{"id":"https://openalex.org/W3153980448","doi":"https://doi.org/10.1145/3404835.3462993","title":"Deep Music Retrieval for Fine-Grained Videos by Exploiting Cross-Modal-Encoded Voice-Overs","display_name":"Deep Music Retrieval for Fine-Grained Videos by Exploiting Cross-Modal-Encoded Voice-Overs","publication_year":2021,"publication_date":"2021-07-11","ids":{"openalex":"https://openalex.org/W3153980448","doi":"https://doi.org/10.1145/3404835.3462993","mag":"3153980448"},"language":"en","primary_location":{"id":"doi:10.1145/3404835.3462993","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3462993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.10557","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078082551","display_name":"Tingtian Li","orcid":"https://orcid.org/0000-0001-9124-2600"},"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":true,"raw_author_name":"Tingtian Li","raw_affiliation_strings":["Tencent, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067395825","display_name":"Zixun Sun","orcid":null},"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":"Zixun Sun","raw_affiliation_strings":["Tencent, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101534930","display_name":"Haoruo Zhang","orcid":"https://orcid.org/0000-0002-4508-096X"},"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":"Haoruo Zhang","raw_affiliation_strings":["Tencent, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100781249","display_name":"Jin Li","orcid":"https://orcid.org/0000-0002-0260-3169"},"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":"Jin Li","raw_affiliation_strings":["Tencent, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024398284","display_name":"Ziming Wu","orcid":"https://orcid.org/0000-0003-3348-7727"},"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":"Ziming Wu","raw_affiliation_strings":["Tencent, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064016787","display_name":"Hui Zhan","orcid":"https://orcid.org/0009-0005-2183-8675"},"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":"Hui Zhan","raw_affiliation_strings":["Tencent, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110643048","display_name":"Yipeng Yu","orcid":"https://orcid.org/0000-0002-4212-0153"},"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":"Yipeng Yu","raw_affiliation_strings":["Tencent, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077320973","display_name":"Hengcan Shi","orcid":"https://orcid.org/0000-0002-1340-0009"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengcan Shi","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5078082551"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":1.0773,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.76243205,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1880","last_page":"1884"},"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":0.9926999807357788,"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":0.9850999712944031,"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":0.8762463331222534},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6692155599594116},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6379890441894531},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6148830652236938},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.518277108669281},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5177251696586609},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.4793999195098877},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4225490689277649},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3975820541381836},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3952939808368683},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.19239559769630432}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8762463331222534},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6692155599594116},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6379890441894531},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6148830652236938},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.518277108669281},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5177251696586609},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.4793999195098877},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4225490689277649},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3975820541381836},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3952939808368683},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19239559769630432},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3404835.3462993","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3462993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.10557","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.10557","pdf_url":"https://arxiv.org/pdf/2104.10557","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:2104.10557","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.10557","pdf_url":"https://arxiv.org/pdf/2104.10557","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W28802910","https://openalex.org/W306648316","https://openalex.org/W1535753778","https://openalex.org/W1593534454","https://openalex.org/W1964940342","https://openalex.org/W2049633694","https://openalex.org/W2110505738","https://openalex.org/W2331128040","https://openalex.org/W2340600463","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2600087639","https://openalex.org/W2604292070","https://openalex.org/W2914092515","https://openalex.org/W2954312077","https://openalex.org/W2954672622","https://openalex.org/W2962970472","https://openalex.org/W2963403868","https://openalex.org/W2963470893","https://openalex.org/W2964593454","https://openalex.org/W2967957126","https://openalex.org/W2990387939","https://openalex.org/W2990503944","https://openalex.org/W3035309251","https://openalex.org/W3037149862","https://openalex.org/W3094520012","https://openalex.org/W4234552385","https://openalex.org/W4236965008","https://openalex.org/W4301409532","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"Recently,":[0],"the":[1,4,17,34,53,77,81,88,91,99,107,116,119,130,133],"witness":[2],"of":[3,8,93,132],"rapidly":[5],"growing":[6],"popularity":[7],"short":[9,58,70],"videos":[10,42,59],"on":[11,33],"different":[12,94,104],"Internet":[13],"platforms":[14],"has":[15],"intensified":[16],"need":[18],"for":[19,68],"a":[20,62,111,124],"background":[21],"music":[22],"(BGM)":[23],"retrieval":[24,29,143],"system.":[25],"However,":[26],"existing":[27,140],"video-music":[28],"methods":[30,169],"only":[31],"based":[32],"visual":[35],"modality":[36],"cannot":[37],"show":[38,158],"promising":[39],"performance":[40,164],"regarding":[41],"with":[43,170],"fine-grained":[44,69],"virtual":[45],"contents.":[46],"In":[47,72],"this":[48],"paper,":[49],"we":[50,75,101,122,145],"also":[51],"investigate":[52],"widely":[54],"added":[55],"voice-overs":[56],"in":[57],"and":[60,80,90,118,147,154,165],"propose":[61],"novel":[63],"framework":[64],"to":[65,86,106,128],"retrieve":[66],"BGM":[67,120],"videos.":[71],"our":[73,160],"framework,":[74],"use":[76],"self-attention":[78],"(SA)":[79],"cross-modal":[82],"attention":[83],"(CMA)":[84],"modules":[85],"explore":[87],"intra-":[89],"inter-relationships":[92],"modalities":[95],"respectively.":[96],"For":[97,114],"balancing":[98],"modalities,":[100],"dynamically":[102],"assign":[103],"weights":[105],"modal":[108,134],"features":[109],"via":[110],"fusion":[112],"gate.":[113],"paring":[115],"query":[117],"embeddings,":[121],"introduce":[123],"triplet":[125],"pseudo-label":[126],"loss":[127],"constrain":[129],"semantics":[131],"embeddings.":[135],"As":[136],"there":[137],"are":[138],"no":[139],"virtual-content":[141,150],"video-BGM":[142],"datasets,":[144],"build":[146],"release":[148],"two":[149],"video":[151],"datasets":[152],"HoK400":[153],"CFM400.":[155],"Experimental":[156],"results":[157],"that":[159],"method":[161],"achieves":[162],"superior":[163],"outperforms":[166],"other":[167],"state-of-the-art":[168],"large":[171],"margins.":[172]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2021-04-26T00:00:00"}
