{"id":"https://openalex.org/W7139960428","doi":"https://doi.org/10.1016/j.procs.2026.01.055","title":"Modular Arabic VQA System Using Pre-Trained Models","display_name":"Modular Arabic VQA System Using Pre-Trained Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7139960428","doi":"https://doi.org/10.1016/j.procs.2026.01.055"},"language":"en","primary_location":{"id":"doi:10.1016/j.procs.2026.01.055","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.01.055","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1016/j.procs.2026.01.055","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130222496","display_name":"Shahad Alshalawi","orcid":null},"institutions":[{"id":"https://openalex.org/I185163786","display_name":"King Abdulaziz University","ror":"https://ror.org/02ma4wv74","country_code":"SA","type":"education","lineage":["https://openalex.org/I185163786"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Shahad Alshalawi","raw_affiliation_strings":["Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia","institution_ids":["https://openalex.org/I185163786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045265992","display_name":"Amal Almansour","orcid":"https://orcid.org/0000-0001-6689-4666"},"institutions":[{"id":"https://openalex.org/I185163786","display_name":"King Abdulaziz University","ror":"https://ror.org/02ma4wv74","country_code":"SA","type":"education","lineage":["https://openalex.org/I185163786"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Amal Almansour","raw_affiliation_strings":["Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia","institution_ids":["https://openalex.org/I185163786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073697159","display_name":"Amani Jamal","orcid":"https://orcid.org/0000-0001-9725-7985"},"institutions":[{"id":"https://openalex.org/I185163786","display_name":"King Abdulaziz University","ror":"https://ror.org/02ma4wv74","country_code":"SA","type":"education","lineage":["https://openalex.org/I185163786"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Amani Jamal","raw_affiliation_strings":["Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia","institution_ids":["https://openalex.org/I185163786"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5130222496"],"corresponding_institution_ids":["https://openalex.org/I185163786"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93617601,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"275","issue":null,"first_page":"455","last_page":"463"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.07150000333786011,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.07150000333786011,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0714000016450882,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.061000000685453415,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8794000148773193},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.771399974822998},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.7190999984741211},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.559499979019165},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.503600001335144},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.48010000586509705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9052000045776367},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8794000148773193},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.771399974822998},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7190999984741211},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6582000255584717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5741000175476074},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.559499979019165},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.503600001335144},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.48010000586509705},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.43959999084472656},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.37070000171661377},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.30959999561309814},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.26249998807907104}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.procs.2026.01.055","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.01.055","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.procs.2026.01.055","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.01.055","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2101105183","https://openalex.org/W2560730294","https://openalex.org/W2745461083","https://openalex.org/W2947312908","https://openalex.org/W2963176022","https://openalex.org/W2966683369","https://openalex.org/W2998356391","https://openalex.org/W3099655892","https://openalex.org/W3116506157","https://openalex.org/W3199693760","https://openalex.org/W4309734222","https://openalex.org/W4360828194","https://openalex.org/W4385574156","https://openalex.org/W4386076140","https://openalex.org/W4389009503","https://openalex.org/W4389518385","https://openalex.org/W4407667962","https://openalex.org/W4411113196"],"related_works":[],"abstract_inverted_index":{"This":[0,126],"paper":[1],"presents":[2],"Modular":[3,171],"Arabic":[4,50,135,172],"Visual":[5],"Question":[6],"Answering":[7],"(VQA),":[8],"a":[9,14,69],"novel":[10],"system":[11,46,174],"that":[12,28,93],"leverages":[13],"language-mediated":[15,134],"framework":[16],"to":[17,59,117,123,156],"perform":[18],"open-ended":[19],"VQA":[20,87,136,173],"task":[21],"in":[22,119],"Arabic.":[23],"Unlike":[24],"traditional":[25],"vision-language":[26],"models":[27],"rely":[29],"on":[30,83],"multimodal":[31],"pretraining":[32],"and":[33,49,57,90,137,163],"dense":[34],"visual":[35,95,147,162],"embeddings,":[36],"our":[37],"approach":[38],"represents":[39],"images":[40],"entirely":[41],"through":[42],"natural":[43],"language.":[44],"The":[45,103,166],"integrates":[47],"multilingual":[48,146],"image":[51,62],"captioning":[52],"models,":[53],"namely":[54],"AraBERT32-Flickr8k,":[55],"Violet,":[56],"GPT-4o,":[58],"generate":[60],"context-rich":[61],"descriptions,":[63],"which":[64],"are":[65],"then":[66],"processed":[67],"by":[68],"frozen":[70],"large":[71],"language":[72],"model":[73],"(LLM),":[74],"Gemini":[75,110],"1.5":[76,111],"Flash,":[77,112],"for":[78,145,178],"answer":[79],"generation.":[80],"Experimental":[81],"results":[82],"two":[84],"large-scale":[85],"Arabic-translated":[86],"datasets,":[88],"VQAv2-ar":[89],"OKVQA-ar,":[91],"demonstrate":[92],"replacing":[94],"embeddings":[96],"with":[97,109],"text-based":[98],"captions":[99,108],"significantly":[100],"enhances":[101],"performance.":[102],"best":[104],"configuration,":[105],"combining":[106],"GPT-4o":[107],"achieved":[113],"improvements":[114],"of":[115,133,141,169],"up":[116],"9.5%":[118],"Fuzz":[120],"Accuracy":[121],"compared":[122],"visual-token-based":[124],"baseline.":[125],"study":[127],"provides":[128],"the":[129,139,170],"first":[130],"comprehensive":[131],"evaluation":[132],"highlights":[138],"potential":[140],"modular,":[142],"text-driven":[143],"designs":[144],"reasoning.":[148],"Future":[149],"directions":[150],"include":[151],"developing":[152],"question-conditioned":[153],"caption":[154],"generation":[155],"further":[157],"strengthen":[158],"contextual":[159],"alignment":[160],"between":[161],"linguistic":[164],"cues.":[165],"complete":[167],"implementation":[168],"is":[175],"publicly":[176],"released":[177],"research":[179],"purposes":[180],"1":[181],".":[182]},"counts_by_year":[],"updated_date":"2026-03-22T06:25:25.174409","created_date":"2026-03-21T00:00:00"}
