{"id":"https://openalex.org/W3179432212","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":"2021-11-16","ids":{"openalex":"https://openalex.org/W3179432212","doi":"https://doi.org/10.1109/tmm.2021.3128254","mag":"3179432212"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2021.3128254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3128254","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.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":"Jing Yi","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":"Yaochen Zhu","raw_affiliation_strings":["School of Remote Sensing and Information Engineering, Wuhan University, Hubei, China"],"raw_orcid":"https://orcid.org/0000-0001-6266-2788","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":"Jiayi Xie","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":"Zhenzhong Chen","raw_affiliation_strings":["School of Computer Science, Wuhan University, Hubei, China","Wuhan University"],"raw_orcid":"https://orcid.org/0000-0002-7882-1066","affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Hubei, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Wuhan University","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":{"value":2045,"currency":"USD","value_usd":2045},"apc_paid":null,"fwci":1.1257,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.76734166,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"25","issue":null,"first_page":"515","last_page":"528"},"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":0.9973000288009644,"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":0.993399977684021,"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":0.7673021554946899},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.549898624420166},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5359346270561218},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.506614089012146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44501766562461853},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4378681182861328},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.352761834859848},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.34737300872802734},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3451001048088074},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3331916928291321},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13771885633468628}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7673021554946899},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.549898624420166},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5359346270561218},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.506614089012146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44501766562461853},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4378681182861328},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.352761834859848},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.34737300872802734},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3451001048088074},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3331916928291321},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13771885633468628},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tmm.2021.3128254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3128254","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},{"id":"doi:10.48550/arxiv.2107.07268","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2107.07268","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"mag:3179432212","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.48550/arxiv.2107.07268","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2107.07268","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":97,"referenced_works":["https://openalex.org/W877909479","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1866281937","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/W2089468765","https://openalex.org/W2100235303","https://openalex.org/W2116777898","https://openalex.org/W2122279656","https://openalex.org/W2132551672","https://openalex.org/W2137028279","https://openalex.org/W2145094598","https://openalex.org/W2164290393","https://openalex.org/W2165857685","https://openalex.org/W2194775991","https://openalex.org/W2209982072","https://openalex.org/W2225156818","https://openalex.org/W2265989499","https://openalex.org/W2326180695","https://openalex.org/W2334831412","https://openalex.org/W2340600463","https://openalex.org/W2425121537","https://openalex.org/W2476034201","https://openalex.org/W2526050071","https://openalex.org/W2527573165","https://openalex.org/W2564325886","https://openalex.org/W2593116425","https://openalex.org/W2600087639","https://openalex.org/W2605350416","https://openalex.org/W2606473278","https://openalex.org/W2617585083","https://openalex.org/W2725606191","https://openalex.org/W2740276176","https://openalex.org/W2756946152","https://openalex.org/W2783457476","https://openalex.org/W2803054945","https://openalex.org/W2883308936","https://openalex.org/W2884436226","https://openalex.org/W2886087818","https://openalex.org/W2913351023","https://openalex.org/W2948958195","https://openalex.org/W2956335072","https://openalex.org/W2962814609","https://openalex.org/W2962964995","https://openalex.org/W2962970472","https://openalex.org/W2963085847","https://openalex.org/W2963198154","https://openalex.org/W2963341956","https://openalex.org/W2963389687","https://openalex.org/W2963524571","https://openalex.org/W2963650472","https://openalex.org/W2963916161","https://openalex.org/W2967638906","https://openalex.org/W2967957126","https://openalex.org/W2970873268","https://openalex.org/W2970971581","https://openalex.org/W2971187489","https://openalex.org/W2981473723","https://openalex.org/W2981951787","https://openalex.org/W2994818707","https://openalex.org/W2996478685","https://openalex.org/W3034306482","https://openalex.org/W3035212740","https://openalex.org/W3035454331","https://openalex.org/W3035485997","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/W3097679710","https://openalex.org/W3101380508","https://openalex.org/W3133431537","https://openalex.org/W3142813226","https://openalex.org/W3154026371","https://openalex.org/W3156939347","https://openalex.org/W3172253407","https://openalex.org/W3199736415","https://openalex.org/W4251194840","https://openalex.org/W4252028749","https://openalex.org/W4388317387","https://openalex.org/W6640963894","https://openalex.org/W6684090549","https://openalex.org/W6685777803","https://openalex.org/W6721087566","https://openalex.org/W6728047685","https://openalex.org/W6730357551","https://openalex.org/W6748455135","https://openalex.org/W6767441326","https://openalex.org/W6767551140","https://openalex.org/W6771024394"],"related_works":["https://openalex.org/W3213942508","https://openalex.org/W3198668032","https://openalex.org/W2908965201","https://openalex.org/W2968808972","https://openalex.org/W3197980617","https://openalex.org/W3205716523","https://openalex.org/W3179529441","https://openalex.org/W3081040707","https://openalex.org/W3047425522","https://openalex.org/W1968600390","https://openalex.org/W2926312400","https://openalex.org/W353528578","https://openalex.org/W3161635175","https://openalex.org/W1606236744","https://openalex.org/W3160632021","https://openalex.org/W2890234836","https://openalex.org/W3002493597","https://openalex.org/W2897439619","https://openalex.org/W2154748549","https://openalex.org/W1967535461"],"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":[13,26,126,139],"music":[14,27,127,140],"recommendation.":[15],"CMVAE":[16,167],"is":[17,55,63,98,173],"hierarchical":[19],"Bayesian":[20],"generative":[21],"model":[22,117],"that":[23,90,111],"matches":[24],"relevant":[25],"to":[28,85,143],"by":[31,57,65,168],"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":[44,60,66,71,80,91,103,152,157,160],"alignment":[45],"of":[46,50,79,132,159,166],"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":[112,172],"robust":[116],"generalization.":[118],"Furthermore,":[119],"establish":[121],"large-scale":[123],"recommendation":[128,171],"dataset,":[129],"TT-150k,":[130],"composed":[131],"extracted":[133],"features":[134],"from":[135,146],"approximately":[136],"3,000":[137],"different":[138,147],"clips":[141],"associated":[142],"150,000":[144],"micro-videos":[145],"users.":[148],"Extensive":[149],"experiments":[150],"on":[151],"established":[153],"TT-150k":[154],"dataset":[155],"demonstrate":[156],"effectiveness":[158],"proposed":[161],"method.":[162],"A":[163],"qualitative":[164],"assessment":[165],"visualizing":[169],"some":[170],"also":[174],"included.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}