{"id":"https://openalex.org/W4406523865","doi":"https://doi.org/10.1109/fit63703.2024.10838438","title":"Medical Visual Question Answering using Contrastive Language-Image Pre-training","display_name":"Medical Visual Question Answering using Contrastive Language-Image Pre-training","publication_year":2024,"publication_date":"2024-12-09","ids":{"openalex":"https://openalex.org/W4406523865","doi":"https://doi.org/10.1109/fit63703.2024.10838438"},"language":"en","primary_location":{"id":"doi:10.1109/fit63703.2024.10838438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fit63703.2024.10838438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Frontiers of Information Technology (FIT)","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/A5115921063","display_name":"Zahra Khalid Butt","orcid":null},"institutions":[{"id":"https://openalex.org/I16076960","display_name":"COMSATS University Islamabad","ror":"https://ror.org/00nqqvk19","country_code":"PK","type":"education","lineage":["https://openalex.org/I16076960"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Zahra Khalid Butt","raw_affiliation_strings":["COMSATS University Islamabad,Department of Computer Science,Islamabad,Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"COMSATS University Islamabad,Department of Computer Science,Islamabad,Pakistan","institution_ids":["https://openalex.org/I16076960"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020271211","display_name":"Aiman Shahid Butt","orcid":"https://orcid.org/0000-0002-0397-2775"},"institutions":[{"id":"https://openalex.org/I16076960","display_name":"COMSATS University Islamabad","ror":"https://ror.org/00nqqvk19","country_code":"PK","type":"education","lineage":["https://openalex.org/I16076960"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Asma Khalid Butt","raw_affiliation_strings":["COMSATS University Islamabad,Department of Computer Science,Islamabad,Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"COMSATS University Islamabad,Department of Computer Science,Islamabad,Pakistan","institution_ids":["https://openalex.org/I16076960"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054034369","display_name":"Tehseen Zia","orcid":"https://orcid.org/0000-0001-8176-3373"},"institutions":[{"id":"https://openalex.org/I16076960","display_name":"COMSATS University Islamabad","ror":"https://ror.org/00nqqvk19","country_code":"PK","type":"education","lineage":["https://openalex.org/I16076960"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Tehseen Zia","raw_affiliation_strings":["COMSATS University Islamabad,Department of Computer Science,Islamabad,Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"COMSATS University Islamabad,Department of Computer Science,Islamabad,Pakistan","institution_ids":["https://openalex.org/I16076960"]}]},{"author_position":"last","author":{"id":null,"display_name":"Mutahra Khalid Butt","orcid":null},"institutions":[{"id":"https://openalex.org/I16076960","display_name":"COMSATS University Islamabad","ror":"https://ror.org/00nqqvk19","country_code":"PK","type":"education","lineage":["https://openalex.org/I16076960"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Mutahra Khalid Butt","raw_affiliation_strings":["COMSATS University Islamabad,Department of Computer Science,Islamabad,Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"COMSATS University Islamabad,Department of Computer Science,Islamabad,Pakistan","institution_ids":["https://openalex.org/I16076960"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16076960"],"apc_list":null,"apc_paid":null,"fwci":0.7888,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79626887,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9775999784469604,"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":0.9775999784469604,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9318000078201294,"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/computer-science","display_name":"Computer science","score":0.7899686694145203},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7527633905410767},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6597132682800293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6122859120368958},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3503792881965637}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7899686694145203},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7527633905410767},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6597132682800293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6122859120368958},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3503792881965637},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fit63703.2024.10838438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fit63703.2024.10838438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Frontiers of Information Technology (FIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2108598243","https://openalex.org/W2152772232","https://openalex.org/W2516809705","https://openalex.org/W2777186991","https://openalex.org/W2896457183","https://openalex.org/W2901466771","https://openalex.org/W2979525559","https://openalex.org/W3094950914","https://openalex.org/W3165058054","https://openalex.org/W3203255640","https://openalex.org/W3204544513","https://openalex.org/W4295917908","https://openalex.org/W4304092130","https://openalex.org/W4379879090","https://openalex.org/W4386352883","https://openalex.org/W4392207614","https://openalex.org/W6637373629","https://openalex.org/W6769627184","https://openalex.org/W6791353385"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Medical":[0],"Visual":[1],"Question":[2],"Answering":[3],"(MedVQA)":[4],"is":[5,122],"an":[6,62],"emerging":[7],"field":[8],"that":[9,95],"combines":[10],"natural":[11,163],"language":[12,127,164],"processing":[13],"and":[14,33,50,77,176,196],"computer":[15],"vision":[16],"to":[17,20,29,70,72,139,159,191],"enable":[18,160],"systems":[19,201],"answer":[21,63],"questions":[22,76],"about":[23],"medical":[24,35,156],"images.":[25],"Despite":[26],"its":[27],"potential":[28],"enhance":[30],"diagnostic":[31],"accuracy":[32],"support":[34],"professionals,":[36],"MedVQA":[37,60,93,200],"faces":[38],"significant":[39,141],"challenges.":[40],"Two":[41],"major":[42],"challenges":[43],"are":[44,83],"the":[45,51,103,120,154,173,182,193],"lack":[46],"of":[47,75,172,199],"annotated":[48],"data":[49,101],"need":[52],"for":[53],"AI":[54],"explainability.":[55],"Existing":[56],"models":[57],"often":[58],"treat":[59],"as":[61],"classification":[64],"task,":[65],"which":[66,129,144],"restricts":[67],"their":[68],"capacity":[69],"adapt":[71],"a":[73,90,126,151,188],"variety":[74],"real-world":[78],"situations":[79],"when":[80],"predefined":[81],"answers":[82],"unavailable.":[84],"In":[85,147],"this":[86],"paper,":[87],"we":[88,149],"proposed":[89],"novel":[91],"generative":[92],"model":[94,169,178],"converts":[96],"visual":[97],"information":[98,117],"into":[99,125],"textual":[100,116],"using":[102],"CLIP":[104],"model,":[105,128],"improved":[106],"by":[107,136],"our":[108,168,177],"suggested":[109],"Contrastive":[110],"Concept-Phrase":[111],"Pre-training":[112],"(C2P2)":[113],"technique.":[114],"This":[115],"together":[118],"with":[119,170],"query":[121],"then":[123],"fed":[124],"produces":[130],"human-like":[131],"responses.":[132,165],"We":[133,166],"address":[134],"interpretability":[135],"utilizing":[137],"LIME":[138],"highlight":[140],"image":[142],"regions,":[143],"improves":[145],"transparency.":[146],"addition,":[148],"create":[150],"dataset":[152],"from":[153],"IU":[155],"report":[157],"collection":[158],"more":[161],"complex,":[162],"compared":[167],"state":[171],"art":[174],"models,":[175],"performed":[179],"better":[180],"than":[181],"existing":[183],"models.":[184],"Our":[185],"work":[186],"provides":[187],"substantial":[189],"contribution":[190],"increasing":[192],"adaptability,":[194],"interpretability,":[195],"practical":[197],"implementation":[198],"in":[202],"healthcare.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}