{"id":"https://openalex.org/W3213942508","doi":"https://doi.org/10.1109/tmm.2021.3128254","title":"Cross-modal Variational Auto-encoder for Content-based Micro-video Background Music Recommendation","display_name":"Cross-modal Variational Auto-encoder for Content-based Micro-video Background Music Recommendation","publication_year":2021,"publication_date":"2021-07-15","ids":{"openalex":"https://openalex.org/W3213942508","doi":"https://doi.org/10.1109/tmm.2021.3128254","mag":"3213942508"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2107.07268","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.07268","pdf_url":"https://arxiv.org/pdf/2107.07268","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"},"type":"preprint","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2107.07268","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101601049","display_name":"Jing Yi","orcid":"https://orcid.org/0000-0001-7776-1500"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi, Jing","raw_affiliation_strings":["School of Computer Science, Wuhan University, Hubei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Hubei, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102911934","display_name":"Yaochen Zhu","orcid":"https://orcid.org/0000-0001-6266-2788"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu, Yaochen","raw_affiliation_strings":["School of Remote Sensing and Information Engineering, Wuhan University, Hubei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Remote Sensing and Information Engineering, Wuhan University, Hubei, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100928892","display_name":"Jiayi Xie","orcid":"https://orcid.org/0000-0002-8712-326X"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie, Jiayi","raw_affiliation_strings":["School of Remote Sensing and Information Engineering, Wuhan University, Hubei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Remote Sensing and Information Engineering, Wuhan University, Hubei, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006748765","display_name":"Zhenzhong Chen","orcid":"https://orcid.org/0000-0002-7882-1066"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Zhenzhong","raw_affiliation_strings":["School of Remote Sensing and Information Engineering, Wuhan University, Hubei, China","School of Computer Science, Wuhan University, Hubei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Remote Sensing and Information Engineering, Wuhan University, Hubei, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Computer Science, Wuhan University, Hubei, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9965999722480774,"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":0.9940000176429749,"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":0.8369293808937073},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5072050094604492},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.47398701310157776},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.470263808965683},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4566563367843628},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3684627413749695},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3296595513820648},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.28585395216941833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8369293808937073},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5072050094604492},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.47398701310157776},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.470263808965683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4566563367843628},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3684627413749695},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3296595513820648},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.28585395216941833},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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":"pmh:oai:arXiv.org:2107.07268","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.07268","pdf_url":"https://arxiv.org/pdf/2107.07268","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:2107.07268","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.07268","pdf_url":"https://arxiv.org/pdf/2107.07268","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":[{"id":"https://openalex.org/G879442631","display_name":null,"funder_award_id":"62036005","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":81,"referenced_works":["https://openalex.org/W877909479","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1959608418","https://openalex.org/W1987800703","https://openalex.org/W1997249373","https://openalex.org/W2006556239","https://openalex.org/W2007972815","https://openalex.org/W2085662862","https://openalex.org/W2100235303","https://openalex.org/W2116777898","https://openalex.org/W2122279656","https://openalex.org/W2132551672","https://openalex.org/W2137028279","https://openalex.org/W2164290393","https://openalex.org/W2165857685","https://openalex.org/W2181347294","https://openalex.org/W2194775991","https://openalex.org/W2209982072","https://openalex.org/W2225156818","https://openalex.org/W2265989499","https://openalex.org/W2334831412","https://openalex.org/W2340600463","https://openalex.org/W2425121537","https://openalex.org/W2476034201","https://openalex.org/W2524365899","https://openalex.org/W2526050071","https://openalex.org/W2527573165","https://openalex.org/W2556013083","https://openalex.org/W2564325886","https://openalex.org/W2568262903","https://openalex.org/W2593116425","https://openalex.org/W2600087639","https://openalex.org/W2605350416","https://openalex.org/W2606473278","https://openalex.org/W2725606191","https://openalex.org/W2740276176","https://openalex.org/W2756946152","https://openalex.org/W2786541991","https://openalex.org/W2803054945","https://openalex.org/W2883308936","https://openalex.org/W2884436226","https://openalex.org/W2886087818","https://openalex.org/W2896457183","https://openalex.org/W2913351023","https://openalex.org/W2956335072","https://openalex.org/W2962964995","https://openalex.org/W2962968152","https://openalex.org/W2962970472","https://openalex.org/W2963085847","https://openalex.org/W2963524571","https://openalex.org/W2964015378","https://openalex.org/W2967638906","https://openalex.org/W2967957126","https://openalex.org/W2981473723","https://openalex.org/W2981951787","https://openalex.org/W2982298563","https://openalex.org/W2987472543","https://openalex.org/W2990387939","https://openalex.org/W2996478685","https://openalex.org/W2997574889","https://openalex.org/W3034306482","https://openalex.org/W3035212740","https://openalex.org/W3035552787","https://openalex.org/W3038033387","https://openalex.org/W3081404490","https://openalex.org/W3081484346","https://openalex.org/W3093061104","https://openalex.org/W3093199520","https://openalex.org/W3101380508","https://openalex.org/W3103717910","https://openalex.org/W3133431537","https://openalex.org/W3142813226","https://openalex.org/W3154026371","https://openalex.org/W3156939347","https://openalex.org/W3170713142","https://openalex.org/W3172253407","https://openalex.org/W3199736415","https://openalex.org/W4251194840","https://openalex.org/W4252028749","https://openalex.org/W4388317387"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W2379948177","https://openalex.org/W2334580170"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,120],"propose":[4],"a":[5,18,29,38,51,94,114,122],"cross-modal":[6],"variational":[7],"auto-encoder":[8],"(CMVAE)":[9],"for":[10],"content-based":[11,124],"micro-video":[12,30,81,104,125],"background":[13,26,126,136],"music":[14,27,127,137],"recommendation.":[15],"CMVAE":[16,164],"is":[17,55,63,98,170],"hierarchical":[19],"Bayesian":[20],"generative":[21],"model":[22,117],"that":[23,90,111],"matches":[24],"relevant":[25],"to":[28,85,140],"by":[31,57,65,165],"projecting":[32],"these":[33],"two":[34,47],"multimodal":[35,61],"inputs":[36],"into":[37],"shared":[39],"low-dimensional":[40],"latent":[41,105],"space,":[42],"where":[43,70],"the":[44,60,66,71,80,91,103,149,154,157],"alignment":[45],"of":[46,50,79,132,156,163],"corresponding":[48],"embeddings":[49],"matched":[52],"video-music":[53],"pair":[54],"achieved":[56],"cross-generation.":[58],"Moreover,":[59],"information":[62,73,110],"fused":[64],"product-of-experts":[67],"(PoE)":[68],"principle,":[69],"semantic":[72],"in":[74,113],"visual":[75],"and":[76],"textual":[77],"modalities":[78],"are":[82],"weighted":[83],"according":[84],"their":[86],"variance":[87],"estimations":[88],"such":[89],"modality":[92],"with":[93],"lower":[95],"noise":[96],"level":[97],"given":[99],"more":[100,115],"weights.":[101],"Therefore,":[102],"variables":[106],"contain":[107],"less":[108],"irrelevant":[109],"results":[112,169],"robust":[116],"generalization.":[118],"Furthermore,":[119],"establish":[121],"large-scale":[123],"recommendation":[128,168],"dataset,":[129],"TT-150k,":[130],"composed":[131],"approximately":[133],"3,000":[134],"different":[135,144],"clips":[138],"associated":[139],"150,000":[141],"micro-videos":[142],"from":[143],"users.":[145],"Extensive":[146],"experiments":[147],"on":[148],"established":[150],"TT-150k":[151],"dataset":[152],"demonstrate":[153],"effectiveness":[155],"proposed":[158],"method.":[159],"A":[160],"qualitative":[161],"assessment":[162],"visualizing":[166],"some":[167],"also":[171],"included.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2021-11-22T00:00:00"}