ORTPiece: An ORT-based Turkish image captioning network based on transformers and WordPiece

Name: ORTPiece: An ORT-based Turkish image captioning network based on transformers and WordPiece
Author: Ersoy, Asım, Yıldız, Olcay Taner, Özer, Sedat

İsim	ORTPiece: An ORT-based Turkish image captioning network based on transformers and WordPiece
Yazar	Ersoy, Asım, Yıldız, Olcay Taner, Özer, Sedat
Basım Tarihi:	2023
Basım Yeri	- IEEE
Konu	Object Relation Transformer, Transformer, Turkish Image captioning, WordPiece Tokenization
Tür	Belge
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	979-835034355-7
Kayıt Numarası	c5034de6-1a9c-41b6-b4fc-4179b15dac08
Lokasyon	Computer Science
Tarih	2023
Örnek Metin	Recent transformers-based systems are advancing image captioning applications. However, those works have been mainly applied to English-based image captioning problems. In this paper, we introduce a transformers-based Turkish-based image captioning algorithm. Our proposed algorithm uses appearance and geometry features from the input image and combines them along with the WordPiece embeddings to generate the Turkish-based caption. Our experimental results show improvement when compared to the other existing techniques including the original ORT and the show-and-tell algorithms.
DOI	10.1109/SIU59756.2023.10223956

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

ORTPiece: An ORT-based Turkish image captioning network based on transformers and WordPiece

Yazar Ersoy, Asım, Yıldız, Olcay Taner, Özer, Sedat

Basım Tarihi 2023

Basım Yeri - IEEE

Konu Object Relation Transformer, Transformer, Turkish Image captioning, WordPiece Tokenization

Tür Belge

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 979-835034355-7

Kayıt Numarası c5034de6-1a9c-41b6-b4fc-4179b15dac08

Lokasyon Computer Science

Tarih 2023

Örnek Metin Recent transformers-based systems are advancing image captioning applications. However, those works have been mainly applied to English-based image captioning problems. In this paper, we introduce a transformers-based Turkish-based image captioning algorithm. Our proposed algorithm uses appearance and geometry features from the input image and combines them along with the WordPiece embeddings to generate the Turkish-based caption. Our experimental results show improvement when compared to the other existing techniques including the original ORT and the show-and-tell algorithms.

DOI 10.1109/SIU59756.2023.10223956