{"id":"https://openalex.org/W4392904709","doi":"https://doi.org/10.1109/icassp48485.2024.10446029","title":"Unified Pretraining Target Based Video-Music Retrieval with Music Rhythm and Video Optical Flow Information","display_name":"Unified Pretraining Target Based Video-Music Retrieval with Music Rhythm and Video Optical Flow Information","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904709","doi":"https://doi.org/10.1109/icassp48485.2024.10446029"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5109639654","display_name":"Tianjun Mao","orcid":null},"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":"Tianjun Mao","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066070154","display_name":"Shansong Liu","orcid":"https://orcid.org/0000-0001-6202-5615"},"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":"Shansong Liu","raw_affiliation_strings":["ARC Lab,Tencent PCG 3","Tencent PCG 3, ARC Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ARC Lab,Tencent PCG 3","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent PCG 3, ARC Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103284748","display_name":"Yunxuan Zhang","orcid":"https://orcid.org/0000-0002-2609-344X"},"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":"Yunxuan Zhang","raw_affiliation_strings":["Fundamental Technology Center,Tencent PCG","Tencent PCG, Fundamental Technology Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fundamental Technology Center,Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent PCG, Fundamental Technology Center","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675450","display_name":"Dian Li","orcid":"https://orcid.org/0000-0002-7183-0090"},"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":"Dian Li","raw_affiliation_strings":["Fundamental Technology Center,Tencent PCG","Tencent PCG, Fundamental Technology Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fundamental Technology Center,Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent PCG, Fundamental Technology Center","institution_ids":["https://openalex.org/I2250653659"]}]},{"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":["ARC Lab,Tencent PCG 3","Tencent PCG 3, ARC Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ARC Lab,Tencent PCG 3","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent PCG 3, ARC Lab","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7890","last_page":"7894"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9890000224113464,"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":0.9855999946594238,"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":0.799206018447876},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5438022017478943},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.49247798323631287},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.490444153547287},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4767250120639801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46300676465034485},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.45230865478515625},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4520712196826935},{"id":"https://openalex.org/keywords/crossmodal","display_name":"Crossmodal","score":0.4322414994239807},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.430669903755188},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35358625650405884},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3328527510166168},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.292198121547699},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.17020541429519653},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13843071460723877},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11592856049537659}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.799206018447876},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5438022017478943},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.49247798323631287},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.490444153547287},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4767250120639801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46300676465034485},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.45230865478515625},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4520712196826935},{"id":"https://openalex.org/C60115397","wikidata":"https://www.wikidata.org/wiki/Q5188732","display_name":"Crossmodal","level":4,"score":0.4322414994239807},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.430669903755188},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35358625650405884},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3328527510166168},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.292198121547699},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.17020541429519653},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13843071460723877},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11592856049537659},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W306648316","https://openalex.org/W1813265826","https://openalex.org/W1985697096","https://openalex.org/W2144211451","https://openalex.org/W2191779130","https://openalex.org/W2340600463","https://openalex.org/W2524365899","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W2884436226","https://openalex.org/W2939574508","https://openalex.org/W2962970472","https://openalex.org/W2970641574","https://openalex.org/W3015470225","https://openalex.org/W3097777922","https://openalex.org/W3109908659","https://openalex.org/W3153980448","https://openalex.org/W3198668032","https://openalex.org/W3207290297","https://openalex.org/W3213942508","https://openalex.org/W4212774754","https://openalex.org/W4213276648","https://openalex.org/W4286836754","https://openalex.org/W4312763854","https://openalex.org/W4385245566","https://openalex.org/W4388317387","https://openalex.org/W6713345880","https://openalex.org/W6728047685","https://openalex.org/W6766978945","https://openalex.org/W6768465061","https://openalex.org/W6771024394","https://openalex.org/W6798693674"],"related_works":["https://openalex.org/W4240440807","https://openalex.org/W953566696","https://openalex.org/W2010220987","https://openalex.org/W2010927954","https://openalex.org/W2085535992","https://openalex.org/W4386123105","https://openalex.org/W3117345873","https://openalex.org/W2933405975","https://openalex.org/W2053951134","https://openalex.org/W2067981595"],"abstract_inverted_index":{"Background":[0],"music":[1,77,115],"(BGM)":[2],"can":[3,127],"enhance":[4],"the":[5,21,60,70,110,132],"video\u2019s":[6],"emotion.":[7],"However,":[8],"selecting":[9],"an":[10],"appropriate":[11],"BGM":[12],"often":[13],"requires":[14],"domain":[15],"knowledge.":[16],"This":[17],"has":[18],"led":[19],"to":[20,40,64,91,99],"development":[22],"of":[23],"video-music":[24],"retrieval":[25],"techniques.":[26],"Most":[27],"existing":[28],"approaches":[29],"utilize":[30],"pretrained":[31],"video/music":[32,56,93],"feature":[33],"extractors":[34],"trained":[35],"with":[36,113],"different":[37,52],"target":[38,53,89],"sets":[39,54],"obtain":[41],"average":[42],"video/music-level":[43],"embeddings.":[44],"The":[45,66,103],"drawbacks":[46],"are":[47],"two-fold.":[48],"One":[49],"is":[50,68,78,107],"that":[51,69,123],"for":[55],"pretraining":[57,94],"may":[58],"cause":[59],"generated":[61],"embeddings":[62,98],"difficult":[63],"match.":[65],"second":[67],"underlying":[71],"temporal":[72,101],"correlation":[73],"between":[74],"video":[75],"and":[76,95,117],"ignored.":[79],"In":[80],"this":[81],"paper,":[82],"our":[83,124],"proposed":[84,125],"approach":[85],"leverages":[86],"a":[87,136],"unified":[88],"set":[90],"perform":[92],"produces":[96],"clip-level":[97,111],"preserve":[100],"information.":[102,120],"downstream":[104],"crossmodal":[105],"matching":[106],"based":[108],"on":[109],"features":[112],"embedded":[114],"rhythm":[116],"optical":[118],"flow":[119],"Experiments":[121],"demonstrate":[122],"method":[126],"achieve":[128],"superior":[129],"performance":[130],"over":[131],"state-of-the-art":[133],"methods":[134],"by":[135],"significant":[137],"margin.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}