{"id":"https://openalex.org/W4367860227","doi":"https://doi.org/10.48550/arxiv.2305.01319","title":"Long-Term Rhythmic Video Soundtracker","display_name":"Long-Term Rhythmic Video Soundtracker","publication_year":2023,"publication_date":"2023-05-02","ids":{"openalex":"https://openalex.org/W4367860227","doi":"https://doi.org/10.48550/arxiv.2305.01319"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2305.01319","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.01319","pdf_url":"https://arxiv.org/pdf/2305.01319","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":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.01319","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052798964","display_name":"Jiashuo Yu","orcid":"https://orcid.org/0000-0002-3094-6687"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yu, Jiashuo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100672233","display_name":"Yaohui Wang","orcid":"https://orcid.org/0009-0002-6262-7450"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yaohui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100664513","display_name":"Xinyuan Chen","orcid":"https://orcid.org/0000-0002-6127-9602"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xinyuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100642898","display_name":"Xiao Sun","orcid":"https://orcid.org/0000-0002-2530-5412"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Xiao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100748135","display_name":"Yu Qiao","orcid":"https://orcid.org/0000-0002-1889-2567"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao, Yu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5052798964"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9959999918937683,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.9890000224113464,"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/computer-science","display_name":"Computer science","score":0.7130715250968933},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.6309913992881775},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.5529671311378479},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5451506972312927},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5012063980102539},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.47789204120635986},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.47283443808555603},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4387784004211426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.349919855594635},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.2065151333808899}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7130715250968933},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.6309913992881775},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.5529671311378479},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5451506972312927},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5012063980102539},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.47789204120635986},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.47283443808555603},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4387784004211426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.349919855594635},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2065151333808899},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2305.01319","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.01319","pdf_url":"https://arxiv.org/pdf/2305.01319","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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2305.01319","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.01319","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:2305.01319","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.01319","pdf_url":"https://arxiv.org/pdf/2305.01319","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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1487784003","display_name":null,"funder_award_id":"62102150","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4367860227.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2072492413","https://openalex.org/W2364370872","https://openalex.org/W2997159972","https://openalex.org/W2053269318","https://openalex.org/W4296378967","https://openalex.org/W2025614924","https://openalex.org/W2064134577","https://openalex.org/W2373995729","https://openalex.org/W3203096336","https://openalex.org/W2294335174"],"abstract_inverted_index":{"We":[0],"consider":[1],"the":[2,24,131],"problem":[3],"of":[4,26,69,83],"generating":[5,34],"musical":[6,152],"soundtracks":[7,129,149],"in":[8],"sync":[9],"with":[10,150],"rhythmic":[11,127,155],"visual":[12],"cues.":[13],"Most":[14],"existing":[15],"works":[16],"rely":[17],"on":[18],"pre-defined":[19],"music":[20],"representations,":[21],"leading":[22],"to":[23,60,76,89,107],"incompetence":[25],"generative":[27,139],"flexibility":[28],"and":[29,43,115,137,154],"complexity.":[30],"Other":[31],"methods":[32],"directly":[33],"video-conditioned":[35],"waveforms":[36],"suffer":[37],"from":[38,105],"limited":[39],"scenarios,":[40],"short":[41],"lengths,":[42],"unstable":[44],"generation":[45],"quality.":[46],"To":[47,118],"this":[48],"end,":[49],"we":[50,100,122],"present":[51],"Long-Term":[52],"Rhythmic":[53],"Video":[54],"Soundtracker":[55],"(LORIS),":[56],"a":[57,70,81,96,124],"novel":[58],"framework":[59,67],"synthesize":[61],"long-term":[62,97,148],"conditional":[63,72],"waveforms.":[64],"Specifically,":[65],"our":[66,102,145],"consists":[68],"latent":[71],"diffusion":[73],"probabilistic":[74],"model":[75,146],"perform":[77,119],"waveform":[78],"synthesis.":[79],"Furthermore,":[80],"series":[82],"context-aware":[84],"conditioning":[85],"encoders":[86],"are":[87,158],"proposed":[88],"take":[90],"temporal":[91],"information":[92],"into":[93],"consideration":[94],"for":[95,126],"generation.":[98],"Notably,":[99],"extend":[101],"model's":[103],"applicability":[104],"dances":[106],"multiple":[108],"sports":[109],"scenarios":[110],"such":[111],"as":[112],"floor":[113],"exercise":[114],"figure":[116],"skating.":[117],"comprehensive":[120],"evaluations,":[121],"establish":[123],"benchmark":[125],"video":[128],"including":[130],"pre-processed":[132],"dataset,":[133],"improved":[134],"evaluation":[135],"metrics,":[136],"robust":[138],"baselines.":[140],"Extensive":[141],"experiments":[142],"show":[143],"that":[144],"generates":[147],"state-of-the-art":[151],"quality":[153],"correspondence.":[156],"Codes":[157],"available":[159],"at":[160],"\\url{https://github.com/OpenGVLab/LORIS}.":[161]},"counts_by_year":[{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
