{"id":"https://openalex.org/W4409014352","doi":"https://doi.org/10.1109/access.2025.3555297","title":"BS-BGM: Leveraging Vision Language Models and Shot Boundary for Beat-Synced Video Background Music Generation","display_name":"BS-BGM: Leveraging Vision Language Models and Shot Boundary for Beat-Synced Video Background Music Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409014352","doi":"https://doi.org/10.1109/access.2025.3555297"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3555297","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3555297","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3555297","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103772284","display_name":"Yuan Hsun Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I141649914","display_name":"Nanchang University","ror":"https://ror.org/042v6xz23","country_code":"CN","type":"education","lineage":["https://openalex.org/I141649914"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuji Sun","raw_affiliation_strings":["School of Arts, Nanchang University, Honggutan, Nanchang, China","School of Arts, Nanchang University, No. 999, Xuefu Avenue, Honggutan New District, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"School of Arts, Nanchang University, Honggutan, Nanchang, China","institution_ids":["https://openalex.org/I141649914"]},{"raw_affiliation_string":"School of Arts, Nanchang University, No. 999, Xuefu Avenue, Honggutan New District, Nanchang, China","institution_ids":["https://openalex.org/I141649914"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004669931","display_name":"Yaguang Luo","orcid":"https://orcid.org/0000-0001-6164-4318"},"institutions":[{"id":"https://openalex.org/I141649914","display_name":"Nanchang University","ror":"https://ror.org/042v6xz23","country_code":"CN","type":"education","lineage":["https://openalex.org/I141649914"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunbin Luo","raw_affiliation_strings":["School of Arts, Nanchang University, Honggutan, Nanchang, China","School of Arts, Nanchang University, No. 999, Xuefu Avenue, Honggutan New District, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"School of Arts, Nanchang University, Honggutan, Nanchang, China","institution_ids":["https://openalex.org/I141649914"]},{"raw_affiliation_string":"School of Arts, Nanchang University, No. 999, Xuefu Avenue, Honggutan New District, Nanchang, China","institution_ids":["https://openalex.org/I141649914"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009385884","display_name":"Hao Chen","orcid":"https://orcid.org/0000-0002-5700-1202"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":["Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), Fusionopolis, Singapore","Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), Fusionopolis, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103772284"],"corresponding_institution_ids":["https://openalex.org/I141649914"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.6525,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.79781657,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"13","issue":null,"first_page":"57241","last_page":"57254"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9778000116348267,"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":0.9778000116348267,"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":0.9614999890327454,"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/T12290","display_name":"Human Motion and Animation","score":0.9415000081062317,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7456200122833252},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6075067520141602},{"id":"https://openalex.org/keywords/beat","display_name":"Beat (acoustics)","score":0.5014204978942871},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49530234932899475},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44556981325149536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4366459846496582},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.1015540063381195},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06872287392616272}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7456200122833252},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6075067520141602},{"id":"https://openalex.org/C189809214","wikidata":"https://www.wikidata.org/wiki/Q829522","display_name":"Beat (acoustics)","level":2,"score":0.5014204978942871},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49530234932899475},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44556981325149536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4366459846496582},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.1015540063381195},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06872287392616272},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3555297","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3555297","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:e28af645690c4516a2e5d481c532c2e7","is_oa":true,"landing_page_url":"https://doaj.org/article/e28af645690c4516a2e5d481c532c2e7","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 57241-57254 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3555297","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3555297","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2073411909","https://openalex.org/W2145364658","https://openalex.org/W2759171953","https://openalex.org/W2766525251","https://openalex.org/W2919115771","https://openalex.org/W2963300588","https://openalex.org/W3048938178","https://openalex.org/W3096831136","https://openalex.org/W3108049163","https://openalex.org/W3109897136","https://openalex.org/W3186392065","https://openalex.org/W3197294703","https://openalex.org/W3203711169","https://openalex.org/W3204221554","https://openalex.org/W4252337780","https://openalex.org/W4289821286","https://openalex.org/W4312814772","https://openalex.org/W4312933868","https://openalex.org/W4327521813","https://openalex.org/W4368364190","https://openalex.org/W4381708595","https://openalex.org/W4385801461","https://openalex.org/W4386071596","https://openalex.org/W4387195417","https://openalex.org/W4389520460","https://openalex.org/W4389819713","https://openalex.org/W4390343450","https://openalex.org/W4390873340","https://openalex.org/W4391136507","https://openalex.org/W4392172801","https://openalex.org/W4392435044","https://openalex.org/W4394896914","https://openalex.org/W4400118679","https://openalex.org/W4402715807","https://openalex.org/W6631190155","https://openalex.org/W6635270393","https://openalex.org/W6640963894","https://openalex.org/W6746596988","https://openalex.org/W6755182157","https://openalex.org/W6768465061","https://openalex.org/W6770639321","https://openalex.org/W6779823529","https://openalex.org/W6780770960","https://openalex.org/W6781642761","https://openalex.org/W6781678156","https://openalex.org/W6781910838","https://openalex.org/W6783182287","https://openalex.org/W6783713337","https://openalex.org/W6793578827","https://openalex.org/W6799025473","https://openalex.org/W6802978154","https://openalex.org/W6838327568","https://openalex.org/W6838582276","https://openalex.org/W6849105126","https://openalex.org/W6850357939","https://openalex.org/W6851596329","https://openalex.org/W6852278565","https://openalex.org/W6854445938","https://openalex.org/W6854652134","https://openalex.org/W6857284302","https://openalex.org/W6863632957","https://openalex.org/W6864124617","https://openalex.org/W6865466262","https://openalex.org/W6870515680","https://openalex.org/W6873009247","https://openalex.org/W6873075066","https://openalex.org/W6873575711","https://openalex.org/W6876112599"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Short":[0],"videos":[1,52],"have":[2],"emerged":[3],"as":[4,69,98],"a":[5,15,46,80,99,147],"powerful":[6],"medium":[7],"for":[8,84,154],"self-expression":[9],"and":[10,59,73,90,110,121,141,163],"background":[11],"music":[12,164],"(BGM)":[13],"plays":[14],"crucial":[16],"role":[17],"in":[18,134,150],"enhancing":[19],"audience":[20],"immersion.":[21],"Existing":[22],"video-to-audio":[23],"generation":[24,153],"methods":[25],"struggle":[26],"to":[27,36],"achieve":[28],"precise":[29],"alignment":[30,113],"with":[31,53,114],"beat-synced":[32,142],"dynamic":[33,107],"rhythms":[34],"tailored":[35],"video":[37,115,161],"content.":[38,116],"To":[39],"address":[40],"this":[41],"challenge,":[42],"we":[43,77],"introduce":[44],"BS-BGM500,":[45],"curated":[47],"dataset":[48,64,125],"comprising":[49],"500":[50],"short":[51,155],"meticulous":[54],"synchronization":[55],"between":[56,160],"shot":[57,70,95],"boundaries":[58],"audio":[60,137],"rhythm":[61,74,108],"changes.":[62],"This":[63,144],"includes":[65],"comprehensive":[66],"annotations":[67],"such":[68],"boundaries,":[71],"captions,":[72],"information.":[75],"Additionally,":[76],"propose":[78],"BS-BGM,":[79],"diffusion-based":[81],"model":[82,105],"designed":[83],"generating":[85],"BGMs.":[86],"By":[87],"integrating":[88],"visual":[89],"textual":[91],"features":[92],"while":[93],"leveraging":[94],"boundary":[96],"information":[97],"Boundary":[100],"Rhythm":[101],"Bias":[102],"(BRB),":[103],"the":[104,122,158],"achieves":[106],"transitions":[109],"ensures":[111],"seamless":[112],"Extensive":[117],"evaluations":[118],"on":[119],"BS-BGM500":[120],"widely-used":[123],"BGM909":[124],"demonstrate":[126],"that":[127],"our":[128],"method":[129],"significantly":[130],"outperforms":[131],"previous":[132],"approaches":[133],"terms":[135],"of":[136],"quality,":[138],"emotional":[139],"alignment,":[140],"consistency.":[143],"work":[145],"represents":[146],"substantial":[148],"advancement":[149],"automated":[151],"BGM":[152],"videos,":[156],"bridging":[157],"gap":[159],"dynamics":[162],"generation.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}