UICD: A new dataset and approach for urdu image captioning
PLOS One · 02.06.2025 · 20 (6) · e0320701
DOI: 10.1371/journal.pone.0320701 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 02.06.2025. Verfasst von Rimsha Muzaffar und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of CS&IT, Mirpur University of Science and Technology (MUST), Mirpur-10250 (AJK), Pakistan. Hauptthemen laut MEDLINE: Deep Learning, Image Processing, Computer-Assisted, Language. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 83 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: South Korean Ministry of Science and ICT, South Korean Ministry of Trade, Industry & Energy.
Abstract (Originalsprache)
Advancements in deep learning have revolutionized numerous real-world applications, including image recognition, visual question answering, and image captioning. Among these, image captioning has emerged as a critical area of research, with substantial progress achieved in Arabic, Chinese, Uyghur, Hindi, and predominantly English. However, despite Urdu being a morphologically rich and widely spoken language, research in Urdu image captioning remains underexplored due to a lack of resources. This study creates a new Urdu Image Captioning Dataset (UCID) called UC-23-RY to fill in the gaps in Urdu image captioning. The Flickr30k dataset inspired the 159,816 Urdu captions in the dataset. Additionally, it suggests deep learning architectures designed especially for Urdu image captioning, including NASNetLarge-LSTM and ResNet-50-LSTM. The NASNetLarge-LSTM and ResNet-50-LSTM models achieved notable BLEU-1 scores of 0.86 and 0.84 respectively, as demonstrated through evaluation in this study accessing the model’s impact on caption quality. Additionally, it provides useful datasets and shows how well-suited sophisticated deep learning models are for improving automatic Urdu image captioning.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of CS&IT, Mirpur University of Science and Technology (MUST), Mirpur-10250 (AJK), Pakistan.
- Department of Artificial Intelligence and Data Science, Sejong University, Seoul, Republic of Korea.
- Department of Computer Science and Engineering, Inha University, Incheon, Republic of Korea.
- School of Computing, Macquarie University, Sydney, Australia.
ORCID-Profile: Rimsha Muzaffar, Junaid Rashid
Förderung
- South Korean Ministry of Science and ICT
- South Korean Ministry of Trade, Industry & Energy
Zitieren
APA
Muzaffar, R., Arafat, S. Y., Rashid, J., Kim, J., & Naseem, U. (2025). UICD: A new dataset and approach for urdu image captioning. PLOS One, 20(6), e0320701. https://doi.org/10.1371/journal.pone.0320701
Vancouver
Muzaffar R, Arafat SY, Rashid J, Kim J, Naseem U. UICD: A new dataset and approach for urdu image captioning. PLOS One. 2025;20(6):e0320701. doi:10.1371/journal.pone.0320701
BibTeX
@article{Muzaffar2025,
author = {Muzaffar, Rimsha and Arafat, Syed Yasser and Rashid, Junaid and Kim, Jungeun and Naseem, Usman},
title = {UICD: A new dataset and approach for urdu image captioning},
journal = {PLOS One},
year = {2025},
volume = {20},
number = {6},
pages = {e0320701},
doi = {10.1371/journal.pone.0320701}
}
EUVIMED