{"id":"https://openalex.org/W7125767149","doi":"https://doi.org/10.1007/s42979-025-04676-w","title":"Advancing Bengali Vision-Language Comprehension: A Deep Learning and NLP Paradigm for Image Captioning","display_name":"Advancing Bengali Vision-Language Comprehension: A Deep Learning and NLP Paradigm for Image Captioning","publication_year":2026,"publication_date":"2026-01-27","ids":{"openalex":"https://openalex.org/W7125767149","doi":"https://doi.org/10.1007/s42979-025-04676-w"},"language":"en","primary_location":{"id":"doi:10.1007/s42979-025-04676-w","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s42979-025-04676-w","pdf_url":null,"source":{"id":"https://openalex.org/S4210174798","display_name":"SN Computer Science","issn_l":"2661-8907","issn":["2661-8907","2662-995X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SN Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124012731","display_name":"Dipankar Dey","orcid":null},"institutions":[{"id":"https://openalex.org/I175399479","display_name":"Haldia Institute of Technology","ror":"https://ror.org/0211bs523","country_code":"IN","type":"education","lineage":["https://openalex.org/I175399479"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dipankar Dey","raw_affiliation_strings":["Global Institute of Science and Technology, Haldia, West Bengal, India"],"raw_orcid":"https://orcid.org/0000-0003-4872-9901","affiliations":[{"raw_affiliation_string":"Global Institute of Science and Technology, Haldia, West Bengal, India","institution_ids":["https://openalex.org/I175399479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073249271","display_name":"Dipak Kumar Jana","orcid":"https://orcid.org/0000-0003-2297-6576"},"institutions":[{"id":"https://openalex.org/I175399479","display_name":"Haldia Institute of Technology","ror":"https://ror.org/0211bs523","country_code":"IN","type":"education","lineage":["https://openalex.org/I175399479"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Dipak Kumar Jana","raw_affiliation_strings":["School of Applied Science and Humanities, Haldia Institute of Technology, Haldia, 721657, India"],"raw_orcid":"https://orcid.org/0000-0003-2297-6576","affiliations":[{"raw_affiliation_string":"School of Applied Science and Humanities, Haldia Institute of Technology, Haldia, 721657, India","institution_ids":["https://openalex.org/I175399479"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124046765","display_name":"Prajna Bhunia","orcid":null},"institutions":[{"id":"https://openalex.org/I175399479","display_name":"Haldia Institute of Technology","ror":"https://ror.org/0211bs523","country_code":"IN","type":"education","lineage":["https://openalex.org/I175399479"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prajna Bhunia","raw_affiliation_strings":["Global Institute of Science and Technology, Haldia, West Bengal, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Global Institute of Science and Technology, Haldia, West Bengal, India","institution_ids":["https://openalex.org/I175399479"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5073249271"],"corresponding_institution_ids":["https://openalex.org/I175399479"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14246479,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bengali","display_name":"Bengali","score":0.9732999801635742},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.858299970626831},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6704999804496765},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6478999853134155},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5676000118255615},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.4327000081539154},{"id":"https://openalex.org/keywords/paraphrase","display_name":"Paraphrase","score":0.42410001158714294}],"concepts":[{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.9732999801635742},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.858299970626831},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7789999842643738},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7508000135421753},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6704999804496765},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6664999723434448},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6478999853134155},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5676000118255615},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.4327000081539154},{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.42410001158714294},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.38530001044273376},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3292999863624573},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.26159998774528503},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s42979-025-04676-w","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s42979-025-04676-w","pdf_url":null,"source":{"id":"https://openalex.org/S4210174798","display_name":"SN Computer Science","issn_l":"2661-8907","issn":["2661-8907","2662-995X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SN Computer Science","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1998237531","https://openalex.org/W2020509198","https://openalex.org/W2901083258","https://openalex.org/W2932402324","https://openalex.org/W3012159041","https://openalex.org/W3017078175","https://openalex.org/W3034124732","https://openalex.org/W3180896826","https://openalex.org/W3182816087","https://openalex.org/W3216197972","https://openalex.org/W4292424911","https://openalex.org/W4293328686","https://openalex.org/W4296008866","https://openalex.org/W4298112168","https://openalex.org/W4304891204","https://openalex.org/W4321080401","https://openalex.org/W4366979886","https://openalex.org/W4382930509","https://openalex.org/W4401690668"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-05-01T08:36:08.643496","created_date":"2026-01-28T00:00:00"}
