Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386460438> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4386460438 endingPage "301" @default.
- W4386460438 startingPage "294" @default.
- W4386460438 abstract "Image captioning is a growing topic of research in which numerous advancements have been made in the past few years. Deep learning methods have been used extensively for generating textual descriptions of image data. In addition, attention-based image captioning mechanisms have also been proposed, which give state-ofthe- art results in image captioning. However, many applications and analyses of these methodologies have not been made in the case of languages from the Indian subcontinent. This paper presents attention-based merge architecture models to achieve accurate captions of images in four Indian languages- Marathi, Kannada, Malayalam, and Tamil. The widely known Flickr8K dataset was used for this project. Pre-trained Convolutional Neural Network (CNN) models and language decoder attention models were implemented, which serve as the components of the mergearchitecture proposed here. Finally, the accuracy of the generated captions was compared against the gold captions using Bilingual Evaluation Understudy (BLEU) as an evaluation metric. It was observed that the merge architectures consisting of InceptionV3 give the best results for the languages we test on, the scores discussed in the paper. Highest BLEU-1 scores obtained for each language were: 0.4939 for Marathi, 0.4557 for Kannada, 0.5082 for Malayalam, and 0.5201 for Tamil. Our proposed architectures gave much higher scores than other architectures implemented for these languages." @default.
- W4386460438 created "2023-09-06" @default.
- W4386460438 creator A5022514940 @default.
- W4386460438 creator A5032244320 @default.
- W4386460438 creator A5032763492 @default.
- W4386460438 creator A5056992470 @default.
- W4386460438 creator A5076040193 @default.
- W4386460438 date "2023-09-01" @default.
- W4386460438 modified "2023-09-27" @default.
- W4386460438 title "Evaluating Performances of Attention-Based Merge Architecture Models for Image Captioning in Indian Languages" @default.
- W4386460438 doi "https://doi.org/10.18178/joig.11.3.294-301" @default.
- W4386460438 hasPublicationYear "2023" @default.
- W4386460438 type Work @default.
- W4386460438 citedByCount "0" @default.
- W4386460438 crossrefType "journal-article" @default.
- W4386460438 hasAuthorship W4386460438A5022514940 @default.
- W4386460438 hasAuthorship W4386460438A5032244320 @default.
- W4386460438 hasAuthorship W4386460438A5032763492 @default.
- W4386460438 hasAuthorship W4386460438A5056992470 @default.
- W4386460438 hasAuthorship W4386460438A5076040193 @default.
- W4386460438 hasBestOaLocation W43864604381 @default.
- W4386460438 hasConcept C115961682 @default.
- W4386460438 hasConcept C138885662 @default.
- W4386460438 hasConcept C140688305 @default.
- W4386460438 hasConcept C154945302 @default.
- W4386460438 hasConcept C157657479 @default.
- W4386460438 hasConcept C197129107 @default.
- W4386460438 hasConcept C204321447 @default.
- W4386460438 hasConcept C23123220 @default.
- W4386460438 hasConcept C2776844415 @default.
- W4386460438 hasConcept C2779662586 @default.
- W4386460438 hasConcept C28490314 @default.
- W4386460438 hasConcept C41008148 @default.
- W4386460438 hasConcept C41895202 @default.
- W4386460438 hasConceptScore W4386460438C115961682 @default.
- W4386460438 hasConceptScore W4386460438C138885662 @default.
- W4386460438 hasConceptScore W4386460438C140688305 @default.
- W4386460438 hasConceptScore W4386460438C154945302 @default.
- W4386460438 hasConceptScore W4386460438C157657479 @default.
- W4386460438 hasConceptScore W4386460438C197129107 @default.
- W4386460438 hasConceptScore W4386460438C204321447 @default.
- W4386460438 hasConceptScore W4386460438C23123220 @default.
- W4386460438 hasConceptScore W4386460438C2776844415 @default.
- W4386460438 hasConceptScore W4386460438C2779662586 @default.
- W4386460438 hasConceptScore W4386460438C28490314 @default.
- W4386460438 hasConceptScore W4386460438C41008148 @default.
- W4386460438 hasConceptScore W4386460438C41895202 @default.
- W4386460438 hasIssue "3" @default.
- W4386460438 hasLocation W43864604381 @default.
- W4386460438 hasOpenAccess W4386460438 @default.
- W4386460438 hasPrimaryLocation W43864604381 @default.
- W4386460438 hasRelatedWork W1990387993 @default.
- W4386460438 hasRelatedWork W2011442016 @default.
- W4386460438 hasRelatedWork W3028954259 @default.
- W4386460438 hasRelatedWork W3134916539 @default.
- W4386460438 hasRelatedWork W3153739492 @default.
- W4386460438 hasRelatedWork W3184477063 @default.
- W4386460438 hasRelatedWork W359020983 @default.
- W4386460438 hasRelatedWork W4296612768 @default.
- W4386460438 hasRelatedWork W2282668075 @default.
- W4386460438 hasRelatedWork W2408288895 @default.
- W4386460438 hasVolume "11" @default.
- W4386460438 isParatext "false" @default.
- W4386460438 isRetracted "false" @default.
- W4386460438 workType "article" @default.