{"id":"https://openalex.org/W4415538778","doi":"https://doi.org/10.1145/3746027.3754991","title":"Semantic-Aware Hard Negative Mining for Medical Vision-Language Contrastive Pretraining","display_name":"Semantic-Aware Hard Negative Mining for Medical Vision-Language Contrastive Pretraining","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538778","doi":"https://doi.org/10.1145/3746027.3754991"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754991","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd 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":null,"display_name":"Yongxin Li","orcid":"https://orcid.org/0009-0006-0499-2192"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongxin Li","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-0499-2192","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114859513","display_name":"Ying Cheng","orcid":"https://orcid.org/0000-0002-8964-3998"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Cheng","raw_affiliation_strings":["School of Computer Science and Technology, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8964-3998","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102737326","display_name":"Yaning Pan","orcid":"https://orcid.org/0009-0006-0936-470X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaning Pan","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-0936-470X","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112118627","display_name":"Wen He","orcid":"https://orcid.org/0000-0003-0440-8516"},"institutions":[{"id":"https://openalex.org/I4210159329","display_name":"Children's Hospital of Fudan University","ror":"https://ror.org/05n13be63","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210159329"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen He","raw_affiliation_strings":["National Children's Medical Center, Children's Hospital of Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0440-8516","affiliations":[{"raw_affiliation_string":"National Children's Medical Center, Children's Hospital of Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I4210159329"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115597561","display_name":"Qing Wang","orcid":"https://orcid.org/0009-0004-6252-2565"},"institutions":[{"id":"https://openalex.org/I4210159329","display_name":"Children's Hospital of Fudan University","ror":"https://ror.org/05n13be63","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210159329"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Wang","raw_affiliation_strings":["National Children's Medical Center, Children's Hospital of Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-6252-2565","affiliations":[{"raw_affiliation_string":"National Children's Medical Center, Children's Hospital of Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I4210159329"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100680617","display_name":"Rui Feng","orcid":"https://orcid.org/0000-0002-4747-0574"},"institutions":[{"id":"https://openalex.org/I4210159329","display_name":"Children's Hospital of Fudan University","ror":"https://ror.org/05n13be63","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210159329"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Feng","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China, National Children's Medical Center, Children's Hospital of Fudan University, Shanghai, China, and College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4747-0574","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China, National Children's Medical Center, Children's Hospital of Fudan University, Shanghai, China, and College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I4210159329"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100462481","display_name":"Xiaobo Zhang","orcid":"https://orcid.org/0000-0002-8645-5414"},"institutions":[{"id":"https://openalex.org/I4210159329","display_name":"Children's Hospital of Fudan University","ror":"https://ror.org/05n13be63","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210159329"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobo Zhang","raw_affiliation_strings":["National Children's Medical Center, Children's Hospital of Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8645-5414","affiliations":[{"raw_affiliation_string":"National Children's Medical Center, Children's Hospital of Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I4210159329"]}]}],"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":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3133","last_page":"3142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9966999888420105,"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/T12874","display_name":"Digital Imaging for Blood Diseases","score":0.9936000108718872,"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/similarity","display_name":"Similarity (geometry)","score":0.676800012588501},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6589999794960022},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6028000116348267},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.566100001335144},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.507099986076355},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45329999923706055},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.41019999980926514},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.3919000029563904}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.676800012588501},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6589999794960022},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6276999711990356},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6028000116348267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.579200029373169},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.566100001335144},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.507099986076355},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47749999165534973},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45329999923706055},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.41019999980926514},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40939998626708984},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3919000029563904},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36250001192092896},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.36149999499320984},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3034000098705292},{"id":"https://openalex.org/C2777946921","wikidata":"https://www.wikidata.org/wiki/Q7449044","display_name":"Semantic analysis (machine learning)","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C113619468","wikidata":"https://www.wikidata.org/wiki/Q595597","display_name":"Negative","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C3019060180","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automated method","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.26030001044273376}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754991","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3380183446","display_name":null,"funder_award_id":"EKYX202409","funder_id":"https://openalex.org/F4320321851","funder_display_name":"Fudan University"},{"id":"https://openalex.org/G6549978052","display_name":null,"funder_award_id":"No.62172101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321851","display_name":"Fudan University","ror":"https://ror.org/013q1eq08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2096733369","https://openalex.org/W2194775991","https://openalex.org/W2611650229","https://openalex.org/W2886281300","https://openalex.org/W2901954625","https://openalex.org/W2914203365","https://openalex.org/W2963466845","https://openalex.org/W3106743555","https://openalex.org/W3201906559","https://openalex.org/W4304092062","https://openalex.org/W4312533035","https://openalex.org/W4384162023","https://openalex.org/W4385347692","https://openalex.org/W4385573131","https://openalex.org/W7093349750"],"related_works":[],"abstract_inverted_index":{"Existing":[0],"medical":[1,22,187],"vision-language":[2],"contrastive":[3],"pretraining":[4],"methods":[5,67],"aim":[6],"to":[7,35,52,61,75,114,118,136,158,175],"bring":[8],"the":[9,17,36,47,55,70,112,137,150,155,177,200],"paired":[10],"image-report":[11],"embeddings":[12],"close":[13,51],"together":[14],"while":[15,163],"pushing":[16],"unpaired":[18],"ones":[19],"apart.":[20],"However,":[21],"images":[23],"often":[24,79],"exhibit":[25],"high":[26,129],"inter-class":[27],"visual":[28],"similarity":[29,72,131,135],"with":[30,128],"only":[31,69],"subtle":[32],"differences,":[33],"leading":[34],"presence":[37],"of":[38,179,202],"hard":[39,77,85,105,119,122],"negative":[40],"samples":[41,74,127,162],"that":[42],"are":[43,124],"semantically":[44,63,160,165],"distinct":[45],"from":[46,107],"anchor":[48,138],"but":[49,132],"incorrectly":[50],"it":[53,59],"in":[54],"embedding":[56,71,130],"space,":[57],"making":[58],"challenging":[60],"distinguish":[62],"dissimilar":[64,161],"samples.":[65],"Previous":[66],"consider":[68],"between":[73],"identify":[76],"negatives,":[78],"wrongly":[80],"treating":[81],"false":[82,108],"negatives":[83,106,109,123],"as":[84,126],"negatives.":[86,120],"To":[87],"address":[88],"this":[89],"issue,":[90],"we":[91],"design":[92],"a":[93,171],"simple":[94],"yet":[95],"effective":[96],"approach":[97],"called":[98],"Semantic-Aware":[99],"Hard":[100],"Negative":[101],"mining":[102],"(SAHN),":[103],"distinguishing":[104],"and":[110,139,196],"encouraging":[111],"model":[113],"pay":[115],"greater":[116,141],"attention":[117],"Specifically,":[121],"identified":[125],"low":[133],"semantic":[134,194],"assigned":[140],"importance":[142,147],"weights.":[143],"By":[144],"integrating":[145],"these":[146],"weights":[148],"into":[149],"InfoNCE":[151],"loss,":[152],"SAHN":[153],"enhances":[154],"model's":[156],"ability":[157],"separate":[159],"clustering":[164],"similar":[166],"ones.":[167],"We":[168],"further":[169],"conduct":[170],"gradient-based":[172],"theoretical":[173],"analysis":[174],"validate":[176],"effectiveness":[178],"SAHN.":[180],"Extensive":[181],"experimental":[182],"results":[183],"on":[184],"four":[185],"downstream":[186],"tasks":[188],"covering":[189],"image":[190],"classification,":[191],"object":[192],"detection,":[193],"segmentation,":[195],"cross-modal":[197],"retrieval":[198],"demonstrate":[199],"superiority":[201],"our":[203],"approach.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}