{"id":"https://openalex.org/W4416037776","doi":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.56","title":"VLCAP at ImageEval 2025 Shared Task: Multimodal Arabic Captioning with Interpretable Visual Concept Integration","display_name":"VLCAP at ImageEval 2025 Shared Task: Multimodal Arabic Captioning with Interpretable Visual Concept Integration","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416037776","doi":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.56"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.arabicnlp-sharedtasks.56","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.56","pdf_url":"https://aclanthology.org/2025.arabicnlp-sharedtasks.56.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.arabicnlp-sharedtasks.56.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114408266","display_name":"Passant Elchafei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Passant Elchafei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5067503166","display_name":"Amany Fashwan","orcid":"https://orcid.org/0009-0005-8091-8405"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amany Fashwan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9349,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80831087,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"408","last_page":"413"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9872000217437744,"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":0.9872000217437744,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.00279999990016222,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.0013000000035390258,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8446000218391418},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4361000061035156},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.37459999322891235},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.3325999975204468},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.3158999979496002},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.28119999170303345}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8446000218391418},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6739000082015991},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5839999914169312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5182999968528748},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4361000061035156},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3046000003814697},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2865000069141388},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.25850000977516174}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.arabicnlp-sharedtasks.56","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.56","pdf_url":"https://aclanthology.org/2025.arabicnlp-sharedtasks.56.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.arabicnlp-sharedtasks.56","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.56","pdf_url":"https://aclanthology.org/2025.arabicnlp-sharedtasks.56.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416037776.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}
