{"id":"https://openalex.org/W4403021930","doi":"https://doi.org/10.1109/tcss.2024.3451515","title":"Video Echoed in Harmony: Learning and Sampling Video-Integrated Chord Progression Sequences for Controllable Video Background Music Generation","display_name":"Video Echoed in Harmony: Learning and Sampling Video-Integrated Chord Progression Sequences for Controllable Video Background Music Generation","publication_year":2024,"publication_date":"2024-10-01","ids":{"openalex":"https://openalex.org/W4403021930","doi":"https://doi.org/10.1109/tcss.2024.3451515"},"language":"en","primary_location":{"id":"doi:10.1109/tcss.2024.3451515","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcss.2024.3451515","pdf_url":null,"source":{"id":"https://openalex.org/S2490693980","display_name":"IEEE Transactions on Computational Social Systems","issn_l":"2329-924X","issn":["2329-924X","2373-7476"],"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 Computational Social Systems","raw_type":"journal-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/A5103092617","display_name":"Xinyi Tong","orcid":"https://orcid.org/0000-0002-3269-3628"},"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":"Xinyi Tong","raw_affiliation_strings":["Department of AI Music and Music Information Technology, Central Conservatory of Music, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3269-3628","affiliations":[{"raw_affiliation_string":"Department of AI Music and Music Information Technology, Central Conservatory of Music, Beijing, China","institution_ids":["https://openalex.org/I2799899675"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062546245","display_name":"Sitong Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4392738278","display_name":"Beijing Institute for General Artificial Intelligence","ror":"https://ror.org/02kw1ws04","country_code":"CN","type":"government","lineage":["https://openalex.org/I4392738278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sitong Chen","raw_affiliation_strings":["Beijing Institute for General Artificial Intelligence, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-8055-9237","affiliations":[{"raw_affiliation_string":"Beijing Institute for General Artificial Intelligence, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4392738278"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113411903","display_name":"Peiyang Yu","orcid":null},"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":"Peiyang Yu","raw_affiliation_strings":["Department of AI Music and Music Information Technology, Central Conservatory of Music, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-5308-771X","affiliations":[{"raw_affiliation_string":"Department of AI Music and Music Information Technology, Central Conservatory of Music, Beijing, China","institution_ids":["https://openalex.org/I2799899675"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054508826","display_name":"Nian Liu","orcid":"https://orcid.org/0009-0001-8887-0478"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4392738278","display_name":"Beijing Institute for General Artificial Intelligence","ror":"https://ror.org/02kw1ws04","country_code":"CN","type":"government","lineage":["https://openalex.org/I4392738278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nian Liu","raw_affiliation_strings":["Beijing Institute for General Artificial Intelligence, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-8887-0478","affiliations":[{"raw_affiliation_string":"Beijing Institute for General Artificial Intelligence, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4392738278"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044030351","display_name":"Hui Qv","orcid":"https://orcid.org/0000-0003-1645-777X"},"institutions":[{"id":"https://openalex.org/I15089104","display_name":"China Aerospace Science and Industry Corporation (China)","ror":"https://ror.org/0523vvf33","country_code":"CN","type":"company","lineage":["https://openalex.org/I15089104"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Qv","raw_affiliation_strings":["Intelligent Science and Technology Academy of CASIC, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1645-777X","affiliations":[{"raw_affiliation_string":"Intelligent Science and Technology Academy of CASIC, Beijing, China","institution_ids":["https://openalex.org/I15089104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101910089","display_name":"Tao Ma","orcid":"https://orcid.org/0000-0003-3475-7987"},"institutions":[{"id":"https://openalex.org/I2802505932","display_name":"China Aerodynamics Research and Development Center","ror":"https://ror.org/00jma8s40","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802505932"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Ma","raw_affiliation_strings":["China Academy of Aerospace Aerodynamics, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3475-7987","affiliations":[{"raw_affiliation_string":"China Academy of Aerospace Aerodynamics, Beijing, China","institution_ids":["https://openalex.org/I2802505932"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073856221","display_name":"Bo Zheng","orcid":"https://orcid.org/0000-0002-4037-6315"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Zheng","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4037-6315","affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049175891","display_name":"Feng Yu","orcid":"https://orcid.org/0009-0007-0607-7315"},"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":"Feng Yu","raw_affiliation_strings":["Department of AI Music and Music Information Technology, Central Conservatory of Music, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-0607-7315","affiliations":[{"raw_affiliation_string":"Department of AI Music and Music Information Technology, Central Conservatory of Music, Beijing, China","institution_ids":["https://openalex.org/I2799899675"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034228010","display_name":"Song\u2010Chun Zhu","orcid":"https://orcid.org/0000-0002-1925-5973"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4392738278","display_name":"Beijing Institute for General Artificial Intelligence","ror":"https://ror.org/02kw1ws04","country_code":"CN","type":"government","lineage":["https://openalex.org/I4392738278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song-Chun Zhu","raw_affiliation_strings":["Beijing Institute for General Artificial Intelligence, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute for General Artificial Intelligence, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4392738278"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2044,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.48704238,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"12","issue":"2","first_page":"905","last_page":"917"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9991999864578247,"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/T11309","display_name":"Music and Audio Processing","score":0.9925000071525574,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.944599986076355,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/chord","display_name":"Chord (peer-to-peer)","score":0.6498854756355286},{"id":"https://openalex.org/keywords/harmony","display_name":"Harmony (color)","score":0.6303609609603882},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6150108575820923},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.45311295986175537},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43375518918037415},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39329397678375244},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37472301721572876},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1367141306400299},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.12531721591949463},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.11401504278182983}],"concepts":[{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.6498854756355286},{"id":"https://openalex.org/C2776453491","wikidata":"https://www.wikidata.org/wiki/Q5659234","display_name":"Harmony (color)","level":2,"score":0.6303609609603882},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6150108575820923},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.45311295986175537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43375518918037415},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39329397678375244},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37472301721572876},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1367141306400299},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.12531721591949463},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.11401504278182983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcss.2024.3451515","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcss.2024.3451515","pdf_url":null,"source":{"id":"https://openalex.org/S2490693980","display_name":"IEEE Transactions on Computational Social Systems","issn_l":"2329-924X","issn":["2329-924X","2373-7476"],"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 Computational Social Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4320266551","display_name":null,"funder_award_id":"21ZD19","funder_id":"https://openalex.org/F4320327785","funder_display_name":"Major Program of National Fund of Philosophy and Social Science of China"}],"funders":[{"id":"https://openalex.org/F4320327785","display_name":"Major Program of National Fund of Philosophy and Social Science of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W306648316","https://openalex.org/W2043181832","https://openalex.org/W2074308058","https://openalex.org/W2116777898","https://openalex.org/W2126174118","https://openalex.org/W2149628368","https://openalex.org/W2185897478","https://openalex.org/W2776011565","https://openalex.org/W2908965201","https://openalex.org/W2962970472","https://openalex.org/W2972478942","https://openalex.org/W3104790520","https://openalex.org/W3108047681","https://openalex.org/W3108240585","https://openalex.org/W3198668032","https://openalex.org/W3207290297","https://openalex.org/W3213942508","https://openalex.org/W4220729694","https://openalex.org/W4237301464","https://openalex.org/W4280599323","https://openalex.org/W4309617705","https://openalex.org/W4312097518","https://openalex.org/W4312814772","https://openalex.org/W4362514612","https://openalex.org/W4362670469","https://openalex.org/W4372260310","https://openalex.org/W4386076222","https://openalex.org/W4390872366","https://openalex.org/W4390873340","https://openalex.org/W4393148499","https://openalex.org/W4399959430","https://openalex.org/W4401023668","https://openalex.org/W4403759910","https://openalex.org/W6733339138","https://openalex.org/W6746363961","https://openalex.org/W6749351710","https://openalex.org/W6763362620","https://openalex.org/W6768465061","https://openalex.org/W6769627184","https://openalex.org/W6771024394","https://openalex.org/W6779254424","https://openalex.org/W6780316881","https://openalex.org/W6780713994","https://openalex.org/W6782602824","https://openalex.org/W6787185846","https://openalex.org/W6789449647","https://openalex.org/W6801284891","https://openalex.org/W6838582276","https://openalex.org/W6843584345","https://openalex.org/W6845479124","https://openalex.org/W6846594926","https://openalex.org/W6846726380","https://openalex.org/W6846867676","https://openalex.org/W6847363464","https://openalex.org/W6849105126","https://openalex.org/W6849109464","https://openalex.org/W6849416043","https://openalex.org/W6849635556","https://openalex.org/W6851334955","https://openalex.org/W6852776751","https://openalex.org/W6853096648","https://openalex.org/W6856602346","https://openalex.org/W6858882736","https://openalex.org/W6858930701","https://openalex.org/W6859169327","https://openalex.org/W6860951137","https://openalex.org/W6861148439","https://openalex.org/W6862527196"],"related_works":["https://openalex.org/W229552792","https://openalex.org/W4321448422","https://openalex.org/W2351864507","https://openalex.org/W3215212221","https://openalex.org/W3159818711","https://openalex.org/W2382969832","https://openalex.org/W2070360846","https://openalex.org/W2042398445","https://openalex.org/W2348535019","https://openalex.org/W2060448190"],"abstract_inverted_index":{"Automatically":[0],"generating":[1],"video":[2,14,62],"background":[3],"music":[4,40,55,90,105,161,165,180],"mitigates":[5],"the":[6,20,23,58,131,159,171,175,183],"inefficiency":[7],"and":[8,35,71,98,118,144],"time-consuming":[9],"drawbacks":[10],"of":[11,22,25,31,39,133],"current":[12],"manual":[13],"editing.":[15],"Two":[16],"key":[17],"challenges":[18],"hinder":[19],"expansion":[21],"inception":[24],"video-to-music":[26],"tasks.":[27],"1)":[28],"Limited":[29],"availability":[30],"high-quality":[32],"video\u2013music":[33,135],"datasets":[34],"annotations.":[36],"2)":[37],"Absence":[38],"generation":[41,162],"methods":[42],"that":[43,85,170],"consider":[44],"actual":[45],"musicality,":[46],"which":[47],"are":[48,86],"controlled":[49],"by":[50,82],"interpretable":[51,156],"factors":[52,157],"based":[53,163],"on":[54,164],"theory.":[56,166],"In":[57],"article,":[59],"we":[60],"propose":[61],"echoed":[63],"in":[64,103,121],"harmony":[65,149],"(VEH),":[66],"a":[67,178],"method":[68,173],"for":[69,158,182],"learning":[70,143],"sampling":[72,145],"video-integrated":[73],"chord":[74,83,101,113,141],"progression":[75,142],"sequences.":[76],"Our":[77],"approach":[78],"adopts":[79],"harmony,":[80],"represented":[81],"progressions":[84,114],"aligned":[87],"with":[88],"various":[89],"formats":[91],"[musical":[92],"instrument":[93],"digital":[94],"interface":[95],"(MIDI),":[96],"audio,":[97],"score],":[99],"imitating":[100],"precedence":[102],"human":[104],"composition.":[106],"Visual-language":[107],"models":[108],"link":[109],"visual":[110],"features":[111,128],"to":[112,151],"through":[115],"genre":[116],"labels":[117],"descriptive":[119],"words":[120],"generated":[122],"textualized":[123],"videos.":[124],"The":[125],"two":[126],"aforementioned":[127],"collectively":[129],"obviate":[130],"necessity":[132],"extensive":[134],"paired":[136],"data.":[137],"Besides,":[138],"an":[139],"energy-based":[140],"algorithm":[146],"quantifies":[147],"abstract":[148],"impressions":[150],"statistical":[152],"features,":[153],"serving":[154],"as":[155],"controllable":[160],"Experimental":[167],"results":[168],"demonstrate":[169],"proposed":[172],"outperforms":[174],"state-of-the-art,":[176],"producing":[177],"superior":[179],"alignment":[181],"given":[184],"video.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
