{"id":"https://openalex.org/W4392903955","doi":"https://doi.org/10.1109/icassp48485.2024.10446808","title":"Dual-Mix for Cross-Modal Retrieval with Noisy Labels","display_name":"Dual-Mix for Cross-Modal Retrieval with Noisy Labels","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903955","doi":"https://doi.org/10.1109/icassp48485.2024.10446808"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100626870","display_name":"Feng Ding","orcid":"https://orcid.org/0000-0003-2512-5443"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Ding","raw_affiliation_strings":["Dalian University of Technology,School of Software Technology,Dalian,China,116620"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Software Technology,Dalian,China,116620","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668978","display_name":"Xiu Liu","orcid":"https://orcid.org/0009-0005-5721-4100"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiu Liu","raw_affiliation_strings":["Dalian University of Technology,School of Software Technology,Dalian,China,116620"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Software Technology,Dalian,China,116620","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100382947","display_name":"Xinyi Wang","orcid":"https://orcid.org/0000-0002-5278-6872"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyi Wang","raw_affiliation_strings":["Dalian University of Technology,School of Software Technology,Dalian,China,116620"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Software Technology,Dalian,China,116620","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091207959","display_name":"Fangming Zhong","orcid":"https://orcid.org/0000-0002-2775-8175"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangming Zhong","raw_affiliation_strings":["Dalian University of Technology,School of Software Technology,Dalian,China,116620"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Software Technology,Dalian,China,116620","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":0.5259,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64912828,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"6505","last_page":"6509"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994000196456909,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994000196456909,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9951000213623047,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9948999881744385,"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/modal","display_name":"Modal","score":0.7048702836036682},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6946080327033997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5460756421089172},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5229095816612244},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5171005725860596},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.5135214924812317},{"id":"https://openalex.org/keywords/cross-validation","display_name":"Cross-validation","score":0.43539106845855713},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.4325811266899109},{"id":"https://openalex.org/keywords/mixing","display_name":"Mixing (physics)","score":0.4222131073474884},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34985023736953735},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34863561391830444},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.34413665533065796},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.07075187563896179}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7048702836036682},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6946080327033997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5460756421089172},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5229095816612244},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5171005725860596},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.5135214924812317},{"id":"https://openalex.org/C27181475","wikidata":"https://www.wikidata.org/wiki/Q541014","display_name":"Cross-validation","level":2,"score":0.43539106845855713},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.4325811266899109},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.4222131073474884},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34985023736953735},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34863561391830444},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34413665533065796},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.07075187563896179},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4237573054","display_name":null,"funder_award_id":"62006035","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/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2106277773","https://openalex.org/W2119775030","https://openalex.org/W2566079294","https://openalex.org/W2803187616","https://openalex.org/W2804165720","https://openalex.org/W2804378530","https://openalex.org/W2954672622","https://openalex.org/W2963351448","https://openalex.org/W2963735582","https://openalex.org/W2964081303","https://openalex.org/W2967957126","https://openalex.org/W2978426779","https://openalex.org/W2981873476","https://openalex.org/W2996108195","https://openalex.org/W3176451698","https://openalex.org/W4221138649","https://openalex.org/W4226172762","https://openalex.org/W4304083193","https://openalex.org/W4312097321","https://openalex.org/W4312382184","https://openalex.org/W4312601326","https://openalex.org/W4313135270","https://openalex.org/W4372259983","https://openalex.org/W4378417893","https://openalex.org/W4380520382","https://openalex.org/W6631190155","https://openalex.org/W6639103823","https://openalex.org/W6677994088","https://openalex.org/W6740005241","https://openalex.org/W6751420435","https://openalex.org/W6751647823","https://openalex.org/W6751883947","https://openalex.org/W6762913911","https://openalex.org/W6771630921","https://openalex.org/W6779784029","https://openalex.org/W6809741598"],"related_works":["https://openalex.org/W1571141552","https://openalex.org/W4391636338","https://openalex.org/W4386067343","https://openalex.org/W4294250823","https://openalex.org/W2093086151","https://openalex.org/W55936454","https://openalex.org/W2803187616","https://openalex.org/W2963759070","https://openalex.org/W2025158506","https://openalex.org/W3082640823"],"abstract_inverted_index":{"Cross-modal":[0],"retrieval":[1],"with":[2,73],"deep":[3],"neural":[4],"networks":[5],"heavily":[6],"relies":[7],"on":[8],"accurate":[9],"annotation.":[10],"However,":[11],"existing":[12],"methods":[13],"may":[14],"easily":[15],"suffer":[16],"from":[17],"the":[18,26,52,85,96,100,135,143],"scarcity":[19,136],"and":[20,89,105,119],"validity":[21],"of":[22,29,54,79,137,146],"annotations":[23],"due":[24],"to":[25,50,111,132],"expensive":[27],"cost":[28],"manual":[30],"labeling.":[31,43],"In":[32,60,95],"addition,":[33],"it":[34,47],"is":[35,48],"inevitable":[36],"that":[37],"noisy":[38,55,74,93,120],"labels":[39,56,75],"are":[40,83,109],"imposed":[41],"during":[42],"To":[44],"this":[45,61],"end,":[46],"worthwhile":[49],"explore":[51],"potential":[53],"in":[57],"cross-modal":[58],"retrieval.":[59],"work,":[62],"we":[63,126],"propose":[64],"a":[65],"novel":[66],"framework":[67],"entitled":[68],"Dual-Mix":[69],"for":[70,92],"Cross-Modal":[71],"Retrieval":[72],"(DMCM).":[76],"It":[77],"consists":[78],"two":[80],"components,":[81],"which":[82],"mixing":[84,90,98],"robust":[86],"loss":[87],"functions":[88],"augmentation":[91,131],"samples.":[94,139],"first":[97],"stage,":[99],"normalized":[101],"generalized":[102],"cross":[103],"entropy":[104],"mean":[106],"absolute":[107],"error":[108],"combined":[110],"boost":[112],"each":[113],"other.":[114],"Then,":[115],"after":[116],"separating":[117],"clean":[118],"samples":[121,129],"by":[122],"Beta":[123],"Mixture":[124],"Model,":[125],"mix":[127],"these":[128],"via":[130],"further":[133],"address":[134],"labeled":[138],"Extensive":[140],"experiments":[141],"demonstrate":[142],"significant":[144],"superiority":[145],"our":[147],"DMCM.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}