{"id":"https://openalex.org/W3152015664","doi":"https://doi.org/10.1109/isbi48211.2021.9434063","title":"MMBERT: Multimodal BERT Pretraining for Improved Medical VQA","display_name":"MMBERT: Multimodal BERT Pretraining for Improved Medical VQA","publication_year":2021,"publication_date":"2021-04-13","ids":{"openalex":"https://openalex.org/W3152015664","doi":"https://doi.org/10.1109/isbi48211.2021.9434063","mag":"3152015664"},"language":"en","primary_location":{"id":"doi:10.1109/isbi48211.2021.9434063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isbi48211.2021.9434063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.01394","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018591362","display_name":"Yash Khare","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Yash Khare","raw_affiliation_strings":["IIIT, Hyderabad, India","IIIT-Hyderabad, India#TAB#"],"affiliations":[{"raw_affiliation_string":"IIIT, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"IIIT-Hyderabad, India#TAB#","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083698352","display_name":"Viraj Bagal","orcid":"https://orcid.org/0000-0002-0815-6865"},"institutions":[{"id":"https://openalex.org/I181996519","display_name":"Indian Institute of Science Education and Research Pune","ror":"https://ror.org/028qa3n13","country_code":"IN","type":"education","lineage":["https://openalex.org/I181996519"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Viraj Bagal","raw_affiliation_strings":["IISER, Pune, India","IISER Pune (India)"],"affiliations":[{"raw_affiliation_string":"IISER, Pune, India","institution_ids":["https://openalex.org/I181996519"]},{"raw_affiliation_string":"IISER Pune (India)","institution_ids":["https://openalex.org/I181996519"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026729420","display_name":"Minesh Mathew","orcid":"https://orcid.org/0000-0002-0809-2590"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Minesh Mathew","raw_affiliation_strings":["IIIT, Hyderabad, India","IIIT-Hyderabad, India#TAB#"],"affiliations":[{"raw_affiliation_string":"IIIT, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"IIIT-Hyderabad, India#TAB#","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055756055","display_name":"Adithi Devi","orcid":null},"institutions":[{"id":"https://openalex.org/I99557698","display_name":"Osmania Medical College","ror":"https://ror.org/00hr54p22","country_code":"IN","type":"healthcare","lineage":["https://openalex.org/I4210126239","https://openalex.org/I99557698"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Adithi Devi","raw_affiliation_strings":["Osmania Medical College, India","Osmania Medical College,India"],"affiliations":[{"raw_affiliation_string":"Osmania Medical College, India","institution_ids":["https://openalex.org/I99557698"]},{"raw_affiliation_string":"Osmania Medical College,India","institution_ids":["https://openalex.org/I99557698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034329125","display_name":"U. Deva Priyakumar","orcid":"https://orcid.org/0000-0001-7114-3955"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"U Deva Priyakumar","raw_affiliation_strings":["IIIT, Hyderabad, India","IIIT-Hyderabad, India#TAB#"],"affiliations":[{"raw_affiliation_string":"IIIT, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"IIIT-Hyderabad, India#TAB#","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053112307","display_name":"C. V. Jawahar","orcid":"https://orcid.org/0000-0001-6767-7057"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"CV Jawahar","raw_affiliation_strings":["IIIT, Hyderabad, India","IIIT-Hyderabad, India#TAB#"],"affiliations":[{"raw_affiliation_string":"IIIT, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"IIIT-Hyderabad, India#TAB#","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5018591362"],"corresponding_institution_ids":["https://openalex.org/I65181880"],"apc_list":null,"apc_paid":null,"fwci":0.2905,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.53802735,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1033","last_page":"1036"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9952999949455261,"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":0.9883999824523926,"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/interpretability","display_name":"Interpretability","score":0.9041621685028076},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7787581086158752},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6406358480453491},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5684798955917358},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5229730606079102},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4832378327846527},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.47885915637016296},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4723682999610901},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.46575289964675903},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4539905786514282},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.43130743503570557},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.41363072395324707},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07541325688362122}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9041621685028076},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7787581086158752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6406358480453491},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5684798955917358},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5229730606079102},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4832378327846527},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.47885915637016296},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4723682999610901},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.46575289964675903},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4539905786514282},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.43130743503570557},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.41363072395324707},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07541325688362122},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/isbi48211.2021.9434063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isbi48211.2021.9434063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.01394","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.01394","pdf_url":"https://arxiv.org/pdf/2104.01394","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3152015664","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2104.01394","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2104.01394","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.01394","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.01394","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.01394","pdf_url":"https://arxiv.org/pdf/2104.01394","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3152015664.pdf","grobid_xml":"https://content.openalex.org/works/W3152015664.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2897980926","https://openalex.org/W2901466771","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2964121744","https://openalex.org/W2965729401","https://openalex.org/W2965818302","https://openalex.org/W2970608575","https://openalex.org/W2979525559","https://openalex.org/W3011651912","https://openalex.org/W3012608737","https://openalex.org/W3020257313","https://openalex.org/W3090449556","https://openalex.org/W3094950914","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6766253171","https://openalex.org/W6766819354"],"related_works":["https://openalex.org/W3164670515","https://openalex.org/W3198730297","https://openalex.org/W2982584731","https://openalex.org/W2963355794","https://openalex.org/W2508795679","https://openalex.org/W2963377948","https://openalex.org/W3203635737","https://openalex.org/W3041203335","https://openalex.org/W2971185145","https://openalex.org/W3033754661","https://openalex.org/W2952572977","https://openalex.org/W2803367139","https://openalex.org/W3194380524","https://openalex.org/W2751608058","https://openalex.org/W2800046969","https://openalex.org/W3195299381","https://openalex.org/W2975706270","https://openalex.org/W3045951017","https://openalex.org/W3170928047","https://openalex.org/W2909206463"],"abstract_inverted_index":{"Images":[0],"in":[1,125],"the":[2,9,28,78,110],"medical":[3,29,32,67,84],"domain":[4,11,21],"are":[5],"fundamentally":[6],"different":[7],"from":[8],"general":[10,20],"images.":[12],"Consequently,":[13],"it":[14],"is":[15,35],"infeasible":[16],"to":[17],"directly":[18],"employ":[19],"Visual":[22],"Question":[23],"Answering":[24],"(VQA)":[25],"models":[26,112],"for":[27,56,100],"domain.":[30],"Additionally,":[31],"image":[33,68,85],"annotation":[34],"a":[36,47,82],"costly":[37],"and":[38,59,69,106],"time-consuming":[39],"process.":[40],"To":[41],"overcome":[42],"these":[43],"limitations,":[44],"we":[45],"propose":[46],"solution":[48,91,119],"inspired":[49],"by":[50],"self-supervised":[51],"pretraining":[52],"of":[53,113],"Transformer-style":[54],"architectures":[55],"NLP,":[57],"Vision,":[58],"Language":[60],"tasks.":[61],"Our":[62],"method":[63],"involves":[64],"learning":[65],"richer":[66],"text":[70],"semantic":[71],"representations":[72],"using":[73],"Masked":[74],"Vision-Language":[75],"Modeling":[76],"as":[77],"pretext":[79],"task":[80],"on":[81,96],"large":[83],"+":[86],"caption":[87],"dataset.":[88],"The":[89],"proposed":[90],"achieves":[92],"new":[93],"state-of-the-art":[94],"performance":[95],"two":[97],"VQA":[98],"datasets":[99],"radiology":[101],"images":[102],"-":[103],"VQA-Med":[104],"2019":[105],"VQA-RAD,":[107],"outperforming":[108],"even":[109],"ensemble":[111],"previous":[114],"best":[115],"solutions.":[116],"Moreover,":[117],"our":[118],"provides":[120],"attention":[121],"maps":[122],"which":[123],"help":[124],"model":[126],"interpretability.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}