{"id":"https://openalex.org/W4387969743","doi":"https://doi.org/10.1145/3581783.3611830","title":"RAMM: Retrieval-augmented Biomedical Visual Question Answering with Multi-modal Pre-training","display_name":"RAMM: Retrieval-augmented Biomedical Visual Question Answering with Multi-modal Pre-training","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969743","doi":"https://doi.org/10.1145/3581783.3611830"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611830","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st 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/A5020682113","display_name":"Zheng Yuan","orcid":"https://orcid.org/0000-0001-7179-2437"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Yuan","raw_affiliation_strings":["Alibaba DAMO Academy, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7179-2437","affiliations":[{"raw_affiliation_string":"Alibaba DAMO Academy, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100611571","display_name":"Qiao Jin","orcid":"https://orcid.org/0000-0002-1268-7239"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiao Jin","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1268-7239","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065907658","display_name":"Chuanqi Tan","orcid":"https://orcid.org/0000-0002-6676-3057"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanqi Tan","raw_affiliation_strings":["Alibaba DAMO Academy, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6676-3057","affiliations":[{"raw_affiliation_string":"Alibaba DAMO Academy, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071925457","display_name":"Zhengyun Zhao","orcid":"https://orcid.org/0000-0001-9425-7752"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengyun Zhao","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9425-7752","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038332216","display_name":"Hongyi Yuan","orcid":"https://orcid.org/0000-0003-2597-1973"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyi Yuan","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2597-1973","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101488344","display_name":"Fei Huang","orcid":"https://orcid.org/0000-0002-3709-5053"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Huang","raw_affiliation_strings":["Alibaba DAMO Academy, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3709-5053","affiliations":[{"raw_affiliation_string":"Alibaba DAMO Academy, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047856952","display_name":"Songfang Huang","orcid":"https://orcid.org/0000-0001-8084-0904"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songfang Huang","raw_affiliation_strings":["Alibaba DAMO Academy, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8084-0904","affiliations":[{"raw_affiliation_string":"Alibaba DAMO Academy, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"547","last_page":"556"},"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":0.9965000152587891,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9948999881744385,"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":0.8339319229125977},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6506246328353882},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6363109350204468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6154661774635315},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.6007393002510071},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.561496376991272},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.534881591796875},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.532648503780365},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.4863048493862152},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.47337526082992554},{"id":"https://openalex.org/keywords/augmented-reality","display_name":"Augmented reality","score":0.41522669792175293},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38595330715179443},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3431433141231537}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8339319229125977},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6506246328353882},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6363109350204468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6154661774635315},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.6007393002510071},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.561496376991272},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.534881591796875},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.532648503780365},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.4863048493862152},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47337526082992554},{"id":"https://openalex.org/C153715457","wikidata":"https://www.wikidata.org/wiki/Q254183","display_name":"Augmented reality","level":2,"score":0.41522669792175293},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38595330715179443},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3431433141231537},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611830","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2911489562","https://openalex.org/W2951434086","https://openalex.org/W2963954913","https://openalex.org/W2979525559","https://openalex.org/W2995225687","https://openalex.org/W2998702515","https://openalex.org/W3027879771","https://openalex.org/W3046375318","https://openalex.org/W3083376569","https://openalex.org/W3094950914","https://openalex.org/W3138516171","https://openalex.org/W3164654615","https://openalex.org/W3164670515","https://openalex.org/W3165058054","https://openalex.org/W3166593409","https://openalex.org/W3198080531","https://openalex.org/W3198570286","https://openalex.org/W3199965269","https://openalex.org/W4223492536","https://openalex.org/W4252076394","https://openalex.org/W4303444943","https://openalex.org/W4304092062","https://openalex.org/W4385574358","https://openalex.org/W6600459194"],"related_works":["https://openalex.org/W2354322770","https://openalex.org/W3000097931","https://openalex.org/W4237547500","https://openalex.org/W1570848052","https://openalex.org/W2373192430","https://openalex.org/W4239268388","https://openalex.org/W2172197285","https://openalex.org/W1537496349","https://openalex.org/W2991048842","https://openalex.org/W2379407973"],"abstract_inverted_index":{"Vision-and-language":[0],"multi-modal":[1,73],"pretraining":[2,116],"and":[3,78,84,118,131,138,154,164,175,180],"fine-tuning":[4],"have":[5],"shown":[6],"great":[7],"success":[8],"in":[9],"visual":[10,77],"question":[11,133],"answering":[12],"(VQA).":[13],"Compared":[14],"to":[15,42,75,99,107,124],"general":[16],"domain":[17],"VQA,":[18],"the":[19,44,71,102,126,129,132,135,161],"performance":[20,149,170],"of":[21,128],"biomedical":[22,40,53,72,168],"VQA":[23,41,169],"suffers":[24],"from":[25,66,115],"limited":[26,103],"data.":[27,104],"In":[28],"this":[29],"paper,":[30],"we":[31,49,69,94],"propose":[32,95,106],"a":[33,51,96,120],"retrieval-augmented":[34,97,144],"pretrain-and-finetune":[35,145],"paradigm":[36,146],"named":[37,55],"RAMM":[38,163],"for":[39,81],"overcome":[43],"data":[45],"limitation":[46],"issue.":[47],"Specifically,":[48],"collect":[50],"new":[52],"dataset":[54],"PMCPM":[56,165],"which":[57],"offers":[58],"patient-based":[59],"image-text":[60,82,89,110],"pairs":[61,83,111],"containing":[62],"diverse":[63],"patient":[64],"situations":[65],"PubMed.":[67],"Then,":[68],"pretrain":[70],"model":[74],"learn":[76],"textual":[79],"representation":[80,127],"align":[85],"these":[86],"representations":[87],"with":[88,134,172],"contrastive":[90],"objective":[91],"(ITC).":[92],"Finally,":[93],"method":[98],"better":[100],"use":[101],"We":[105],"retrieve":[108],"similar":[109],"based":[112],"on":[113,150],"ITC":[114],"datasets":[117],"introduce":[119],"novel":[121],"retrieval-attention":[122],"module":[123],"fuse":[125],"image":[130],"retrieved":[136],"images":[137],"texts.":[139],"Experiments":[140],"demonstrate":[141],"that":[142,160],"our":[143],"obtains":[147],"state-of-the-art":[148],"Med-VQA2019,":[151],"Med-VQA2021,":[152],"VQARAD,":[153],"SLAKE":[155],"datasets.":[156],"Further":[157],"analysis":[158],"shows":[159],"proposed":[162],"can":[166],"enhance":[167],"compared":[171],"previous":[173],"resources":[174],"methods.":[176],"The":[177],"pre-trained":[178],"models":[179],"codes":[181],"are":[182],"published":[183],"at":[184],"https://github.com/GanjinZero/RAMM.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}