{"id":"https://openalex.org/W4401387482","doi":"https://doi.org/10.1109/tpami.2024.3429301","title":"Self-Supervised Multimodal Learning: A Survey","display_name":"Self-Supervised Multimodal Learning: A Survey","publication_year":2024,"publication_date":"2024-08-07","ids":{"openalex":"https://openalex.org/W4401387482","doi":"https://doi.org/10.1109/tpami.2024.3429301","pmid":"https://pubmed.ncbi.nlm.nih.gov/39110564"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3429301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3429301","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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":"Yongshuo Zong","orcid":"https://orcid.org/0009-0002-6726-8776"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yongshuo Zong","raw_affiliation_strings":["School of Informatics, University of Edinburgh, Edinburgh, U.K","School of Informatics, University of Edinburgh, U.K"],"raw_orcid":"https://orcid.org/0009-0002-6726-8776","affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"School of Informatics, University of Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063600180","display_name":"Oisin Mac Aodha","orcid":"https://orcid.org/0000-0002-5787-5073"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oisin Mac Aodha","raw_affiliation_strings":["School of Informatics, University of Edinburgh, Edinburgh, U.K","School of Informatics, University of Edinburgh, U.K"],"raw_orcid":"https://orcid.org/0000-0002-5787-5073","affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"School of Informatics, University of Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107949426","display_name":"Timothy Hospedales","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Timothy M. Hospedales","raw_affiliation_strings":["School of Informatics, University of Edinburgh, Edinburgh, U.K","School of Informatics, University of Edinburgh, U.K"],"raw_orcid":"https://orcid.org/0000-0003-4867-7486","affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"School of Informatics, University of Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":19.0119,"has_fulltext":false,"cited_by_count":80,"citation_normalized_percentile":{"value":0.99499236,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"47","issue":"7","first_page":"5299","last_page":"5318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.7444999814033508,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.7444999814033508,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.6695312857627869},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6570045948028564},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49815964698791504},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34435558319091797}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6695312857627869},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6570045948028564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49815964698791504},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34435558319091797}],"mesh":[{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3429301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3429301","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:39110564","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39110564","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":191,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1912570122","https://openalex.org/W2100235303","https://openalex.org/W2110119381","https://openalex.org/W2157364932","https://openalex.org/W2194775991","https://openalex.org/W2203271703","https://openalex.org/W2277195237","https://openalex.org/W2321533354","https://openalex.org/W2423557781","https://openalex.org/W2619383789","https://openalex.org/W2619697695","https://openalex.org/W2767290858","https://openalex.org/W2767325013","https://openalex.org/W2787666871","https://openalex.org/W2796093898","https://openalex.org/W2842511635","https://openalex.org/W2883725317","https://openalex.org/W2917551568","https://openalex.org/W2962793481","https://openalex.org/W2962865004","https://openalex.org/W2962960500","https://openalex.org/W2964187781","https://openalex.org/W2964532449","https://openalex.org/W2968095426","https://openalex.org/W2970231061","https://openalex.org/W2981851019","https://openalex.org/W2981851635","https://openalex.org/W2982619606","https://openalex.org/W2992478697","https://openalex.org/W2998356391","https://openalex.org/W3017343282","https://openalex.org/W3023371261","https://openalex.org/W3035265375","https://openalex.org/W3035635319","https://openalex.org/W3035725276","https://openalex.org/W3042609801","https://openalex.org/W3048939150","https://openalex.org/W3090350559","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3105232955","https://openalex.org/W3108655343","https://openalex.org/W3121972911","https://openalex.org/W3153167542","https://openalex.org/W3154222058","https://openalex.org/W3158986867","https://openalex.org/W3171536535","https://openalex.org/W3172424021","https://openalex.org/W3175300676","https://openalex.org/W3176445421","https://openalex.org/W3176481196","https://openalex.org/W3177224328","https://openalex.org/W3182680257","https://openalex.org/W3184369217","https://openalex.org/W3188030217","https://openalex.org/W3188558905","https://openalex.org/W3190018318","https://openalex.org/W3193171560","https://openalex.org/W3201597391","https://openalex.org/W3201906559","https://openalex.org/W3203711169","https://openalex.org/W3207924272","https://openalex.org/W3212022090","https://openalex.org/W3217084439","https://openalex.org/W4200436929","https://openalex.org/W4206471589","https://openalex.org/W4212844288","https://openalex.org/W4214717370","https://openalex.org/W4283697304","https://openalex.org/W4285606530","https://openalex.org/W4287891019","https://openalex.org/W4289821912","https://openalex.org/W4295185249","https://openalex.org/W4295951577","https://openalex.org/W4296027312","https://openalex.org/W4312245858","https://openalex.org/W4312317653","https://openalex.org/W4312384316","https://openalex.org/W4312420631","https://openalex.org/W4312463400","https://openalex.org/W4312629998","https://openalex.org/W4312709113","https://openalex.org/W4312810944","https://openalex.org/W4312818263","https://openalex.org/W4312864639","https://openalex.org/W4312910992","https://openalex.org/W4312973985","https://openalex.org/W4313123347","https://openalex.org/W4313128851","https://openalex.org/W4313156423","https://openalex.org/W4318071656","https://openalex.org/W4376226279","https://openalex.org/W4376481237","https://openalex.org/W4385245566","https://openalex.org/W4385573131","https://openalex.org/W4385573483","https://openalex.org/W4386071687","https://openalex.org/W4386071707","https://openalex.org/W4386072185","https://openalex.org/W4386075632","https://openalex.org/W4386076084","https://openalex.org/W4386180266","https://openalex.org/W4387195417","https://openalex.org/W4392752752","https://openalex.org/W4394606408","https://openalex.org/W4404356490","https://openalex.org/W4409057813","https://openalex.org/W6606244218","https://openalex.org/W6631216910","https://openalex.org/W6637108112","https://openalex.org/W6639103823","https://openalex.org/W6677082149","https://openalex.org/W6677477928","https://openalex.org/W6720501231","https://openalex.org/W6752474537","https://openalex.org/W6754048563","https://openalex.org/W6754184789","https://openalex.org/W6755207826","https://openalex.org/W6756256016","https://openalex.org/W6766904570","https://openalex.org/W6767211374","https://openalex.org/W6767279747","https://openalex.org/W6767624375","https://openalex.org/W6770196601","https://openalex.org/W6770805772","https://openalex.org/W6773737242","https://openalex.org/W6774733536","https://openalex.org/W6775188310","https://openalex.org/W6778883912","https://openalex.org/W6779518175","https://openalex.org/W6779579431","https://openalex.org/W6779739962","https://openalex.org/W6779823529","https://openalex.org/W6779844698","https://openalex.org/W6780191644","https://openalex.org/W6780294235","https://openalex.org/W6783961830","https://openalex.org/W6783990618","https://openalex.org/W6784185929","https://openalex.org/W6784761581","https://openalex.org/W6785011006","https://openalex.org/W6785028840","https://openalex.org/W6789753369","https://openalex.org/W6790019176","https://openalex.org/W6790830454","https://openalex.org/W6790978476","https://openalex.org/W6791353385","https://openalex.org/W6793736971","https://openalex.org/W6797307915","https://openalex.org/W6797716411","https://openalex.org/W6798805250","https://openalex.org/W6799465499","https://openalex.org/W6800139874","https://openalex.org/W6800751262","https://openalex.org/W6802142950","https://openalex.org/W6803316292","https://openalex.org/W6803567076","https://openalex.org/W6803728867","https://openalex.org/W6809646742","https://openalex.org/W6810007534","https://openalex.org/W6810168380","https://openalex.org/W6810334672","https://openalex.org/W6810443764","https://openalex.org/W6810452849","https://openalex.org/W6811013733","https://openalex.org/W6838154772","https://openalex.org/W6838461927","https://openalex.org/W6838580846","https://openalex.org/W6839003588","https://openalex.org/W6839091850","https://openalex.org/W6839213706","https://openalex.org/W6839423864","https://openalex.org/W6839579409","https://openalex.org/W6839936984","https://openalex.org/W6839990677","https://openalex.org/W6845354634","https://openalex.org/W6845514976","https://openalex.org/W6845577938","https://openalex.org/W6845952779","https://openalex.org/W6846007759","https://openalex.org/W6847495150","https://openalex.org/W6849141701","https://openalex.org/W6849177959","https://openalex.org/W6850159125","https://openalex.org/W6850184056","https://openalex.org/W6850503672","https://openalex.org/W6850625674","https://openalex.org/W6851949647","https://openalex.org/W6857083971"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W2033914206"],"abstract_inverted_index":{"Multimodal":[0],"learning,":[1],"which":[2,92],"aims":[3],"to":[4,56,72,99,129],"understand":[5],"and":[6,118,156,163,182,189],"analyze":[7],"information":[8],"from":[9,74,108,139,148],"multiple":[10],"modalities,":[11,117],"has":[12,51],"achieved":[13],"substantial":[14],"progress":[15],"in":[16,20,46,89,91,174],"the":[17,24,40,47,58,87,149],"supervised":[18],"regime":[19],"recent":[21],"years.":[22],"However,":[23],"heavy":[25],"dependence":[26],"on":[27,62],"data":[28,45,110,142],"paired":[29],"with":[30,102,121],"expensive":[31],"human":[32],"annotations":[33],"impedes":[34],"scaling":[35],"up":[36],"models.":[37],"Meanwhile,":[38],"given":[39],"availability":[41],"of":[42,86,115,151,171],"large-scale":[43],"unannotated":[44],"wild,":[48],"self-supervised":[49,66,100],"learning":[50,68,101,106,120,138,159],"become":[52],"an":[53],"attractive":[54],"strategy":[55],"alleviate":[57],"annotation":[59],"bottleneck.":[60],"Building":[61],"these":[63,130],"two":[64],"directions,":[65],"multimodal":[67,76,103,109,140,153],"(SSML)":[69],"provides":[70],"ways":[71],"learn":[73],"raw":[75],"data.":[77,123],"In":[78],"this":[79],"survey,":[80],"we":[81,93,133,186],"provide":[82],"a":[83],"comprehensive":[84],"review":[85,168],"state-of-the-art":[88],"SSML,":[90],"elucidate":[94],"three":[95],"major":[96],"challenges":[97,188],"intrinsic":[98],"data:":[104],"1)":[105,135],"representations":[107],"without":[111],"labels,":[112],"2)":[113,145],"fusion":[114,154],"different":[116,152],"3)":[119,157],"unaligned":[122],"We":[124,166],"then":[125],"detail":[126],"existing":[127],"solutions":[128],"challenges.":[131],"Specifically,":[132],"consider":[134],"objectives":[136],"for":[137,161,192],"unlabeled":[141],"via":[143],"self-supervision,":[144],"model":[146],"architectures":[147],"perspective":[150],"strategies,":[155],"pair-free":[158],"strategies":[160],"coarse-grained":[162],"fine-grained":[164],"alignment.":[165],"also":[167],"real-world":[169],"applications":[170],"SSML":[172],"algorithms":[173],"diverse":[175],"fields,":[176],"such":[177],"as":[178],"healthcare,":[179],"remote":[180],"sensing,":[181],"machine":[183],"translation.":[184],"Finally,":[185],"discuss":[187],"future":[190],"directions":[191],"SSML.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":28},{"year":2025,"cited_by_count":43},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2025-10-10T00:00:00"}