{"id":"https://openalex.org/W4406266133","doi":"https://doi.org/10.1109/gcce62371.2024.10760865","title":"Zero-shot Controllable Music Generation from Videos Using Facial Expressions","display_name":"Zero-shot Controllable Music Generation from Videos Using Facial Expressions","publication_year":2024,"publication_date":"2024-10-29","ids":{"openalex":"https://openalex.org/W4406266133","doi":"https://doi.org/10.1109/gcce62371.2024.10760865"},"language":"en","primary_location":{"id":"doi:10.1109/gcce62371.2024.10760865","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce62371.2024.10760865","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 13th Global Conference on Consumer Electronics (GCCE)","raw_type":"proceedings-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/A5100399763","display_name":"Shilin Liu","orcid":"https://orcid.org/0000-0002-3704-3798"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shilin Liu","raw_affiliation_strings":["Hokkaido University,Graduate School of Information Science and Technology,Japan"],"affiliations":[{"raw_affiliation_string":"Hokkaido University,Graduate School of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015425921","display_name":"Kyohei Kamikawa","orcid":"https://orcid.org/0000-0002-7054-7920"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kyohei Kamikawa","raw_affiliation_strings":["Hokkaido University,Graduate School of Information Science and Technology,Japan"],"affiliations":[{"raw_affiliation_string":"Hokkaido University,Graduate School of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033215072","display_name":"Keisuke Maeda","orcid":"https://orcid.org/0000-0001-8039-3462"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Maeda","raw_affiliation_strings":["Hokkaido University,Data-Driven Interdisciplinary Research Emergence Department,Japan"],"affiliations":[{"raw_affiliation_string":"Hokkaido University,Data-Driven Interdisciplinary Research Emergence Department,Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009032240","display_name":"Takahiro Ogawa","orcid":"https://orcid.org/0000-0001-5332-8112"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Ogawa","raw_affiliation_strings":["Hokkaido University,Faculty of Information Science and Technology,Japan"],"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"last","author":{"id":null,"display_name":"Miki Haseyama","orcid":null},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Miki Haseyama","raw_affiliation_strings":["Hokkaido University,Faculty of Information Science and Technology,Japan"],"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100399763"],"corresponding_institution_ids":["https://openalex.org/I205349734"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2531305,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1169","last_page":"1170"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9819999933242798,"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":0.9819999933242798,"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":0.9763000011444092,"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/T10860","display_name":"Speech and Audio Processing","score":0.9519000053405762,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.7017591595649719},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6047728061676025},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5468279719352722},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4662705063819885},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4343380630016327},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36376363039016724},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35692065954208374},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.08660444617271423},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08348742127418518}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7017591595649719},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6047728061676025},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5468279719352722},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4662705063819885},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4343380630016327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36376363039016724},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35692065954208374},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.08660444617271423},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08348742127418518},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gcce62371.2024.10760865","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce62371.2024.10760865","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 13th Global Conference on Consumer Electronics (GCCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,7,43,62,89,100],"method":[4,27],"to":[5,36],"control":[6],"music":[8,19,50,58,68],"generation":[9,59,63,69],"process":[10,60],"from":[11],"videos":[12],"using":[13],"users\u2019":[14,29],"facial":[15,30,47,71],"expressions,":[16,31],"aligning":[17],"the":[18,57,77,82,108],"with":[20,70],"their":[21,34],"emotions.":[22],"Unlike":[23],"previous":[24],"works,":[25],"this":[26],"considers":[28],"which":[32],"reflect":[33],"emotions,":[35],"create":[37],"more":[38],"resonant":[39],"music.":[40],"We":[41],"establish":[42],"functional":[44],"relationship":[45],"between":[46],"expressions":[48,72],"and":[49,52,97],"attributes":[51],"integrate":[53],"these":[54],"functions":[55],"into":[56],"in":[61],"phase.":[64],"Then":[65],"zero-shot":[66],"controllable":[67],"becomes":[73],"feasible.":[74],"To":[75],"address":[76],"challenge":[78],"of":[79,110],"objectively":[80],"verifying":[81],"generated":[83],"music\u2019s":[84],"emotional":[85],"correspondence,":[86],"we":[87],"introduce":[88],"novel":[90],"evaluation":[91],"metric":[92],"that":[93],"compares":[94],"video,":[95],"music,":[96],"emotions":[98],"within":[99],"common":[101],"latent":[102],"space.":[103],"The":[104],"experimental":[105],"results":[106],"show":[107],"effectiveness":[109],"our":[111],"method.":[112]},"counts_by_year":[],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2025-10-10T00:00:00"}
