{"id":"https://openalex.org/W7147559842","doi":"https://doi.org/10.1007/978-3-032-18474-0_8","title":"Vision-Language Integration for\u00a0Image Captioning Using Vision Transformers and\u00a0GPT-J","display_name":"Vision-Language Integration for\u00a0Image Captioning Using Vision Transformers and\u00a0GPT-J","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7147559842","doi":"https://doi.org/10.1007/978-3-032-18474-0_8"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-032-18474-0_8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-18474-0_8","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5132561467","display_name":"Ali Alfatemi","orcid":null},"institutions":[{"id":"https://openalex.org/I164389053","display_name":"Fordham University","ror":"https://ror.org/03qnxaf80","country_code":"US","type":"education","lineage":["https://openalex.org/I164389053"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Alfatemi","raw_affiliation_strings":["CIS Deptartment, Fordham University, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIS Deptartment, Fordham University, New York, NY, USA","institution_ids":["https://openalex.org/I164389053"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017529726","display_name":"Mohamed Rahouti","orcid":"https://orcid.org/0000-0001-9701-5505"},"institutions":[{"id":"https://openalex.org/I164389053","display_name":"Fordham University","ror":"https://ror.org/03qnxaf80","country_code":"US","type":"education","lineage":["https://openalex.org/I164389053"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohamed Rahouti","raw_affiliation_strings":["CIS Deptartment, Fordham University, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIS Deptartment, Fordham University, New York, NY, USA","institution_ids":["https://openalex.org/I164389053"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034854700","display_name":"Mohammed Aledhari","orcid":"https://orcid.org/0000-0002-5380-6003"},"institutions":[{"id":"https://openalex.org/I87573096","display_name":"University of North Texas at Dallas","ror":"https://ror.org/01n51v443","country_code":"US","type":"education","lineage":["https://openalex.org/I87573096"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammed Aledhari","raw_affiliation_strings":["Data Science Deptartment, University of North Texas, Dallas, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Science Deptartment, University of North Texas, Dallas, TX, USA","institution_ids":["https://openalex.org/I87573096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023985430","display_name":"Nasir Abdul Ghani","orcid":null},"institutions":[{"id":"https://openalex.org/I2613432","display_name":"University of South Florida","ror":"https://ror.org/032db5x82","country_code":"US","type":"education","lineage":["https://openalex.org/I2613432"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nasir Ghani","raw_affiliation_strings":["EE Deptartment, University of South Florida, Tampa, FL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EE Deptartment, University of South Florida, Tampa, FL, USA","institution_ids":["https://openalex.org/I2613432"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132605662","display_name":"Abdellah Chehri","orcid":null},"institutions":[{"id":"https://openalex.org/I51768193","display_name":"Royal Military College of Canada","ror":"https://ror.org/04yr71909","country_code":"CA","type":"education","lineage":["https://openalex.org/I51768193"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Abdellah Chehri","raw_affiliation_strings":["MCS Deptartment, Royal Military College of Canada, Kingston, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MCS Deptartment, Royal Military College of Canada, Kingston, Canada","institution_ids":["https://openalex.org/I51768193"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049449184","display_name":"Gwanggil Jeon","orcid":"https://orcid.org/0000-0002-0651-4278"},"institutions":[{"id":"https://openalex.org/I146429904","display_name":"Incheon National University","ror":"https://ror.org/02xf7p935","country_code":"KR","type":"education","lineage":["https://openalex.org/I146429904"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gwanggil Jeon","raw_affiliation_strings":["Embedded Systems Engineering Deptartment, Incheon National University, Incheon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Embedded Systems Engineering Deptartment, Incheon National University, Incheon, South Korea","institution_ids":["https://openalex.org/I146429904"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5132605662"],"corresponding_institution_ids":["https://openalex.org/I51768193"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.78463727,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"101","last_page":"114"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9865000247955322,"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":0.9865000247955322,"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":0.0015999999595806003,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.00139999995008111,"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/closed-captioning","display_name":"Closed captioning","score":0.9144999980926514},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7312999963760376},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6438999772071838},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.6434999704360962},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.40689998865127563},{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.3944999873638153},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.375900000333786}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9144999980926514},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8881000280380249},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7312999963760376},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6438999772071838},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6434999704360962},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49300000071525574},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4223000109195709},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.40689998865127563},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.3944999873638153},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.375900000333786},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.35600000619888306},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3253999948501587},{"id":"https://openalex.org/C200220432","wikidata":"https://www.wikidata.org/wiki/Q7936208","display_name":"Vision science","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2646999955177307},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.26409998536109924}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-032-18474-0_8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-18474-0_8","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49549105763435364,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W3035284526","https://openalex.org/W3110019360","https://openalex.org/W3114308765","https://openalex.org/W3167939936","https://openalex.org/W3168463823","https://openalex.org/W3171353004","https://openalex.org/W3192652975","https://openalex.org/W4225832925","https://openalex.org/W4226200183","https://openalex.org/W4283271696","https://openalex.org/W4286742008","https://openalex.org/W4389945963","https://openalex.org/W4394593185","https://openalex.org/W4404801468","https://openalex.org/W4404801487"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2026-04-02T00:00:00"}
