{"id":"https://openalex.org/W4304092062","doi":"https://doi.org/10.1145/3503161.3547948","title":"Align, Reason and Learn: Enhancing Medical Vision-and-Language Pre-training with Knowledge","display_name":"Align, Reason and Learn: Enhancing Medical Vision-and-Language Pre-training with Knowledge","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304092062","doi":"https://doi.org/10.1145/3503161.3547948"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3547948","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547948","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th 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/A5100430139","display_name":"Zhihong Chen","orcid":"https://orcid.org/0000-0003-4064-7987"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihong Chen","raw_affiliation_strings":["Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210099586","https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101691639","display_name":"Guanbin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanbin Li","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030367905","display_name":"Xiang Wan","orcid":"https://orcid.org/0000-0002-2324-6527"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Wan","raw_affiliation_strings":["Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen & Pazhou Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen & Pazhou Lab, Shenzhen, China","institution_ids":["https://openalex.org/I4210099586","https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":80,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5152","last_page":"5161"},"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":0.9970999956130981,"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/T10028","display_name":"Topic Modeling","score":0.9790999889373779,"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/computer-science","display_name":"Computer science","score":0.8180882334709167},{"id":"https://openalex.org/keywords/pretext","display_name":"Pretext","score":0.5577791929244995},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.5548690557479858},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5116808414459229},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4668567478656769},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46189865469932556},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4494832456111908},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32175546884536743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8180882334709167},{"id":"https://openalex.org/C2779627259","wikidata":"https://www.wikidata.org/wiki/Q779763","display_name":"Pretext","level":3,"score":0.5577791929244995},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.5548690557479858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5116808414459229},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4668567478656769},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46189865469932556},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4494832456111908},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32175546884536743},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3547948","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547948","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"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":34,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2892181857","https://openalex.org/W2915623326","https://openalex.org/W2953356739","https://openalex.org/W2963150162","https://openalex.org/W2963486920","https://openalex.org/W2963954913","https://openalex.org/W2970231061","https://openalex.org/W2970771982","https://openalex.org/W2970986510","https://openalex.org/W2979525559","https://openalex.org/W2990138404","https://openalex.org/W2998385486","https://openalex.org/W3083376569","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3094502228","https://openalex.org/W3094950914","https://openalex.org/W3098065087","https://openalex.org/W3106224367","https://openalex.org/W3114916066","https://openalex.org/W3128510757","https://openalex.org/W3135367836","https://openalex.org/W3151929433","https://openalex.org/W3164670515","https://openalex.org/W3165058054","https://openalex.org/W3173220247","https://openalex.org/W3173909648","https://openalex.org/W3177149096","https://openalex.org/W3198570286","https://openalex.org/W3207798279","https://openalex.org/W4312784228","https://openalex.org/W4393782427","https://openalex.org/W6600212061"],"related_works":["https://openalex.org/W161456234","https://openalex.org/W3123043866","https://openalex.org/W2765162471","https://openalex.org/W2367130511","https://openalex.org/W4235007455","https://openalex.org/W2354300066","https://openalex.org/W1583422155","https://openalex.org/W3213252596","https://openalex.org/W1649619740","https://openalex.org/W1534006406"],"abstract_inverted_index":{"Medical":[0],"vision-and-language":[1,15,69,205],"pre-training":[2,70],"(Med-VLP)":[3],"has":[4],"received":[5],"considerable":[6],"attention":[7],"owing":[8],"to":[9,12,62,105,152,156,175],"its":[10],"applicability":[11],"extracting":[13],"generic":[14],"representations":[16,132],"from":[17,112],"medical":[18,53,93,110,204],"images":[19,184],"and":[20,35,43,57,84,102,127,137,168,185,197,238],"texts.":[21],"Most":[22],"existing":[23],"methods":[24,72],"mainly":[25],"contain":[26],"three":[27,113,208],"elements:":[28],"uni-modal":[29],"encoders":[30],"(i.e.,":[31],"a":[32,36,39,100,194,203],"vision":[33,126,135],"encoder":[34,136,140],"language":[37,139],"encoder),":[38],"multi-modal":[40,149],"fusion":[41,150],"module,":[42],"pretext":[44,190],"tasks,":[45],"with":[46],"few":[47],"studies":[48],"considering":[49,116],"the":[50,74,92,122,131,134,138,148,154,162,165,173,179,213,230],"importance":[51],"of":[52,133,164,215,232,235,241],"domain":[54],"expert":[55],"knowledge":[56,61,111,117,146,160],"explicitly":[58],"exploiting":[59],"such":[60],"facilitate":[63,198],"Med-VLP.":[64],"Although":[65],"there":[66],"exist":[67],"knowledge-enhanced":[68],"(VLP)":[71],"in":[73,91,183],"general":[75],"domain,":[76],"most":[77,180],"require":[78],"off-the-shelf":[79],"toolkits":[80],"(e.g.,":[81],"object":[82],"detectors":[83],"scene":[85],"graph":[86],"parsers),":[87],"which":[88],"are":[89],"unavailable":[90],"domain.":[94],"In":[95],"this":[96],"paper,":[97],"we":[98,129,144,171,201],"propose":[99],"systematic":[101],"effective":[103],"approach":[104,237],"enhance":[106],"Med-VLP":[107],"by":[108,187],"structured":[109],"perspectives.":[114],"First,":[115],"can":[118],"be":[119],"regarded":[120],"as":[121,161],"intermediate":[123],"medium":[124],"between":[125],"language,":[128],"align":[130],"through":[141],"knowledge.":[142],"Second,":[143],"inject":[145],"into":[147],"model":[151,155,174],"enable":[153],"perform":[157,193],"reasoning":[158],"using":[159],"supplementation":[163],"input":[166],"image":[167],"text.":[169],"Third,":[170],"guide":[172],"put":[176],"emphasis":[177],"on":[178,223],"critical":[181],"information":[182],"texts":[186],"designing":[188],"knowledge-induced":[189],"tasks.":[191,209,226],"To":[192],"comprehensive":[195],"evaluation":[196],"further":[199],"research,":[200],"construct":[202],"benchmark":[206],"including":[207],"Experimental":[210],"results":[211],"illustrate":[212],"effectiveness":[214],"our":[216,236],"approach,":[217],"where":[218],"state-of-the-art":[219],"performance":[220],"is":[221],"achieved":[222],"all":[224],"downstream":[225],"Further":[227],"analyses":[228],"explore":[229],"effects":[231],"different":[233],"components":[234],"various":[239],"settings":[240],"pre-training.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":38},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}