EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Image captioning in Bengali language using visual attention

Adiba Masud iD, Md Biplob Hosen, Md Habibullah, Mehrin Anannya, M Shamim Kaiser

PLOS ONE · 2025

DOI: 10.1371/journal.pone.0309364 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, 2025. Verfasst von Adiba Masud und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Information Technology, Jahangirnagar University, Dhaka, Bangladesh. Hauptthemen laut MEDLINE: Language, Attention, Natural Language Processing, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automatically generating image captions poses one of the most challenging applications within artificial intelligence due to its integration of computer vision and natural language processing algorithms. This task becomes notably more formidable when dealing with a language as intricate as Bengali and the overall scarcity of Bengali-captioned image databases. In this investigation, a meticulously human-annotated dataset of Bengali captions has been curated specifically for the encompassing collection of pictures. Simultaneously, an innovative end-to-end architecture has been introduced to craft pertinent image descriptions in the Bengali language, leveraging an attention-driven decoder. Initially, the amalgamation of images’ spatial and temporal attributes is facilitated by Gated Recurrent Units, constituting the input features. These features are subsequently fed into the attention layer alongside embedded caption features. The attention mechanism scrutinizes the interrelation between visual and linguistic representations, encompassing both categories of representations. Later, a comprehensive recursive unit comprising two layers employs the amalgamated attention traits to construct coherent sentences. Utilizing our furnished dataset, this model undergoes training, culminating in achievements of a 43% BLEU-4 score, a 39% METEOR score, and a 47% ROUGE score. Compared to all preceding endeavors in Bengali image captioning, these outcomes signify the pinnacle of current attainable standards.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

LanguageAttentionNatural Language ProcessingImage Processing, Computer-AssistedHumansAlgorithmsArtificial Intelligence

Autor:innen und Institutionen

  • Institute of Information Technology, Jahangirnagar University, Dhaka, Bangladesh.
  • Department of Software Engineering, Daffodil International University, Dhaka, Bangladesh.

ORCID-Profile: Adiba Masud

Zitieren

APA

Masud, A., Hosen, M. B., Habibullah, M., Anannya, M., & Kaiser, M. S. (2025). Image captioning in Bengali language using visual attention. PLOS ONE. https://doi.org/10.1371/journal.pone.0309364

Vancouver

Masud A, Hosen MB, Habibullah M, Anannya M, Kaiser MS. Image captioning in Bengali language using visual attention. PLOS ONE. 2025. doi:10.1371/journal.pone.0309364

BibTeX
@article{Masud2025,
  author = {Masud, Adiba and Hosen, Md Biplob and Habibullah, Md and Anannya, Mehrin and Kaiser, M Shamim},
  title = {Image captioning in Bengali language using visual attention},
  journal = {PLOS ONE},
  year = {2025},
  doi = {10.1371/journal.pone.0309364}
}
Kostenlos starten →