan, H.F., Kadir Has University, Department of Computer Engineering, Istanbul, Turkey; Arsan, T., Kadir Has University, Department of Computer Engineering, Istanbul, Turkeyen_US
dc.description5h International Symposium on Multidisciplinary Studies and Innovative Technologies, ISMSIT 2021 --21 October 2021 through 23 October 2021 -- --174473en_US
dc.description.abstractThis paper creates a multimodal retrieval system for image and text data in a multi-type learning approach that enables text-to-image, image-to-text, text-to-text, and image-to-image retrievals. As a practical solution, a mobile application is developed in which the users can upload their images to search a description sentence for the images. The user system is created on the application, which is done with React Native, and crucial features like e-mail authentication and reset password options are added to the application. An essential database system is designed with PostgreSQL to store user information and search for the user. The multimodal embedding study is worked, and the model that recognizes multitype retrievals is formed. The image-to-text retrieval model, which is our application's idea, is applied to the mobile application. © 2021 IEEE.en_US
dc.identifier.citation0
dc.identifier.doi10.1109/ISMSIT52890.2021.9604738en_US
dc.identifier.endpage461en_US
dc.identifier.isbn9781665449304
dc.identifier.scopus2-s2.0-85123309356en_US
dc.identifier.scopusqualityN/A
dc.identifier.startpage457en_US
dc.identifier.urihttps://doi.org/10.1109/ISMSIT52890.2021.9604738
dc.identifier.urihttps://hdl.handle.net/20.500.12469/4969
dc.identifier.wosqualityN/A
dc.khas20231019-Scopusen_US
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.ispartofISMSIT 2021 - 5th International Symposium on Multidisciplinary Studies and Innovative Technologies, Proceedingsen_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectConvolutional Networksen_US
dc.subjectCross-Modal Learningen_US
dc.subjectDeep Learningen_US
dc.subjectLong-Short Term Memory (LSTM)en_US
dc.subjectMobile Applicationen_US
dc.subjectMultimodal Retrievalen_US
dc.subjectReact Nativeen_US
dc.subjectAuthenticationen_US
dc.subjectConvolutional neural networksen_US
dc.subjectEmbeddingsen_US
dc.subjectInformation retrievalen_US
dc.subjectMobile computingen_US
dc.subjectSearch enginesen_US
dc.subjectConvolutional networksen_US
dc.subjectCross-modalen_US
dc.subjectCross-modal learningen_US
dc.subjectDeep learningen_US
dc.subjectLong-short term memoryen_US
dc.subjectMobile applicationsen_US
dc.subjectMulti-modalen_US
dc.subjectMultimodal retrievalen_US
dc.subjectMultitypeen_US
dc.subjectReact nativeen_US
dc.subjectLong short-term memoryen_US
dc.titleMultitype Learning via Multimodal Data Embeddingen_US
dc.typeConference Objecten_US
dspace.entity.typePublication
relation.isAuthorOfPublication7959ea6c-1b30-4fa0-9c40-6311259c0914
relation.isAuthorOfPublication.latestForDiscovery7959ea6c-1b30-4fa0-9c40-6311259c0914

Files

Original bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
4969.pdf
Size:
1.8 MB
Format:
Adobe Portable Document Format
Description:
Tam Metin / Full Text