{"id":"https://openalex.org/W4411635455","doi":"https://doi.org/10.1145/3731715.3733384","title":"MedVSA: Medical Visual Spoken-Question Answering","display_name":"MedVSA: Medical Visual Spoken-Question Answering","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4411635455","doi":"https://doi.org/10.1145/3731715.3733384"},"language":"en","primary_location":{"id":"doi:10.1145/3731715.3733384","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733384","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","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":null,"display_name":"Lei Liu","orcid":"https://orcid.org/0009-0006-0962-724X"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Liu","raw_affiliation_strings":["Inner Mongolia University, Huhhot, China"],"raw_orcid":"https://orcid.org/0009-0006-0962-724X","affiliations":[{"raw_affiliation_string":"Inner Mongolia University, Huhhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010464164","display_name":"Xiangdong Su","orcid":"https://orcid.org/0000-0001-8061-1474"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangdong Su","raw_affiliation_strings":["Inner Mongolia University, Huhhot, China"],"raw_orcid":"https://orcid.org/0000-0001-8061-1474","affiliations":[{"raw_affiliation_string":"Inner Mongolia University, Huhhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":["Inner Mongolia University, Huhhot, China"],"raw_orcid":"https://orcid.org/0009-0005-5513-1192","affiliations":[{"raw_affiliation_string":"Inner Mongolia University, Huhhot, China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2722730"],"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":"880","last_page":"888"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9943000078201294,"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/T12031","display_name":"Speech and dialogue systems","score":0.9930999875068665,"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":0.7238832116127014},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7168479561805725},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5723003149032593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5107710361480713},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4065830707550049}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7238832116127014},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7168479561805725},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5723003149032593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5107710361480713},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4065830707550049}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731715.3733384","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733384","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[{"id":"https://openalex.org/G7215572106","display_name":null,"funder_award_id":"Grant No. 62366036","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2069065514","https://openalex.org/W2127141656","https://openalex.org/W2160451571","https://openalex.org/W2165880886","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2962858109","https://openalex.org/W2963150162","https://openalex.org/W2963308316","https://openalex.org/W2963954913","https://openalex.org/W2979525559","https://openalex.org/W2981441441","https://openalex.org/W2987861506","https://openalex.org/W2990138404","https://openalex.org/W3046375318","https://openalex.org/W3094950914","https://openalex.org/W3164670515","https://openalex.org/W3165058054","https://openalex.org/W3185613252","https://openalex.org/W3203255640","https://openalex.org/W4283258232","https://openalex.org/W4284667763","https://openalex.org/W4295917908","https://openalex.org/W4304092130","https://openalex.org/W4312715257","https://openalex.org/W4313452817","https://openalex.org/W4387211014","https://openalex.org/W4387211307","https://openalex.org/W4393782427","https://openalex.org/W4406261752","https://openalex.org/W6600212061"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W3204019825"],"abstract_inverted_index":{"With":[0],"the":[1,56,133,137,143,155,158,164,169,175,182,187,194,205,210],"rapid":[2],"advancement":[3],"of":[4],"technology,":[5],"smart":[6,225],"healthcare":[7,226],"has":[8],"made":[9],"significant":[10],"progress,":[11],"particularly":[12],"in":[13,35],"medical":[14,36,50,58,179],"visual":[15,51],"question":[16],"answering":[17,53],"(MedVQA).":[18],"However,":[19],"current":[20],"MedVQA":[21,77],"primarily":[22],"relies":[23],"on":[24],"text,":[25,116,172],"whereas":[26],"practical":[27],"applications":[28],"often":[29],"involve":[30],"spoken":[31,66,97],"interactions,":[32],"such":[33],"as":[34],"consultations":[37],"and":[38,60,83,106,117,127,145,178,197,231,241],"mobile-based":[39],"queries.":[40],"To":[41],"bridge":[42],"this":[43],"gap,":[44],"we":[45,122,140,161],"propose":[46],"a":[47,124,128],"novel":[48],"task,":[49],"spoken-question":[52],"(MedVSA),":[54],"extending":[55],"conventional":[57],"image":[59],"text-based":[61],"question-answering":[62],"paradigm":[63],"to":[64,92,103,131,153,167,185,236],"include":[65],"interactions":[67],"for":[68,193,219],"enhanced":[69],"applicability.":[70],"We":[71,189],"expand":[72],"upon":[73],"four":[74],"commonly":[75],"used":[76],"datasets,":[78],"namely":[79],"VQA-RAD,":[80],"SLAKE,":[81],"PathVQA,":[82],"OVQA,":[84],"by":[85,228],"leveraging":[86],"Alibaba":[87],"Cloud":[88],"speech":[89,108,119,144,170],"synthesis":[90],"technology":[91],"convert":[93,168],"text":[94,177,215],"questions":[95],"into":[96,147,171,181],"questions.":[98],"Various":[99],"strategies":[100],"are":[101,244],"incorporated":[102],"ensure":[104],"diverse":[105],"realistic":[107],"synthesis.":[109],"The":[110],"resulting":[111],"dataset":[112,243],"comprises":[113],"images,":[114],"corresponding":[115],"synthesized":[118],"data.":[120],"Subsequently,":[121],"design":[123],"single-stage":[125,138,211],"model":[126,130,152,166,184,207],"two-stage":[129,159,206],"tackle":[132],"MedVSA":[134,195,230,242],"task.":[135],"For":[136,157],"model,":[139,160,212],"directly":[141],"input":[142,174],"images":[146,180],"our":[148],"designed":[149],"whisper":[150],"self-distillation":[151,183],"obtain":[154,186],"results.":[156,188],"first":[162],"use":[163],"Whisper":[165],"then":[173],"converted":[176],"provide":[190],"two":[191,199,233],"solutions":[192],"task":[196],"establish":[198],"baselines.":[200],"Experimental":[201],"results":[202],"show":[203],"that":[204,214],"significantly":[208],"outperforms":[209],"indicating":[213],"conversion":[216],"is":[217],"crucial":[218],"solving":[220],"MedVSA.":[221],"This":[222],"study":[223],"advances":[224],"developments":[227],"proposing":[229],"designing":[232],"baselines":[234],"tailored":[235],"its":[237],"specificities.":[238],"Source":[239],"code":[240],"available":[245],"at":[246],"https://github.com/Alivelei/MedVSA.":[247]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}