{"id":"https://openalex.org/W4415540743","doi":"https://doi.org/10.1145/3746027.3755273","title":"Medical Vision-Language Pre-training with Multimodal Variational Masked Autoencoder for Robust Medical VQA","display_name":"Medical Vision-Language Pre-training with Multimodal Variational Masked Autoencoder for Robust Medical VQA","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540743","doi":"https://doi.org/10.1145/3746027.3755273"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755273","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5069390870","display_name":"Dexuan Xu","orcid":"https://orcid.org/0000-0003-3100-5886"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dexuan Xu","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3100-5886","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104230937","display_name":"Yanyuan Chen","orcid":"https://orcid.org/0000-0003-1579-5857"},"institutions":[{"id":"https://openalex.org/I25041050","display_name":"Augusta University","ror":"https://ror.org/012mef835","country_code":"US","type":"education","lineage":["https://openalex.org/I25041050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanyuan Chen","raw_affiliation_strings":["Augusta University, Augusta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1579-5857","affiliations":[{"raw_affiliation_string":"Augusta University, Augusta, GA, USA","institution_ids":["https://openalex.org/I25041050"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070956286","display_name":"Yu Huang","orcid":"https://orcid.org/0000-0002-1138-1828"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Huang","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1138-1828","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120132469","display_name":"E Shihao","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shihao E","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-4304-3944","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031432933","display_name":"Yiwei Lou","orcid":"https://orcid.org/0000-0002-5618-3366"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwei Lou","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5618-3366","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040695351","display_name":"Yongzhi Cao","orcid":"https://orcid.org/0000-0001-9517-7332"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongzhi Cao","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9517-7332","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hanpin Wang","orcid":"https://orcid.org/0009-0009-7680-9504"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanpin Wang","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-7680-9504","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083330935","display_name":"Meikang Qiu","orcid":"https://orcid.org/0000-0002-1004-0140"},"institutions":[{"id":"https://openalex.org/I25041050","display_name":"Augusta University","ror":"https://ror.org/012mef835","country_code":"US","type":"education","lineage":["https://openalex.org/I25041050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meikang Qiu","raw_affiliation_strings":["Augusta University, Augusta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1004-0140","affiliations":[{"raw_affiliation_string":"Augusta University, Augusta, GA, USA","institution_ids":["https://openalex.org/I25041050"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3991","last_page":"4000"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.975600004196167,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.975600004196167,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9599999785423279,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9501000046730042,"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/robustness","display_name":"Robustness (evolution)","score":0.7225000262260437},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6437000036239624},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6158999800682068},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5026000142097473},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4991999864578247},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42080000042915344}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7225000262260437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6675000190734863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6651999950408936},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6437000036239624},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6158999800682068},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5630000233650208},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5026000142097473},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4991999864578247},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42080000042915344},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3495999872684479},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755273","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1909613347","display_name":null,"funder_award_id":"62206197, 62436006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7621168539","display_name":null,"funder_award_id":"No.2023YFC3502902, 2021YFF1201100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2897980926","https://openalex.org/W2964082701","https://openalex.org/W3115360974","https://openalex.org/W3122924283","https://openalex.org/W3164670515","https://openalex.org/W3165058054","https://openalex.org/W3217571210","https://openalex.org/W4313156423","https://openalex.org/W4379879090","https://openalex.org/W4384162023","https://openalex.org/W4386075916"],"related_works":[],"abstract_inverted_index":{"Medical":[0],"Visual":[1],"Question":[2],"Answering":[3],"(Medical":[4],"VQA)":[5],"plays":[6],"an":[7],"important":[8],"role":[9],"in":[10],"medical":[11,18,70,112,128],"informatics.":[12],"However,":[13],"the":[14,66,69],"robustness":[15,67],"of":[16,68],"existing":[17],"VQA":[19,71,113],"models":[20],"is":[21],"severely":[22],"challenged":[23],"by":[24],"adversarial":[25,30,123],"attacks.":[26],"Current":[27],"methods":[28],"(e.g.":[29],"training":[31],"and":[32,43,77,94,106,125],"noise-based":[33],"reasoning)":[34],"heavily":[35],"rely":[36],"on":[37,110],"additional":[38],"data":[39],"or":[40],"complex":[41],"procedures":[42],"often":[44],"ignore":[45],"model-level":[46],"robustness.":[47],"To":[48],"address":[49],"these":[50],"issues,":[51],"we":[52],"propose":[53],"Multimodal":[54],"Variational":[55],"Masked":[56],"Autoencoder":[57],"(MVMAE),":[58],"a":[59,88],"novel":[60],"pre-training":[61,130],"framework":[62,86],"designed":[63],"to":[64,80,97,121],"enhance":[65],"task.":[72],"MVMAE":[73,117],"leverages":[74],"masked":[75],"modeling":[76],"variational":[78],"inference":[79],"extract":[81],"robust":[82,99],"multimodal":[83,90,129],"features.":[84],"The":[85],"introduces":[87],"low-cost":[89],"bottleneck":[91],"fusion":[92,105],"module":[93],"employs":[95],"reparameterization":[96],"sample":[98],"latent":[100],"representations,":[101],"ensuring":[102],"effective":[103],"feature":[104],"reconstruction.":[107],"Extensive":[108],"experiments":[109],"public":[111],"datasets":[114],"demonstrate":[115],"that":[116],"significantly":[118],"improves":[119],"resistance":[120],"various":[122],"attacks":[124],"outperforms":[126],"other":[127],"methods.":[131]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}