{"id":"https://openalex.org/W3016663370","doi":"https://doi.org/10.1109/jstsp.2020.2987720","title":"Perfect Match: Self-Supervised Embeddings for Cross-Modal Retrieval","display_name":"Perfect Match: Self-Supervised Embeddings for Cross-Modal Retrieval","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3016663370","doi":"https://doi.org/10.1109/jstsp.2020.2987720","mag":"3016663370"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2020.2987720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2020.2987720","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"type":"article","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/A5046276512","display_name":"Soo-Whan Chung","orcid":"https://orcid.org/0000-0001-6529-2196"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Soo-Whan Chung","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-6529-2196","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["Naver Corporation, Seongnam-si, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-7741-7275","affiliations":[{"raw_affiliation_string":"Naver Corporation, Seongnam-si, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056128107","display_name":"Hong-Goo Kang","orcid":"https://orcid.org/0000-0002-6554-0783"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong-Goo Kang","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-6554-0783","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046276512"],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":null,"apc_paid":null,"fwci":2.4311,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.89404319,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"14","issue":"3","first_page":"568","last_page":"576"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9975000023841858,"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/computer-science","display_name":"Computer science","score":0.8222670555114746},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.8045886158943176},{"id":"https://openalex.org/keywords/biometrics","display_name":"Biometrics","score":0.6161333918571472},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5415244102478027},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5308072566986084},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5185297727584839},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.4881478250026703},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4705132842063904},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4665519893169403},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4356766641139984},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3963056802749634},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35366448760032654},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07942605018615723}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8222670555114746},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.8045886158943176},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.6161333918571472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5415244102478027},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5308072566986084},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5185297727584839},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.4881478250026703},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4705132842063904},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4665519893169403},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4356766641139984},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3963056802749634},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35366448760032654},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07942605018615723},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2020.2987720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2020.2987720","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6700000166893005,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1498305593","https://openalex.org/W1533861849","https://openalex.org/W1686810756","https://openalex.org/W1934184906","https://openalex.org/W1974783905","https://openalex.org/W1983685275","https://openalex.org/W1988910659","https://openalex.org/W2030899956","https://openalex.org/W2038158923","https://openalex.org/W2042608483","https://openalex.org/W2070176749","https://openalex.org/W2071207147","https://openalex.org/W2096733369","https://openalex.org/W2100495367","https://openalex.org/W2106277773","https://openalex.org/W2108598243","https://openalex.org/W2109824782","https://openalex.org/W2133564696","https://openalex.org/W2143612262","https://openalex.org/W2157331557","https://openalex.org/W2157364932","https://openalex.org/W2325939864","https://openalex.org/W2326925005","https://openalex.org/W2327501763","https://openalex.org/W2400006663","https://openalex.org/W2403589179","https://openalex.org/W2551572271","https://openalex.org/W2555897561","https://openalex.org/W2594690981","https://openalex.org/W2598915960","https://openalex.org/W2604379605","https://openalex.org/W2619697695","https://openalex.org/W2726515241","https://openalex.org/W2793493229","https://openalex.org/W2796992393","https://openalex.org/W2803113447","https://openalex.org/W2808631503","https://openalex.org/W2809716557","https://openalex.org/W2883222475","https://openalex.org/W2950864153","https://openalex.org/W2951237705","https://openalex.org/W2952746495","https://openalex.org/W2962788625","https://openalex.org/W2962824366","https://openalex.org/W2962918445","https://openalex.org/W2962960500","https://openalex.org/W2963115079","https://openalex.org/W2963173190","https://openalex.org/W2963290645","https://openalex.org/W2963420272","https://openalex.org/W2963516811","https://openalex.org/W2963680395","https://openalex.org/W2963801643","https://openalex.org/W2963887950","https://openalex.org/W2964308564","https://openalex.org/W3043075211","https://openalex.org/W3099206234","https://openalex.org/W3151878189","https://openalex.org/W6631943919","https://openalex.org/W6637373629","https://openalex.org/W6667507107","https://openalex.org/W6679434410","https://openalex.org/W6700903540","https://openalex.org/W6712999683","https://openalex.org/W6713967443","https://openalex.org/W6730323794","https://openalex.org/W6750591037","https://openalex.org/W6751966083","https://openalex.org/W6752791795","https://openalex.org/W6753054903"],"related_works":["https://openalex.org/W2076845124","https://openalex.org/W2183964146","https://openalex.org/W2379932303","https://openalex.org/W2381300099","https://openalex.org/W2811048914","https://openalex.org/W1982479144","https://openalex.org/W1995633573","https://openalex.org/W2767198796","https://openalex.org/W2952745240","https://openalex.org/W2798097728"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3],"new":[4],"strategy":[5,69],"for":[6,76],"learning":[7,49,68],"effective":[8],"cross-modal":[9,22,52,83,104],"joint":[10,96],"embeddings":[11],"using":[12,54,126],"self-supervision.":[13],"We":[14],"set":[15],"up":[16],"the":[17,25,30,45,63,66,103,121],"problem":[18],"as":[19],"one":[20,35],"of":[21,65,98,123,132],"retrieval,":[23],"where":[24],"objective":[26],"is":[27],"to":[28,94],"find":[29],"most":[31],"relevant":[32],"data":[33],"in":[34,39,48],"domain":[36],"given":[37,111],"input":[38],"another.":[40],"The":[41,85],"method":[42,128],"builds":[43],"on":[44,135],"recent":[46],"advances":[47],"representations":[50,110],"from":[51],"self-supervision":[53],"contrastive":[55],"or":[56],"binary":[57],"cross-entropy":[58],"loss":[59],"functions.":[60],"To":[61],"investigate":[62],"robustness":[64],"proposed":[67,127],"across":[70],"multi-modal":[71],"applications,":[72],"we":[73],"perform":[74],"experiments":[75],"two":[77],"applications":[78],"-":[79],"audio-visual":[80,86],"synchronisation":[81,87],"and":[82,100,102,115],"biometrics.":[84],"task":[88,106],"requires":[89,107],"temporal":[90],"correspondence":[91],"between":[92],"modalities":[93],"obtain":[95],"representation":[97],"phonemes":[99],"visemes,":[101],"biometrics":[105],"common":[108],"speakers":[109],"their":[112],"face":[113],"images":[114],"audio":[116],"tracks.":[117],"Experiments":[118],"show":[119],"that":[120,131],"performance":[122],"systems":[124],"trained":[125],"far":[129],"exceed":[130],"existing":[133],"methods":[134],"both":[136],"tasks,":[137],"whilst":[138],"allowing":[139],"significantly":[140],"faster":[141],"training.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}