{"id":"https://openalex.org/W3094950914","doi":"https://doi.org/10.1145/3394171.3413761","title":"Medical Visual Question Answering via Conditional Reasoning","display_name":"Medical Visual Question Answering via Conditional Reasoning","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3094950914","doi":"https://doi.org/10.1145/3394171.3413761","mag":"3094950914"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413761","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","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/A5001643829","display_name":"Li-Ming Zhan","orcid":"https://orcid.org/0000-0001-7173-1116"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Li-Ming Zhan","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461632","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0002-2165-245X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077474877","display_name":"Lu Fan","orcid":"https://orcid.org/0000-0003-1230-7854"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lu Fan","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100360558","display_name":"Jiaxin Chen","orcid":"https://orcid.org/0000-0003-0548-4094"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiaxin Chen","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101981128","display_name":"Xiao-Ming Wu","orcid":"https://orcid.org/0000-0002-3130-0554"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiao-Ming Wu","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5001643829"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":7.8459,"has_fulltext":false,"cited_by_count":153,"citation_normalized_percentile":{"value":0.98113614,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2345","last_page":"2354"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9976999759674072,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9865000247955322,"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/question-answering","display_name":"Question answering","score":0.7855246067047119},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7180683612823486},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6666629314422607},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5915923714637756},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5661977529525757},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5461172461509705},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41071057319641113},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40678051114082336},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3620418310165405},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36171257495880127},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10379251837730408}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7855246067047119},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7180683612823486},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6666629314422607},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5915923714637756},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5661977529525757},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5461172461509705},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41071057319641113},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40678051114082336},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3620418310165405},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36171257495880127},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10379251837730408},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3413761","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2064675550","https://openalex.org/W2136655611","https://openalex.org/W2190656909","https://openalex.org/W2250539671","https://openalex.org/W2265846598","https://openalex.org/W2463565445","https://openalex.org/W2529436507","https://openalex.org/W2560730294","https://openalex.org/W2561715562","https://openalex.org/W2592929672","https://openalex.org/W2613718673","https://openalex.org/W2745461083","https://openalex.org/W2760103357","https://openalex.org/W2793546384","https://openalex.org/W2884093133","https://openalex.org/W2889187377","https://openalex.org/W2897870704","https://openalex.org/W2901466771","https://openalex.org/W2947706148","https://openalex.org/W2953388933","https://openalex.org/W2963223524","https://openalex.org/W2963224792","https://openalex.org/W2963383024","https://openalex.org/W2963518342","https://openalex.org/W2963521239","https://openalex.org/W2963656855","https://openalex.org/W2964118342","https://openalex.org/W2964121744","https://openalex.org/W2964199361","https://openalex.org/W2964301648","https://openalex.org/W2970971581","https://openalex.org/W2981578638","https://openalex.org/W2981963155","https://openalex.org/W2982461533","https://openalex.org/W3038058348","https://openalex.org/W3099849198"],"related_works":["https://openalex.org/W2805599431","https://openalex.org/W1485630101","https://openalex.org/W2498017833","https://openalex.org/W207304934","https://openalex.org/W2798526799","https://openalex.org/W4377703168","https://openalex.org/W2123793327","https://openalex.org/W15319282","https://openalex.org/W1560657467","https://openalex.org/W2296730655"],"abstract_inverted_index":{"Medical":[0],"visual":[1,57],"question":[2,11],"answering":[3],"(Med-VQA)":[4],"aims":[5],"to":[6,45,78,95,121,144,148,185],"accurately":[7],"answer":[8],"a":[9,14,70,91,117,123,162,196],"clinical":[10,50],"presented":[12],"with":[13],"medical":[15],"image.":[16],"Despite":[17],"its":[18,31],"enormous":[19],"potential":[20],"in":[21,30,182,199],"healthcare":[22],"industry":[23],"and":[24,33,52,110,167,188],"services,":[25],"the":[26,46,53,97,105,130,153,171],"technology":[27],"is":[28,34,202],"still":[29],"infancy":[32],"far":[35],"from":[36,210],"practical":[37],"use.":[38],"Med-VQA":[39,86,112,146,165],"tasks":[40,134],"are":[41],"highly":[42],"challenging":[43],"due":[44],"massive":[47],"diversity":[48],"of":[49,55,63,108,126,133,161],"questions":[51],"disparity":[54],"required":[56],"reasoning":[58,73,82,93,119,127,138],"skills":[59,83,128],"for":[60,75,84,129,192],"different":[61,106,124],"types":[62,132],"questions.":[64],"In":[65,152],"this":[66],"paper,":[67],"we":[68,89,114,155],"propose":[69,116],"novel":[71],"conditional":[72,137],"framework":[74,139],"Med-VQA,":[76],"aiming":[77],"automatically":[79],"learn":[80,122],"effective":[81],"various":[85],"tasks.":[87],"Particularly,":[88],"develop":[90],"question-conditioned":[92],"module":[94,120],"guide":[96],"importance":[98],"selection":[99],"over":[100],"multimodal":[101],"fusion":[102],"features.":[103],"Considering":[104],"nature":[107],"closed-ended":[109,187],"open-ended":[111,189,193],"tasks,":[113],"further":[115],"type-conditioned":[118],"set":[125],"two":[131],"separately.":[135],"Our":[136],"can":[140,207],"be":[141,208],"easily":[142],"applied":[143],"existing":[145],"systems":[147],"bring":[149],"performance":[150],"gains.":[151],"experiments,":[154],"build":[156],"our":[157,176],"system":[158,177],"on":[159,170],"top":[160],"recent":[163],"state-of-the-art":[164],"model":[166],"evaluate":[168],"it":[169],"VQA-RAD":[172],"benchmark":[173],"[23].":[174],"Remarkably,":[175],"achieves":[178],"significantly":[179],"increased":[180],"accuracy":[181,201],"predicting":[183],"answers":[184],"both":[186],"questions,":[190,194],"especially":[191],"where":[195],"10.8%":[197],"increase":[198],"absolute":[200],"obtained.":[203],"The":[204],"source":[205],"code":[206],"downloaded":[209],"https://github.com/awenbocc/med-vqa.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":34},{"year":2024,"cited_by_count":34},{"year":2023,"cited_by_count":38},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":17}],"updated_date":"2026-05-12T08:28:47.272897","created_date":"2025-10-10T00:00:00"}