{"id":"https://openalex.org/W4408353571","doi":"https://doi.org/10.1109/icassp49660.2025.10890382","title":"Semi-Supervised Contrastive Learning for Controllable Video-to-Music Retrieval","display_name":"Semi-Supervised Contrastive Learning for Controllable Video-to-Music Retrieval","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353571","doi":"https://doi.org/10.1109/icassp49660.2025.10890382"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890382","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890382","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5028241671","display_name":"Shanti Stewart","orcid":null},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Shanti Stewart","raw_affiliation_strings":["Dolby Laboratories"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069874461","display_name":"Gouthaman KV","orcid":null},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Gouthaman KV","raw_affiliation_strings":["Dolby Laboratories"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110491600","display_name":"Lie Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Lie Lu","raw_affiliation_strings":["Dolby Laboratories"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066999416","display_name":"Andrea Fanelli","orcid":"https://orcid.org/0000-0001-9876-9050"},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Andrea Fanelli","raw_affiliation_strings":["Dolby Laboratories"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.064,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.72374072,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9876999855041504,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9843999743461609,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.807668149471283},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5113322138786316},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.4787665903568268},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4600841999053955},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41758736968040466},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3281744122505188},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.32804134488105774}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.807668149471283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5113322138786316},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.4787665903568268},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4600841999053955},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41758736968040466},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3281744122505188},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.32804134488105774}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890382","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890382","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2593116425","https://openalex.org/W2842511635","https://openalex.org/W2962970472","https://openalex.org/W3015371781","https://openalex.org/W3176445421","https://openalex.org/W3189197309","https://openalex.org/W3198668032","https://openalex.org/W4284898017","https://openalex.org/W4312319752","https://openalex.org/W4372260310","https://openalex.org/W4372267973","https://openalex.org/W4386076057","https://openalex.org/W4386763869","https://openalex.org/W4392903541","https://openalex.org/W6728047685","https://openalex.org/W6739901393","https://openalex.org/W6757817989","https://openalex.org/W6771024394","https://openalex.org/W6776700526","https://openalex.org/W6791353385","https://openalex.org/W6804120432","https://openalex.org/W6841982715","https://openalex.org/W6843026064","https://openalex.org/W6853393314"],"related_works":["https://openalex.org/W304855073","https://openalex.org/W4213212078","https://openalex.org/W938111471","https://openalex.org/W2511882081","https://openalex.org/W2518250394","https://openalex.org/W2032169142","https://openalex.org/W2267221041","https://openalex.org/W2399947890","https://openalex.org/W655728004","https://openalex.org/W2046272293"],"abstract_inverted_index":{"Content":[0],"creators":[1],"often":[2],"use":[3,96],"music":[4,15,27,52,65,77,83,109,121,137],"to":[5,13,102,135],"enhance":[6],"their":[7],"videos,":[8],"from":[9,80],"soundtracks":[10],"in":[11,16],"movies":[12],"background":[14],"video":[17,30],"blogs":[18],"and":[19,35,58,76,91,98,110,129,174,188,191],"social":[20],"media":[21],"content.":[22],"However,":[23],"identifying":[24],"the":[25,70,114,125,152,166,182],"best":[26],"for":[28,47,54,124,194],"a":[29,33,44,50,55,104,170],"can":[31,132],"be":[32,133],"difficult":[34],"time-consuming":[36],"task.":[37],"To":[38],"address":[39],"this":[40],"challenge,":[41],"we":[42],"propose":[43],"novel":[45],"framework":[46,131],"automatically":[48],"retrieving":[49],"matching":[51],"clip":[53],"given":[56],"video,":[57],"vice":[59],"versa.":[60],"Our":[61,178],"approach":[62,118,184],"leverages":[63],"annotated":[64],"labels,":[66],"as":[67,69],"well":[68],"inherent":[71],"artistic":[72],"correspondence":[73],"between":[74,108],"visual":[75],"elements.":[78],"Distinct":[79],"previous":[81],"cross-modal":[82],"retrieval":[84,153,176],"works,":[85],"our":[86,117,130,144],"method":[87,145],"combines":[88,186],"both":[89],"self-supervised":[90,97,157,187],"supervised":[92,126,189],"training":[93,127],"objectives.":[94],"We":[95,112,164],"label-supervised":[99],"contrastive":[100],"learning":[101],"train":[103],"joint":[105],"embedding":[106],"space":[107],"video.":[111],"show":[113,180],"effectiveness":[115],"of":[116,172],"by":[119],"using":[120],"genre":[122],"labels":[123],"component,":[128],"generalized":[134],"other":[136],"annotations":[138],"(e.g.,":[139],"emotion,":[140],"instrument,":[141],"etc.).":[142],"Furthermore,":[143],"enables":[146],"fine-grained":[147],"control":[148],"over":[149],"how":[150],"much":[151],"process":[154],"focuses":[155],"on":[156],"vs.":[158],"label":[159],"information":[160],"at":[161],"inference":[162],"time.":[163],"evaluate":[165],"learned":[167],"embeddings":[168],"through":[169],"variety":[171],"video-to-music":[173],"music-to-video":[175],"tasks.":[177],"experiments":[179],"that":[181],"proposed":[183],"successfully":[185],"objectives":[190],"is":[192],"effective":[193],"controllable":[195],"music-video":[196],"retrieval.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}