{"id":"https://openalex.org/W7171979755","doi":"https://doi.org/10.1145/3774521.3774604","title":"Medical Semantic-Aware Image-Text Alignment loss for Medical Visual Question Answering","display_name":"Medical Semantic-Aware Image-Text Alignment loss for Medical Visual Question Answering","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W7171979755","doi":"https://doi.org/10.1145/3774521.3774604"},"language":null,"primary_location":{"id":"doi:10.1145/3774521.3774604","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774604","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774521.3774604","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011427663","display_name":"Vasudha Joshi","orcid":"https://orcid.org/0009-0002-7425-4559"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vasudha Joshi","raw_affiliation_strings":["Computer Science and Engineering, Indian Institute of Technology Kharagpur, Kharagpur, India"],"raw_orcid":"https://orcid.org/0009-0002-7425-4559","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Indian Institute of Technology Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144141730","display_name":"Adrish Adhikari","orcid":"https://orcid.org/0009-0006-5895-4036"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Adrish Adhikari","raw_affiliation_strings":["Electronics and Electrical Communication, Indian Institute of Technology Kharagpur, Kharagpur, India"],"raw_orcid":"https://orcid.org/0009-0006-5895-4036","affiliations":[{"raw_affiliation_string":"Electronics and Electrical Communication, Indian Institute of Technology Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032809289","display_name":"Pabitra Mitra","orcid":"https://orcid.org/0000-0002-1908-9813"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pabitra Mitra","raw_affiliation_strings":["Computer Science and Engineering, Indian Institute of Technology Kharagpur, Kharagpur, India"],"raw_orcid":"https://orcid.org/0000-0002-1908-9813","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Indian Institute of Technology Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100976267","display_name":"Sugata Bose","orcid":"https://orcid.org/0000-0002-6756-1393"},"institutions":[{"id":"https://openalex.org/I46603895","display_name":"Varian Medical Systems (United States)","ror":"https://ror.org/05yab6874","country_code":"US","type":"company","lineage":["https://openalex.org/I46603895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Supratik Bose","raw_affiliation_strings":["Varian Medical Systems, San Ramon, USA"],"raw_orcid":"https://orcid.org/0000-0002-6756-1393","affiliations":[{"raw_affiliation_string":"Varian Medical Systems, San Ramon, USA","institution_ids":["https://openalex.org/I46603895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.7095000147819519},{"id":"https://openalex.org/keywords/medical-diagnosis","display_name":"Medical diagnosis","score":0.6467999815940857},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6176999807357788},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5921000242233276},{"id":"https://openalex.org/keywords/unified-medical-language-system","display_name":"Unified Medical Language System","score":0.5845000147819519},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.40639999508857727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7802000045776367},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.7095000147819519},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.6467999815940857},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6176999807357788},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5921000242233276},{"id":"https://openalex.org/C69505689","wikidata":"https://www.wikidata.org/wiki/Q455338","display_name":"Unified Medical Language System","level":2,"score":0.5845000147819519},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5322999954223633},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5133000016212463},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5115000009536743},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33570000529289246},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.273499995470047},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C3019150057","wikidata":"https://www.wikidata.org/wiki/Q92779279","display_name":"Medical information","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774521.3774604","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774604","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774521.3774604","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774604","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2064675550","https://openalex.org/W2136655611","https://openalex.org/W2159583324","https://openalex.org/W2194775991","https://openalex.org/W2611650229","https://openalex.org/W2897980926","https://openalex.org/W2915623326","https://openalex.org/W2962858109","https://openalex.org/W2963150162","https://openalex.org/W2963954913","https://openalex.org/W2979525559","https://openalex.org/W2995225687","https://openalex.org/W3035682985","https://openalex.org/W3104050923","https://openalex.org/W3164670515","https://openalex.org/W3165058054","https://openalex.org/W3198570286","https://openalex.org/W3200936534","https://openalex.org/W3203255640","https://openalex.org/W3203635737","https://openalex.org/W4295917908","https://openalex.org/W4386566421","https://openalex.org/W4387211307"],"related_works":[],"abstract_inverted_index":{"Medical":[0,98],"Visual":[1],"Question":[2],"Answering":[3],"(MedVQA)":[4],"is":[5,220],"a":[6,97,206],"complex":[7],"multimodal":[8],"problem":[9],"that":[10,66,103],"requires":[11],"fine-grained":[12],"reasoning":[13],"over":[14],"medical":[15,22,34,124,133,153],"images":[16],"and":[17,64,128,142,182,212],"associated":[18],"textual":[19],"queries.":[20],"Recent":[21],"Vision-Language":[23],"Pretraining(VLP)":[24],"advancements":[25],"have":[26],"significantly":[27],"improved":[28,184],"MedVQA":[29,192,202],"performance":[30,189,197,207],"by":[31],"leveraging":[32],"large-scale":[33],"image-caption":[35],"datasets.":[36,193,203],"Existing":[37],"methods":[38],"use":[39],"instance":[40],"contrastive":[41],"learning":[42],"objectives":[43,48],"for":[44],"image-text":[45,51,100,107,168],"alignment.":[46],"These":[47,160],"treat":[49],"each":[50],"pair":[52],"as":[53],"an":[54],"isolated":[55],"instance,":[56],"ignoring":[57],"the":[58,80,85,152,164,167,171,196],"shared":[59],"high-level":[60],"semantics":[61],"like":[62],"diseases":[63],"organs":[65],"often":[67],"exist":[68],"between":[69],"patients.":[70],"Hence,":[71],"semantically":[72,105],"similar":[73],"examples":[74],"may":[75],"be":[76],"undesirably":[77],"repelled":[78],"in":[79,170],"embedding":[81,172],"space.":[82,173],"This":[83],"limits":[84],"model\u2019s":[86],"ability":[87],"to":[88,109,131,156,187],"learn":[89],"meaningful":[90],"representations.":[91],"In":[92],"this":[93],"work,":[94],"we":[95],"propose":[96],"semantics-aware":[99],"alignment":[101,165],"loss":[102],"allows":[104],"related":[106],"pairs":[108],"align":[110],"even":[111],"if":[112],"they":[113],"come":[114],"from":[115,126],"different":[116],"patients,":[117],"capturing":[118],"latent":[119],"clinical":[120],"similarity.":[121],"We":[122,150,194,204],"extract":[123],"entities":[125],"captions":[127],"map":[129],"them":[130],"their":[132,157],"concepts":[134,154],"(C3":[135],"segment":[136],"of":[137,166,209],"spinal":[138],"cord,":[139],"Pneumonia,":[140],"etc.)":[141],"semantic":[143,158,161],"category(Anatomical":[144],"Structure,":[145],"Disease":[146],"or":[147],"Syndrome,":[148],"etc.).":[149],"cluster":[151],"according":[155],"category.":[159],"groups":[162],"guide":[163],"features":[169],"Our":[174,218],"method":[175],"seamlessly":[176],"integrates":[177],"into":[178],"existing":[179],"VLP":[180],"pipelines":[181],"demonstrates":[183],"alignment,":[185],"leading":[186],"stronger":[188],"on":[190,198,214],"downstream":[191],"evaluate":[195],"three":[199,215],"publicly":[200],"available":[201,221],"achieve":[205],"gain":[208],"1.77%,":[210],"0.95%,":[211],"1%":[213],"datasets":[216],"respectively.":[217],"code":[219],"at":[222],"https://github.com/Vasudha27/MSAITA_MedVQA":[223]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-08-01T00:00:00"}