{"id":"https://openalex.org/W4406860155","doi":"https://doi.org/10.1109/vcip63160.2024.10849886","title":"MVBind: Self-Supervised Music Recommendation for Videos via Embedding Space Binding","display_name":"MVBind: Self-Supervised Music Recommendation for Videos via Embedding Space Binding","publication_year":2024,"publication_date":"2024-12-08","ids":{"openalex":"https://openalex.org/W4406860155","doi":"https://doi.org/10.1109/vcip63160.2024.10849886"},"language":"en","primary_location":{"id":"doi:10.1109/vcip63160.2024.10849886","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip63160.2024.10849886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Visual Communications and Image Processing (VCIP)","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/A5059827282","display_name":"Jiajie Teng","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiajie Teng","raw_affiliation_strings":["Shanghai Jiao Tong University,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015291775","display_name":"Huiyu Duan","orcid":"https://orcid.org/0000-0002-6519-4067"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huiyu Duan","raw_affiliation_strings":["Shanghai Jiao Tong University,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034718093","display_name":"Yucheng Zhu","orcid":"https://orcid.org/0000-0002-3069-060X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yucheng Zhu","raw_affiliation_strings":["Shanghai Jiao Tong University,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019148813","display_name":"Sijing Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sijing Wu","raw_affiliation_strings":["Shanghai Jiao Tong University,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":null,"display_name":"Guangtao Zhai","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangtao Zhai","raw_affiliation_strings":["Shanghai Jiao Tong University,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5059827282"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.3544,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61344716,"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":0.9908000230789185,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9325000047683716,"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":0.6762458086013794},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.672291100025177},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.6087867021560669},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.42982620000839233},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3691129684448242},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.26994726061820984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6762458086013794},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.672291100025177},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.6087867021560669},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.42982620000839233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3691129684448242},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26994726061820984},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip63160.2024.10849886","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip63160.2024.10849886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":37,"referenced_works":["https://openalex.org/W254632926","https://openalex.org/W2194775991","https://openalex.org/W2962970472","https://openalex.org/W2963163009","https://openalex.org/W2995351650","https://openalex.org/W3033909547","https://openalex.org/W3035524453","https://openalex.org/W3091648716","https://openalex.org/W3138516171","https://openalex.org/W3157758108","https://openalex.org/W3180463990","https://openalex.org/W3196974791","https://openalex.org/W4285213119","https://openalex.org/W4308772371","https://openalex.org/W4312510569","https://openalex.org/W4312847199","https://openalex.org/W4313156423","https://openalex.org/W4322730980","https://openalex.org/W4384947975","https://openalex.org/W4386071707","https://openalex.org/W4388004017","https://openalex.org/W4391490252","https://openalex.org/W4402915487","https://openalex.org/W4403601500","https://openalex.org/W6636885848","https://openalex.org/W6680096826","https://openalex.org/W6705283200","https://openalex.org/W6762718338","https://openalex.org/W6768465061","https://openalex.org/W6769190642","https://openalex.org/W6780218876","https://openalex.org/W6784333009","https://openalex.org/W6791353385","https://openalex.org/W6796931752","https://openalex.org/W6798597329","https://openalex.org/W6850563681","https://openalex.org/W6854546182"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4390273403","https://openalex.org/W4386781444","https://openalex.org/W2150182025","https://openalex.org/W3092950680","https://openalex.org/W3197542405","https://openalex.org/W2056712470","https://openalex.org/W3125580266"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2],"witnessed":[3],"the":[4,23,30,33,38,48,94,102],"rapid":[5],"development":[6],"of":[7,32,41,56,87,96,104,125],"short":[8,24,42,62,111,128],"videos,":[9,25,112],"which":[10,26,122],"usually":[11],"contain":[12],"both":[13],"visual":[14],"and":[15,51,145],"audio":[16],"modalities.":[17],"Background":[18],"music":[19,40,58],"is":[20,44,53],"important":[21],"to":[22,100,139],"can":[27],"significantly":[28,135],"influence":[29],"emotions":[31],"viewers.":[34],"However,":[35],"at":[36],"present,":[37],"background":[39],"videos":[43],"generally":[45],"chosen":[46],"by":[47],"video":[49],"producer,":[50],"there":[52],"a":[54,81,105,115],"lack":[55,103],"automatic":[57],"recommendation":[59],"methods":[60],"for":[61,75,110],"videos.":[63,129],"This":[64],"paper":[65],"introduces":[66],"MVBind,":[67],"an":[68],"innovative":[69],"Music-Video":[70],"embedding":[71],"space":[72],"Binding":[73],"model":[74],"cross-modal":[76],"retrieval.":[77],"MVBind":[78,133],"operates":[79],"as":[80],"self-supervised":[82],"approach,":[83],"acquiring":[84],"inherent":[85],"knowledge":[86],"intermodal":[88],"relationships":[89],"directly":[90],"from":[91],"data,":[92],"without":[93],"need":[95],"manual":[97],"annotations.":[98],"Additionally,":[99],"compensate":[101],"corresponding":[106],"musical-visual":[107],"pair":[108],"dataset":[109],"we":[113],"construct":[114],"dataset,":[116,132],"SVM-10K":[117],"(Short":[118],"Video":[119],"with":[120],"Music-10K),":[121],"mainly":[123],"consists":[124],"meticulously":[126],"selected":[127],"On":[130],"this":[131],"manifests":[134],"improved":[136],"performance":[137],"compared":[138],"other":[140],"baseline":[141],"methods.":[142],"The":[143],"database":[144],"code":[146],"are":[147],"available":[148],"at:":[149],"https://github.com/IntMeGroup/MVBind.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2025-10-10T00:00:00"}
