Image captioning in Bengali language using visual attention.
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 a...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0309364 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850040552342421504 |
|---|---|
| author | Adiba Masud Md Biplob Hosen Md Habibullah Mehrin Anannya M Shamim Kaiser |
| author_facet | Adiba Masud Md Biplob Hosen Md Habibullah Mehrin Anannya M Shamim Kaiser |
| author_sort | Adiba Masud |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-3a67bca91d624c88bac5ef4cc867c798 |
| institution | DOAJ |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-3a67bca91d624c88bac5ef4cc867c7982025-08-20T02:56:03ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01202e030936410.1371/journal.pone.0309364Image captioning in Bengali language using visual attention.Adiba MasudMd Biplob HosenMd HabibullahMehrin AnannyaM Shamim KaiserAutomatically 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.https://doi.org/10.1371/journal.pone.0309364 |
| spellingShingle | Adiba Masud Md Biplob Hosen Md Habibullah Mehrin Anannya M Shamim Kaiser Image captioning in Bengali language using visual attention. PLoS ONE |
| title | Image captioning in Bengali language using visual attention. |
| title_full | Image captioning in Bengali language using visual attention. |
| title_fullStr | Image captioning in Bengali language using visual attention. |
| title_full_unstemmed | Image captioning in Bengali language using visual attention. |
| title_short | Image captioning in Bengali language using visual attention. |
| title_sort | image captioning in bengali language using visual attention |
| url | https://doi.org/10.1371/journal.pone.0309364 |
| work_keys_str_mv | AT adibamasud imagecaptioninginbengalilanguageusingvisualattention AT mdbiplobhosen imagecaptioninginbengalilanguageusingvisualattention AT mdhabibullah imagecaptioninginbengalilanguageusingvisualattention AT mehrinanannya imagecaptioninginbengalilanguageusingvisualattention AT mshamimkaiser imagecaptioninginbengalilanguageusingvisualattention |