{"id":"https://openalex.org/W7125797546","doi":"https://doi.org/10.1109/icit64950.2025.11049167","title":"A Transformer-Based Deep Learning Model for Arabic Image Captioning","display_name":"A Transformer-Based Deep Learning Model for Arabic Image Captioning","publication_year":2025,"publication_date":"2025-05-27","ids":{"openalex":"https://openalex.org/W7125797546","doi":"https://doi.org/10.1109/icit64950.2025.11049167"},"language":null,"primary_location":{"id":"doi:10.1109/icit64950.2025.11049167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icit64950.2025.11049167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 12th International Conference on Information Technology (ICIT)","raw_type":"proceedings-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/A5123899782","display_name":"Israa Al Badarneh","orcid":null},"institutions":[{"id":"https://openalex.org/I114972647","display_name":"University of Jordan","ror":"https://ror.org/05k89ew48","country_code":"JO","type":"education","lineage":["https://openalex.org/I114972647"]}],"countries":["JO"],"is_corresponding":false,"raw_author_name":"Israa Al Badarneh","raw_affiliation_strings":["The University of Jordan,King Abdullah II School of Information Technology,Amman,Jordan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Jordan,King Abdullah II School of Information Technology,Amman,Jordan","institution_ids":["https://openalex.org/I114972647"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124027612","display_name":"Bassam H. Hammo","orcid":null},"institutions":[{"id":"https://openalex.org/I114972647","display_name":"University of Jordan","ror":"https://ror.org/05k89ew48","country_code":"JO","type":"education","lineage":["https://openalex.org/I114972647"]}],"countries":["JO"],"is_corresponding":false,"raw_author_name":"Bassam H. Hammo","raw_affiliation_strings":["The University of Jordan,King Abdullah II School of Information Technology,Amman,Jordan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Jordan,King Abdullah II School of Information Technology,Amman,Jordan","institution_ids":["https://openalex.org/I114972647"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124003927","display_name":"Omar Al-Kadi","orcid":null},"institutions":[{"id":"https://openalex.org/I114972647","display_name":"University of Jordan","ror":"https://ror.org/05k89ew48","country_code":"JO","type":"education","lineage":["https://openalex.org/I114972647"]}],"countries":["JO"],"is_corresponding":false,"raw_author_name":"Omar Al-Kadi","raw_affiliation_strings":["The University of Jordan,King Abdullah II School of Information Technology,Amman,Jordan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Jordan,King Abdullah II School of Information Technology,Amman,Jordan","institution_ids":["https://openalex.org/I114972647"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62374986,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"410","last_page":"415"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9943000078201294,"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":0.9943000078201294,"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/T10028","display_name":"Topic Modeling","score":0.0006000000284984708,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0005000000237487257,"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":0.9513999819755554},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7289000153541565},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6309000253677368},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5001999735832214},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4749000072479248},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.41499999165534973},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.3846000134944916},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.37229999899864197}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9513999819755554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7876999974250793},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7289000153541565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7127000093460083},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6309000253677368},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5001999735832214},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4875999987125397},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4749000072479248},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.41499999165534973},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.3846000134944916},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.37229999899864197},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3495999872684479},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3125},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2687000036239624},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.26339998841285706},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icit64950.2025.11049167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icit64950.2025.11049167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 12th International Conference on Information Technology (ICIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8798019289970398,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Image":[0,31],"captioning":[1],"is":[2],"a":[3,36,46,61],"crucial":[4],"process":[5],"that":[6],"connects":[7],"text":[8],"to":[9,64],"images.":[10],"Transformer-based":[11],"deep":[12,37],"learning":[13,38,58],"models":[14],"have":[15],"successfully":[16],"created":[17],"captions,":[18],"especially":[19],"for":[20,29,42,50],"Arabic.":[21],"This":[22],"paper":[23],"introduces":[24],"the":[25,66,69,79],"Attention-Based":[26],"Transformer":[27],"Model":[28],"Arabic":[30],"Captioning":[32],"(ARTIC),":[33],"which":[34],"uses":[35,55],"convolutional":[39],"neural":[40],"network":[41],"feature":[43],"extraction":[44],"and":[45,83,91],"transformer":[47],"encoder-decoder":[48],"architecture":[49],"textual":[51],"captions.":[52],"The":[53,76],"model":[54,77],"an":[56],"ensemble":[57],"approach":[59],"with":[60,68],"voting":[62],"mechanism":[63],"select":[65],"caption":[67],"highest":[70],"bilingual":[71],"evaluation":[72],"understudy":[73],"(BLEU)":[74],"score.":[75],"achieved":[78,93],"best":[80],"BLEU-1,":[81],"CIDEr,":[82],"ROUGE":[84],"scores,":[85],"while":[86],"other":[87],"metrics":[88],"like":[89],"BLEU-2":[90],"METEOR":[92],"competitive":[94],"rates.":[95]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-01-28T00:00:00"}