{"id":"https://openalex.org/W4414086011","doi":"https://doi.org/10.1109/icmew68306.2025.11152178","title":"Video-driven cross-modal controlled music generation","display_name":"Video-driven cross-modal controlled music generation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4414086011","doi":"https://doi.org/10.1109/icmew68306.2025.11152178"},"language":"en","primary_location":{"id":"doi:10.1109/icmew68306.2025.11152178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew68306.2025.11152178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","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":null,"display_name":"Jingge Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingge Zhao","raw_affiliation_strings":["ZhengZhou University,School of Electrical and Information Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZhengZhou University,School of Electrical and Information Engineering,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012356492","display_name":"Xiaobing Li","orcid":"https://orcid.org/0000-0003-0113-824X"},"institutions":[{"id":"https://openalex.org/I2799899675","display_name":"Central Conservatory of Music","ror":"https://ror.org/01pxc4g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799899675"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobing Li","raw_affiliation_strings":["Central Conservatory of Music,Department of AI Music and Music Information Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central Conservatory of Music,Department of AI Music and Music Information Technology,Beijing,China","institution_ids":["https://openalex.org/I2799899675"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618818","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-6628-3408"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weipeng Wang","raw_affiliation_strings":["ZhengZhou University,School of Electrical and Information Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZhengZhou University,School of Electrical and Information Engineering,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059055920","display_name":"Yan Gao","orcid":"https://orcid.org/0000-0002-2954-1922"},"institutions":[{"id":"https://openalex.org/I2799899675","display_name":"Central Conservatory of Music","ror":"https://ror.org/01pxc4g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799899675"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Gao","raw_affiliation_strings":["Central Conservatory of Music,Department of AI Music and Music Information Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central Conservatory of Music,Department of AI Music and Music Information Technology,Beijing,China","institution_ids":["https://openalex.org/I2799899675"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101482945","display_name":"Xiaoqing Wang","orcid":"https://orcid.org/0000-0002-2762-2497"},"institutions":[{"id":"https://openalex.org/I2799899675","display_name":"Central Conservatory of Music","ror":"https://ror.org/01pxc4g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799899675"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqing Wang","raw_affiliation_strings":["Central Conservatory of Music,Department of AI Music and Music Information Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central Conservatory of Music,Department of AI Music and Music Information Technology,Beijing,China","institution_ids":["https://openalex.org/I2799899675"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101112071","display_name":"Yun Tie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yun Tie","raw_affiliation_strings":["ZhengZhou University,School of Electrical and Information Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZhengZhou University,School of Electrical and Information Engineering,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991000294685364,"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":0.9925000071525574,"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/quality","display_name":"Quality (philosophy)","score":0.5392000079154968},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4602000117301941},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4203999936580658},{"id":"https://openalex.org/keywords/music-industry","display_name":"Music industry","score":0.36820000410079956},{"id":"https://openalex.org/keywords/popular-music","display_name":"Popular music","score":0.34850001335144043},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.34549999237060547}],"concepts":[{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.582099974155426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5699999928474426},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5392000079154968},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4602000117301941},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4203999936580658},{"id":"https://openalex.org/C186855751","wikidata":"https://www.wikidata.org/wiki/Q746359","display_name":"Music industry","level":3,"score":0.36820000410079956},{"id":"https://openalex.org/C114611597","wikidata":"https://www.wikidata.org/wiki/Q373342","display_name":"Popular music","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C73520026","wikidata":"https://www.wikidata.org/wiki/Q7229091","display_name":"Pop music automation","level":4,"score":0.32010000944137573},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C2992428333","wikidata":"https://www.wikidata.org/wiki/Q11461","display_name":"Sound production","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C2993931450","wikidata":"https://www.wikidata.org/wiki/Q639197","display_name":"Instrumental music","level":3,"score":0.2628999948501587},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmew68306.2025.11152178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew68306.2025.11152178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","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"},{"id":"https://openalex.org/F4320335869","display_name":"National Social Science Fund of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2129192849","https://openalex.org/W2772474126","https://openalex.org/W3111853169","https://openalex.org/W3207290297","https://openalex.org/W4225736884","https://openalex.org/W4308829742","https://openalex.org/W4312814772","https://openalex.org/W4318351475","https://openalex.org/W4390873340","https://openalex.org/W4391924849","https://openalex.org/W4392120655","https://openalex.org/W4392647990"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Music":[0],"plays":[1],"a":[2,85,104],"crucial":[3],"role":[4],"in":[5,131],"video":[6,28,71,109],"production,":[7],"not":[8,63],"only":[9],"improving":[10],"the":[11,15,20,24,31,68,79,97,114,125,129],"overall":[12],"quality":[13,98],"of":[14,27,99,116,123],"video,":[16],"but":[17],"also":[18,39],"enhancing":[19],"audience\u2019s":[21],"immersion.":[22],"With":[23],"rapid":[25],"growth":[26],"content":[29],"demand,":[30],"demand":[32],"for":[33],"cross":[34],"modal":[35],"music":[36,73,89,101,111,141],"generation":[37,90],"is":[38],"increasing.":[40],"However,":[41],"professional":[42],"composers":[43],"face":[44],"high":[45],"costs":[46],"and":[47,66,72,110,120],"complex":[48],"production":[49],"cycles,":[50],"making":[51],"it":[52],"difficult":[53],"to":[54,95,139],"meet":[55],"this":[56,82,132],"market":[57],"demand.":[58],"Furthermore,":[59],"current":[60],"research":[61],"has":[62],"effectively":[64],"established":[65],"aligned":[67],"relationship":[69,107],"between":[70,108],"as":[74],"two":[75],"modalities.":[76],"To":[77],"address":[78],"aforementioned":[80],"issues,":[81],"paper":[83,133],"proposes":[84],"Video-driven":[86],"cross-modal":[87],"controlled":[88],"(CPVC).":[91],"This":[92],"model":[93,130],"aims":[94],"improve":[96],"generated":[100],"by":[102],"establishing":[103],"multi-level":[105],"mapping":[106],"elements.":[112],"Through":[113],"analysis":[115],"basic":[117],"objective":[118],"evaluation":[119,122],"comprehensive":[121],"controllability,":[124],"experiments":[126],"show":[127],"that":[128,136],"generates":[134],"samples":[135],"are":[137],"closer":[138],"real":[140],"performances.":[142]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
