{"id":"https://openalex.org/W4399455331","doi":"https://doi.org/10.48550/arxiv.2406.04321","title":"VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling","display_name":"VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling","publication_year":2024,"publication_date":"2024-06-06","ids":{"openalex":"https://openalex.org/W4399455331","doi":"https://doi.org/10.48550/arxiv.2406.04321"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2406.04321","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.04321","pdf_url":"https://arxiv.org/pdf/2406.04321","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.04321","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113395535","display_name":"Zeyue Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tian, Zeyue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100603529","display_name":"Zhaoyang Liu","orcid":"https://orcid.org/0009-0007-3892-7118"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zhaoyang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067150934","display_name":"Ruibin Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Ruibin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102684542","display_name":"Jiahao Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Jiahao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061082180","display_name":"Qifeng Liu","orcid":"https://orcid.org/0009-0003-1526-8173"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Qifeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101274342","display_name":"Xu Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Xu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100719529","display_name":"Qifeng Chen","orcid":"https://orcid.org/0000-0003-2199-3948"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Qifeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100652844","display_name":"Wei Xue","orcid":"https://orcid.org/0000-0002-4942-7748"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue, Wei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5051748619","display_name":"Yike Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Yike","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5113395535"],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9908000230789185,"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":0.9908000230789185,"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":0.9872999787330627,"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/T12720","display_name":"Multimedia Communication and Technology","score":0.9803000092506409,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.8328183889389038},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.7945460081100464},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5469423532485962},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3263701796531677},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.08291491866111755},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06159982085227966}],"concepts":[{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.8328183889389038},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.7945460081100464},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5469423532485962},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3263701796531677},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.08291491866111755},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06159982085227966},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2406.04321","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.04321","pdf_url":"https://arxiv.org/pdf/2406.04321","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.04321","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.04321","pdf_url":null,"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":"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.04321","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.04321","pdf_url":"https://arxiv.org/pdf/2406.04321","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W1585007175","https://openalex.org/W2382521049","https://openalex.org/W2390279801","https://openalex.org/W2144385241","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,14,34],"systematically":[4],"study":[5],"music":[6,42,53],"generation":[7],"conditioned":[8],"solely":[9],"on":[10],"the":[11,62,73,83],"video.":[12,63],"First,":[13],"present":[15],"a":[16,37],"large-scale":[17],"dataset":[18],"comprising":[19],"360K":[20],"video-music":[21],"pairs,":[22],"including":[23],"various":[24],"genres":[25],"such":[26],"as":[27],"movie":[28],"trailers,":[29],"advertisements,":[30],"and":[31,58,67,102,107],"documentaries.":[32],"Furthermore,":[33],"propose":[35],"VidMuse,":[36],"simple":[38],"framework":[39],"for":[40],"generating":[41],"aligned":[43,60],"with":[44,61],"video":[45,84],"inputs.":[46],"VidMuse":[47,71,92],"stands":[48],"out":[49],"by":[50],"producing":[51],"high-fidelity":[52],"that":[54,80],"is":[55],"both":[56],"acoustically":[57],"semantically":[59],"By":[64],"incorporating":[65],"local":[66],"global":[68],"visual":[69],"cues,":[70],"enables":[72],"creation":[74],"of":[75,98],"musically":[76],"coherent":[77],"audio":[78,99],"tracks":[79],"consistently":[81],"match":[82],"content":[85],"through":[86],"Long-Short-Term":[87],"modeling.":[88],"Through":[89],"extensive":[90],"experiments,":[91],"outperforms":[93],"existing":[94],"models":[95],"in":[96],"terms":[97],"quality,":[100],"diversity,":[101],"audio-visual":[103],"alignment.":[104],"The":[105],"code":[106],"datasets":[108],"are":[109],"available":[110],"at":[111],"https://vidmuse.github.io/.":[112]},"counts_by_year":[],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2025-10-10T00:00:00"}
