{"id":"https://openalex.org/W4385695898","doi":"https://doi.org/10.1109/tmm.2023.3303690","title":"Learning Music-Dance Representations Through Explicit-Implicit Rhythm Synchronization","display_name":"Learning Music-Dance Representations Through Explicit-Implicit Rhythm Synchronization","publication_year":2023,"publication_date":"2023-08-09","ids":{"openalex":"https://openalex.org/W4385695898","doi":"https://doi.org/10.1109/tmm.2023.3303690"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3303690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3303690","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Transactions on Multimedia","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/A5052798964","display_name":"Jiashuo Yu","orcid":"https://orcid.org/0000-0002-3094-6687"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"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":true,"raw_author_name":"Jiashuo Yu","raw_affiliation_strings":["ARC Lab, PCG Tencent, Shenzhen, China","School of Computer Science, Shanghai Key Lab of Intelligent Information Processing, Shanghai Collaborative Innovation Center of Intelligent Visual Computing, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3094-6687","affiliations":[{"raw_affiliation_string":"ARC Lab, PCG Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"School of Computer Science, Shanghai Key Lab of Intelligent Information Processing, Shanghai Collaborative Innovation Center of Intelligent Visual Computing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058880230","display_name":"Junfu Pu","orcid":"https://orcid.org/0000-0002-9915-5437"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfu Pu","raw_affiliation_strings":["Applied Research Center, PCG, Tencent, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-9915-5437","affiliations":[{"raw_affiliation_string":"Applied Research Center, PCG, Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"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/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":"Ying Cheng","raw_affiliation_strings":["Academy for Engineering and Technology, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8964-3998","affiliations":[{"raw_affiliation_string":"Academy for Engineering and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"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/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":"Rui Feng","raw_affiliation_strings":["School of Computer Science, Shanghai Key Lab of Intelligent Information Processing, Shanghai Collaborative Innovation Center of Intelligent Visual Computing, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4747-0574","affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Key Lab of Intelligent Information Processing, Shanghai Collaborative Innovation Center of Intelligent Visual Computing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102004349","display_name":"Ying Shan","orcid":"https://orcid.org/0000-0001-7673-8325"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Shan","raw_affiliation_strings":["Applied Research Center, PCG, Tencent, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-7673-8325","affiliations":[{"raw_affiliation_string":"Applied Research Center, PCG, Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5052798964"],"corresponding_institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":1.5025,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.8339943,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"26","issue":null,"first_page":"8454","last_page":"8463"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11349","display_name":"Music Technology and Sound Studies","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/T10788","display_name":"Neuroscience and Music Perception","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7985826730728149},{"id":"https://openalex.org/keywords/dance","display_name":"Dance","score":0.7380788326263428},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.6512476205825806},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.6380579471588135},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4357047975063324},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.16367533802986145},{"id":"https://openalex.org/keywords/aesthetics","display_name":"Aesthetics","score":0.13136222958564758},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.09887397289276123},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09206509590148926}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7985826730728149},{"id":"https://openalex.org/C147446459","wikidata":"https://www.wikidata.org/wiki/Q11639","display_name":"Dance","level":2,"score":0.7380788326263428},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.6512476205825806},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.6380579471588135},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4357047975063324},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.16367533802986145},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.13136222958564758},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.09887397289276123},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09206509590148926},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3303690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3303690","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.44999998807907104,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5464079932","display_name":null,"funder_award_id":"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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1940872118","https://openalex.org/W2095705004","https://openalex.org/W2096733369","https://openalex.org/W2128730107","https://openalex.org/W2171819471","https://openalex.org/W2191779130","https://openalex.org/W2296283641","https://openalex.org/W2497597915","https://openalex.org/W2619697695","https://openalex.org/W2785162511","https://openalex.org/W2811167645","https://openalex.org/W2914050240","https://openalex.org/W2962865004","https://openalex.org/W2962960500","https://openalex.org/W2963115079","https://openalex.org/W2963351448","https://openalex.org/W2963782415","https://openalex.org/W2981851635","https://openalex.org/W2982619606","https://openalex.org/W2989980422","https://openalex.org/W3010876998","https://openalex.org/W3011941208","https://openalex.org/W3017343282","https://openalex.org/W3024979138","https://openalex.org/W3048939150","https://openalex.org/W3084572050","https://openalex.org/W3085795245","https://openalex.org/W3093215104","https://openalex.org/W3093287838","https://openalex.org/W3099638501","https://openalex.org/W3105160031","https://openalex.org/W3106118231","https://openalex.org/W3113172960","https://openalex.org/W3116298410","https://openalex.org/W3153167542","https://openalex.org/W3157425405","https://openalex.org/W3172444685","https://openalex.org/W3173187964","https://openalex.org/W3175300676","https://openalex.org/W3205091761","https://openalex.org/W4240592325","https://openalex.org/W4385245566","https://openalex.org/W6604828220","https://openalex.org/W6631190155","https://openalex.org/W6674330103","https://openalex.org/W6682082992","https://openalex.org/W6735927292","https://openalex.org/W6748118685","https://openalex.org/W6754048563","https://openalex.org/W6755207826","https://openalex.org/W6770805772","https://openalex.org/W6779661269","https://openalex.org/W6780294235","https://openalex.org/W6783539077","https://openalex.org/W6785011006","https://openalex.org/W6789528441","https://openalex.org/W6794473712","https://openalex.org/W6796531822","https://openalex.org/W6796928388"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W597595235","https://openalex.org/W3200585538","https://openalex.org/W2357651146","https://openalex.org/W1574267311","https://openalex.org/W2501127304","https://openalex.org/W3209785493","https://openalex.org/W3120492113"],"abstract_inverted_index":{"Although":[0],"audio-visual":[1,154],"representation":[2,14],"has":[3],"been":[4],"proven":[5],"to":[6,71,173],"be":[7,171],"applicable":[8],"in":[9,81,134],"many":[10],"downstream":[11,175],"tasks,":[12],"the":[13,36,40,44,73,89,101,106,113,120,128,145,150,161],"of":[15,43,75,122,131,163],"dancing":[16],"videos,":[17],"which":[18,116],"is":[19],"more":[20],"specific":[21],"and":[22,33,46,77,83,96,136,166,183],"always":[23],"accompanied":[24],"by":[25,100,119,139,148,198],"music":[26,47,76,102,114],"with":[27,112,160],"complex":[28],"auditory":[29],"contents,":[30],"remains":[31],"challenging":[32],"uninvestigated.":[34],"Considering":[35],"intrinsic":[37],"alignment":[38],"between":[39,153],"cadent":[41],"movement":[42],"dancer":[45],"rhythm,":[48],"we":[49,87,126],"introduce":[50],"<bold":[51,57,61,65],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[52,58,62,66],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">MuDaR</b>":[53],",":[54],"a":[55,199],"novel":[56],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Mu</b>":[59],"sic-":[60],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Da</b>":[63],"nce":[64],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">R</b>":[67],"epresentation":[68],"learning":[69],"framework":[70,193],"perform":[72],"synchronization":[74],"dance":[78,90,178],"rhythms":[79,91,108,132],"both":[80],"explicit":[82],"implicit":[84,129],"ways.":[85],"Specifically,":[86],"derive":[88],"based":[92],"on":[93],"visual":[94,107,137,167],"appearance":[95],"motion":[97],"cues":[98],"inspired":[99],"rhythm":[103],"analysis.":[104],"Then":[105],"are":[109,117],"temporally":[110],"aligned":[111],"counterparts,":[115],"extracted":[118],"amplitude":[121],"sound":[123],"intensity.":[124],"Meanwhile,":[125],"exploit":[127],"coherence":[130],"implied":[133],"audio":[135,165],"streams":[138],"contrastive":[140],"learning.":[141],"The":[142,156],"model":[143],"learns":[144],"joint":[146],"embedding":[147],"predicting":[149],"temporal":[151],"consistency":[152],"pairs.":[155],"music-dance":[157,181,185],"representation,":[158],"together":[159],"capability":[162],"detecting":[164],"rhythms,":[168],"can":[169],"further":[170],"applied":[172],"three":[174],"tasks:":[176],"(a)":[177],"classification,":[179],"(b)":[180],"retrieval,":[182],"(c)":[184],"retargeting.":[186],"Extensive":[187],"experiments":[188],"demonstrate":[189],"that":[190],"our":[191],"proposed":[192],"outperforms":[194],"other":[195],"self-supervised":[196],"methods":[197],"large":[200],"margin.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-05-20T08:49:12.498775","created_date":"2023-08-10T00:00:00"}