{"id":"https://openalex.org/W2950864153","doi":"https://doi.org/10.1109/icassp.2019.8682524","title":"Perfect Match: Improved Cross-modal Embeddings for Audio-visual Synchronisation","display_name":"Perfect Match: Improved Cross-modal Embeddings for Audio-visual Synchronisation","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2950864153","doi":"https://doi.org/10.1109/icassp.2019.8682524","mag":"2950864153"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682524","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1809.08001","any_repository_has_fulltext":true},"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 & Electronic Engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical & 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 Corp., Seongnam-si, Gyeonggi-do, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corp., Seongnam-si, Gyeonggi-do, 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 & Electronic Engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical & 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":11.5617,"has_fulltext":false,"cited_by_count":110,"citation_normalized_percentile":{"value":0.99084696,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3965","last_page":"3969"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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":0.9965999722480774,"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":0.823491632938385},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7800418138504028},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6816220283508301},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5871570706367493},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.532310426235199},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5146337747573853},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.508658230304718},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4952758848667145},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.41692739725112915},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4056823253631592},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40331047773361206},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.17140820622444153},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.07069876790046692}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.823491632938385},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7800418138504028},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6816220283508301},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5871570706367493},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.532310426235199},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5146337747573853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.508658230304718},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4952758848667145},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.41692739725112915},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4056823253631592},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40331047773361206},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.17140820622444153},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.07069876790046692},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2019.8682524","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1809.08001","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.08001","pdf_url":"https://arxiv.org/pdf/1809.08001","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1809.08001","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.08001","pdf_url":"https://arxiv.org/pdf/1809.08001","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2100495367","https://openalex.org/W2326925005","https://openalex.org/W2551572271","https://openalex.org/W2594690981","https://openalex.org/W2604379605","https://openalex.org/W2793493229","https://openalex.org/W2796992393","https://openalex.org/W2803113447","https://openalex.org/W2809716557","https://openalex.org/W2886564777","https://openalex.org/W2949307595","https://openalex.org/W2952746495","https://openalex.org/W2962918445","https://openalex.org/W2962960500","https://openalex.org/W2963115079","https://openalex.org/W2963173190","https://openalex.org/W2963420272","https://openalex.org/W2963680395","https://openalex.org/W2963887950","https://openalex.org/W6701655646","https://openalex.org/W6734491695","https://openalex.org/W6735927292","https://openalex.org/W6749336676","https://openalex.org/W6751966083","https://openalex.org/W6753054903","https://openalex.org/W6753490960"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2393726419"],"abstract_inverted_index":{"This":[0],"paper":[1,59],"proposes":[2],"a":[3,37,66,76,83,135],"new":[4,67],"strategy":[5,69],"for":[6,11,118],"learning":[7,49,68],"powerful":[8],"cross-modal":[9,23,52],"embeddings":[10,72,117],"audio-to-video":[12],"synchronisation.":[13],"Here,":[14],"we":[15,64,96,113],"set":[16],"up":[17],"the":[18,26,31,45,71,105,109,115,127,130],"problem":[19,89],"as":[20,61,80,90],"one":[21],"of":[22,57,100],"retrieval,":[24],"where":[25,70],"objective":[27],"is":[28],"to":[29,82],"find":[30],"most":[32],"relevant":[33],"audio":[34],"segment":[35],"given":[36],"short":[38],"video":[39],"clip.":[40],"The":[41,54],"method":[42,102],"builds":[43],"on":[44,108],"recent":[46,93],"advances":[47],"in":[48,122,134],"representations":[50,131],"from":[51],"self-supervision.":[53],"main":[55],"contributions":[56],"this":[58,101],"are":[60,73],"follows:":[62],"(1)":[63],"propose":[65],"learnt":[74,116,132],"via":[75],"multi-way":[77],"matching":[78],"problem,":[79],"opposed":[81],"binary":[84],"classification":[85],"(matching":[86],"or":[87],"non-matching)":[88],"proposed":[91],"by":[92],"papers;":[94],"(2)":[95],"demonstrate":[97],"that":[98,126],"performance":[99,128],"far":[103],"exceeds":[104],"existing":[106],"baselines":[107],"synchronisation":[110],"task;":[111],"(3)":[112],"use":[114],"visual":[119],"speech":[120],"recognition":[121],"self-supervision,":[123],"and":[124],"show":[125],"matches":[129],"end-to-end":[133],"fully-supervised":[136],"manner.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":32},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":7}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}