{"id":"https://openalex.org/W4417201627","doi":"https://doi.org/10.1109/access.2025.3642465","title":"Knowledge-Driven Image Captioning","display_name":"Knowledge-Driven Image Captioning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4417201627","doi":"https://doi.org/10.1109/access.2025.3642465"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3642465","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3642465","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3642465","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054155672","display_name":"Anwar ul Haque","orcid":"https://orcid.org/0000-0002-0188-2653"},"institutions":[{"id":"https://openalex.org/I134784518","display_name":"Institute of Business Administration Karachi","ror":"https://ror.org/03egfpm06","country_code":"PK","type":"education","lineage":["https://openalex.org/I134784518"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Anwar Ul Haque","raw_affiliation_strings":["SMCS, Institute of Business Administration (IBA), Karachi, Pakistan","SMCS, IBA, Karachi, Pakistan"],"raw_orcid":"https://orcid.org/0000-0002-0188-2653","affiliations":[{"raw_affiliation_string":"SMCS, Institute of Business Administration (IBA), Karachi, Pakistan","institution_ids":["https://openalex.org/I134784518"]},{"raw_affiliation_string":"SMCS, IBA, Karachi, Pakistan","institution_ids":["https://openalex.org/I134784518"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037233730","display_name":"Sayeed Ghani","orcid":"https://orcid.org/0000-0003-2938-2789"},"institutions":[{"id":"https://openalex.org/I134784518","display_name":"Institute of Business Administration Karachi","ror":"https://ror.org/03egfpm06","country_code":"PK","type":"education","lineage":["https://openalex.org/I134784518"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Sayeed Ghani","raw_affiliation_strings":["SMCS, Institute of Business Administration (IBA), Karachi, Pakistan","SMCS, IBA, Karachi, Pakistan"],"raw_orcid":"https://orcid.org/0000-0003-2938-2789","affiliations":[{"raw_affiliation_string":"SMCS, Institute of Business Administration (IBA), Karachi, Pakistan","institution_ids":["https://openalex.org/I134784518"]},{"raw_affiliation_string":"SMCS, IBA, Karachi, Pakistan","institution_ids":["https://openalex.org/I134784518"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101776229","display_name":"Muhammad Arif Saeed","orcid":"https://orcid.org/0000-0002-6818-7858"},"institutions":[{"id":"https://openalex.org/I193670377","display_name":"University of Karachi","ror":"https://ror.org/05bbbc791","country_code":"PK","type":"education","lineage":["https://openalex.org/I193670377"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Saeed","raw_affiliation_strings":["Department of Computer Science, University of Karachi, Karachi, Pakistan"],"raw_orcid":"https://orcid.org/0000-0002-6818-7858","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Karachi, Karachi, Pakistan","institution_ids":["https://openalex.org/I193670377"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.5588,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.71393869,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"13","issue":null,"first_page":"211352","last_page":"211369"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9926000237464905,"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":0.9926000237464905,"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/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"}},{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0010000000474974513,"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":0.8899000287055969},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6676999926567078},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4498000144958496},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.41440001130104065},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.414000004529953},{"id":"https://openalex.org/keywords/storytelling","display_name":"Storytelling","score":0.3991999924182892},{"id":"https://openalex.org/keywords/knowledge-based-systems","display_name":"Knowledge-based systems","score":0.3605000078678131},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.35429999232292175}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8899000287055969},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8422999978065491},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6676999926567078},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5562000274658203},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4693000018596649},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4498000144958496},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.41440001130104065},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.414000004529953},{"id":"https://openalex.org/C2776538412","wikidata":"https://www.wikidata.org/wiki/Q989963","display_name":"Storytelling","level":3,"score":0.3991999924182892},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.3605000078678131},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3562999963760376},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.34619998931884766},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3416000008583069},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C85407183","wikidata":"https://www.wikidata.org/wiki/Q1045785","display_name":"Semantic network","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.28299999237060547},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2703000009059906},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26089999079704285},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3642465","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3642465","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:4d984343c0354ac5a487af9f52b4be4c","is_oa":true,"landing_page_url":"https://doaj.org/article/4d984343c0354ac5a487af9f52b4be4c","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 211352-211369 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3642465","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3642465","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,95,111,144,162,182],"human":[1],"ability":[2],"to":[3,24,46,103,173],"detect,":[4],"understand,":[5],"and":[6,34,59,73,76,87,109,118,133,135,141,149,159,166,177],"contextualize":[7],"objects":[8],"in":[9,28],"the":[10,100,115,119,169,174,189],"real":[11],"world":[12],"has":[13],"long":[14],"been":[15],"a":[16,37,48],"dream":[17],"for":[18,66,71,80,123,195],"computer":[19],"scientists,":[20],"who":[21],"have":[22],"sought":[23],"replicate":[25],"this":[26,42],"capability":[27],"machines.":[29],"Image":[30],"captioning":[31],"with":[32,106,152],"context":[33,74,150],"content":[35,72,148],"is":[36,97,128,180,188],"significant":[38],"research":[39,187],"problem.":[40],"In":[41],"work,":[43],"we":[44],"attempted":[45],"develop":[47],"storytelling":[49],"system":[50],"that":[51],"can":[52],"caption":[53],"images,":[54],"considering":[55],"content,":[56,107],"context,":[57,108],"syntax,":[58],"knowledge.":[60],"Our":[61,126],"methodology":[62],"combines":[63,114],"Capsule":[64,93],"Networks":[65,79],"image":[67],"encoding,":[68],"Knowledge":[69,101,116],"Graphs":[70],"awareness,":[75],"Transformer":[77,120],"Neural":[78,121],"decoding.":[81],"During":[82],"feature":[83],"extraction,":[84],"spatial,":[85],"geometrical,":[86],"orientational":[88],"details":[89],"are":[90],"extracted":[91],"using":[92],"Networks.":[94],"corpus":[96],"passed":[98],"through":[99],"Graph":[102,117],"equip":[104],"it":[105],"semantics.":[110],"decoding":[112],"phase":[113],"Network":[122],"knowledge-driven":[124],"captioning.":[125],"model":[127],"trained":[129],"on":[130,137],"MSCOCO,":[131,138],"Flickr8k,":[132,139],"Flickr32k,":[134,140],"tested":[136],"Google":[142],"Images.":[143],"results":[145],"provide":[146],"good":[147],"understanding":[151],"B4:":[153],"49.97,":[154],"M:":[155],"39.14,":[156],"C:":[157],"136.53,":[158],"R:":[160],"74.61.":[161],"usage":[163],"of":[164,185,191],"adverbs":[165],"adjectives":[167],"within":[168],"generated":[170],"sentence,":[171],"according":[172],"objects\u2019":[175],"geometrical":[176],"semantic":[178],"relationship,":[179],"phenomenal.":[181],"primary":[183],"outcome":[184],"our":[186],"generation":[190],"autonomous":[192],"story-type":[193],"captions":[194],"real-world":[196],"images.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-12-10T00:00:00"}