{"id":"https://openalex.org/W7126093515","doi":"https://doi.org/10.1109/bibm66473.2025.11356107","title":"MLP-Based Vision Language Pre-Training for Medical Visual Question Answering","display_name":"MLP-Based Vision Language Pre-Training for Medical Visual Question Answering","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7126093515","doi":"https://doi.org/10.1109/bibm66473.2025.11356107"},"language":null,"primary_location":{"id":"doi:10.1109/bibm66473.2025.11356107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","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/A5101867714","display_name":"Zheng Zhang","orcid":"https://orcid.org/0009-0002-8689-0763"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zequn Zhang","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China,Heifei,China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China,Heifei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003413234","display_name":"Jun He","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinlong He","raw_affiliation_strings":["School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124197584","display_name":"Pengfei Li","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Li","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China,Heifei,China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China,Heifei,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101867714"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.72465358,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1951","last_page":"1956"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9922999739646912,"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":0.9922999739646912,"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":0.0010999999940395355,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0007999999797903001,"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/question-answering","display_name":"Question answering","score":0.8615999817848206},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7548999786376953},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4512999951839447},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4388999938964844},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4228000044822693},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3986000120639801},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.3677000105381012}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8615999817848206},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7548999786376953},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7056000232696533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5867999792098999},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5230000019073486},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4512999951839447},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4388999938964844},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4228000044822693},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3986000120639801},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C3019144022","wikidata":"https://www.wikidata.org/wiki/Q4124998","display_name":"Questions and answers","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C3019150057","wikidata":"https://www.wikidata.org/wiki/Q92779279","display_name":"Medical information","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.272599995136261},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26089999079704285},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm66473.2025.11356107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8262320756912231,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2897980926","https://openalex.org/W2901466771","https://openalex.org/W2979525559","https://openalex.org/W3094950914","https://openalex.org/W3104050923","https://openalex.org/W3163465952","https://openalex.org/W3164670515","https://openalex.org/W3165058054","https://openalex.org/W3174148569","https://openalex.org/W3203255640","https://openalex.org/W3203635737","https://openalex.org/W4224919709","https://openalex.org/W4226297238","https://openalex.org/W4283258232","https://openalex.org/W4293676823","https://openalex.org/W4295917908","https://openalex.org/W4312982094","https://openalex.org/W4386352883","https://openalex.org/W4386566421","https://openalex.org/W4387211307","https://openalex.org/W4387211791","https://openalex.org/W4404297002","https://openalex.org/W4406388205"],"related_works":[],"abstract_inverted_index":{"Medical":[0],"visual":[1,16],"question":[2],"answering":[3],"(VQA)":[4],"aims":[5],"to":[6,21],"answer":[7],"clinical":[8],"questions":[9],"based":[10,36,59],"on":[11,37,60,99,111],"medical":[12,29,101,113,125],"images":[13],"by":[14],"integrating":[15],"and":[17,109],"language":[18,93],"information.":[19],"Due":[20],"the":[22,38,44,53,61,70,89],"limited":[23],"size":[24],"of":[25,52,66],"datasets":[26,104],"used":[27],"for":[28,80],"VQA":[30,114,126],"training,":[31],"vision-language":[32],"pretraining":[33],"(VLP)":[34],"methods":[35,56],"pretrain-finetune":[39],"paradigm":[40],"have":[41],"emerged":[42],"as":[43],"dominant":[45],"solution":[46],"in":[47,69],"recent":[48],"years.":[49],"However,":[50],"most":[51],"current":[54],"VLP":[55,82],"are":[57],"implemented":[58],"transformer":[62],"architecture.":[63],"The":[64,116],"emergence":[65],"MLP":[67],"architecture":[68],"computer":[71],"vision":[72,92],"domain":[73],"provides":[74],"us":[75],"with":[76,105],"a":[77],"novel":[78],"approach":[79],"designing":[81],"models.":[83],"In":[84],"this":[85],"paper,":[86],"we":[87],"propose":[88],"first":[90],"MLP-based":[91],"pre-training":[94,107],"(MBVLP),":[95],"which":[96],"is":[97],"pretrained":[98],"three":[100,124],"image":[102],"captioning":[103],"multiple":[106],"objectives":[108],"fine-tuned":[110],"downstream":[112],"tasks.":[115],"proposed":[117],"MBVLP":[118],"model":[119],"surpasses":[120],"existing":[121],"methodologies":[122],"across":[123],"datasets,":[127],"achieving":[128],"state-of-the-art":[129],"performance.":[130]},"counts_by_year":[],"updated_date":"2026-02-01T03:34:12.195049","created_date":"2026-01-30T00:00:00"}