{"id":"https://openalex.org/W4392903201","doi":"https://doi.org/10.1109/icassp48485.2024.10447637","title":"Improved Image Captioning Via Knowledge Graph-Augmented Models","display_name":"Improved Image Captioning Via Knowledge Graph-Augmented Models","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903201","doi":"https://doi.org/10.1109/icassp48485.2024.10447637"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5071583172","display_name":"Sergio S\u00e1nchez Santiesteban","orcid":null},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sergio S\u00e1nchez Santiesteban","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,United Kingdom,GU2 7XH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,United Kingdom,GU2 7XH","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111136893","display_name":"Sara Atito","orcid":null},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sara Atito","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,United Kingdom,GU2 7XH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,United Kingdom,GU2 7XH","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100778579","display_name":"Muhammad Awais","orcid":"https://orcid.org/0000-0002-1122-0709"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Muhammad Awais","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,United Kingdom,GU2 7XH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,United Kingdom,GU2 7XH","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046046128","display_name":"Yi-Zhe Song","orcid":"https://orcid.org/0000-0001-5908-3275"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yi-Zhe Song","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,United Kingdom,GU2 7XH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,United Kingdom,GU2 7XH","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028209738","display_name":"Josef Kittler","orcid":"https://orcid.org/0000-0002-8110-9205"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Josef Kittler","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,United Kingdom,GU2 7XH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,United Kingdom,GU2 7XH","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4290","last_page":"4294"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9926999807357788,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9825000166893005,"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":0.839260995388031},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.831555962562561},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.666764497756958},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.5845533013343811},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.5670042634010315},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.544577419757843},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.527472198009491},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5202128291130066},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.518817126750946},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4872569143772125},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.47201722860336304},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4618135690689087},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45012167096138},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.44519856572151184},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3743389844894409},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3431764245033264},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2822255492210388},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.12531372904777527},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1135982871055603}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.839260995388031},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.831555962562561},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.666764497756958},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.5845533013343811},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.5670042634010315},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.544577419757843},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.527472198009491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5202128291130066},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.518817126750946},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4872569143772125},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.47201722860336304},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4618135690689087},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45012167096138},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44519856572151184},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3743389844894409},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3431764245033264},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2822255492210388},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.12531372904777527},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1135982871055603},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1889081078","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2154652894","https://openalex.org/W2561529111","https://openalex.org/W2745461083","https://openalex.org/W2896457183","https://openalex.org/W2904565150","https://openalex.org/W2914629512","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3094502228","https://openalex.org/W3104279398","https://openalex.org/W3124149278","https://openalex.org/W3173220247","https://openalex.org/W3173909648","https://openalex.org/W3176750236","https://openalex.org/W3193402170","https://openalex.org/W4226321975","https://openalex.org/W4282968790","https://openalex.org/W4283009931","https://openalex.org/W4287236261","https://openalex.org/W4297733535","https://openalex.org/W4386072307","https://openalex.org/W6639432524","https://openalex.org/W6755207826","https://openalex.org/W6784333009","https://openalex.org/W6789705400","https://openalex.org/W6789753369","https://openalex.org/W6800139874","https://openalex.org/W6839220867","https://openalex.org/W6840952533"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W4292070284","https://openalex.org/W4386298164","https://openalex.org/W4312933959","https://openalex.org/W4287644835","https://openalex.org/W3092281475","https://openalex.org/W4229080059","https://openalex.org/W3098003361","https://openalex.org/W4286257253","https://openalex.org/W2916853871"],"abstract_inverted_index":{"Multimodal":[0],"foundation":[1],"models,":[2],"pre-trained":[3],"on":[4,112,124],"large-scale":[5],"data,":[6],"effectively":[7],"capture":[8,34],"vast":[9],"amounts":[10],"of":[11,49],"factual":[12],"and":[13,30,41,46,89,103],"commonsense":[14],"knowledge.":[15,36],"However,":[16],"these":[17],"models":[18,29,102,110],"store":[19],"all":[20],"their":[21,24],"knowledge":[22,55,73,81],"within":[23],"parameters,":[25],"requiring":[26],"increasingly":[27],"larger":[28,109],"training":[31],"data":[32],"to":[33,66,82,107],"more":[35,44,113],"To":[37],"address":[38],"this":[39],"limitation":[40],"achieve":[42],"a":[43,53,62,120,134],"scalable":[45],"modular":[47],"integration":[48],"knowledge,":[50],"we":[51],"propose":[52],"novel":[54],"graph-augmented":[56],"multimodal":[57,64],"model.":[58],"This":[59],"approach":[60],"enables":[61],"base":[63],"model":[65,99,118,137],"access":[67],"pertinent":[68],"information":[69],"from":[70],"an":[71],"external":[72],"graph.":[74],"Our":[75],"methodology":[76],"leverages":[77],"existing":[78],"general":[79],"domain":[80],"facilitate":[83],"vision-language":[84],"pre-training":[85],"using":[86,128],"paired":[87],"images":[88],"text":[90],"descriptions.":[91],"We":[92],"conduct":[93],"comprehensive":[94],"evaluations":[95],"demonstrating":[96],"that":[97],"our":[98,117],"outperforms":[100],"state-of-the-art":[101],"yields":[104],"comparable":[105],"results":[106],"much":[108],"trained":[111],"extensive":[114],"datasets.":[115],"Notably,":[116],"reached":[119],"145":[121],"Cider":[122],"score":[123],"MS":[125],"COCO":[126],"Captions":[127],"only":[129],"2.9":[130],"million":[131],"samples,":[132],"outperforming":[133],"1.4B":[135],"parameter":[136],"by":[138],"1.7%":[139],"despite":[140],"having":[141],"11":[142],"times":[143],"fewer":[144],"parameters.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}