{"id":"https://openalex.org/W7137840380","doi":"https://doi.org/10.1609/aaai.v40i5.37331","title":"VMChill: A Dataset for Fine-Grained Visual-Musical Synergy","display_name":"VMChill: A Dataset for Fine-Grained Visual-Musical Synergy","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137840380","doi":"https://doi.org/10.1609/aaai.v40i5.37331"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i5.37331","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37331","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37331/41293","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37331/41293","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129664654","display_name":"Xiaowei Chi","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaowei Chi","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129666888","display_name":"Zeyue Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zeyue Tian","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129672118","display_name":"Jialiang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jialiang Chen","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129741629","display_name":"Wei Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wei Xue","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"5","first_page":"3353","last_page":"3362"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.39309999346733093,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.39309999346733093,"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":0.30809998512268066,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.14569999277591705,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6674000024795532},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5462999939918518},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4975999891757965},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.41679999232292175},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4115000069141388},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4108999967575073},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.40630000829696655},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3765000104904175},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.37119999527931213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7879999876022339},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6674000024795532},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5462999939918518},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4975999891757965},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4523000121116638},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41780000925064087},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.41679999232292175},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4115000069141388},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4108999967575073},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.40630000829696655},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3765000104904175},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.37119999527931213},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3589000105857849},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.34619998931884766},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3206999897956848},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C2777526511","wikidata":"https://www.wikidata.org/wiki/Q691543","display_name":"Pace","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C150202949","wikidata":"https://www.wikidata.org/wiki/Q107602","display_name":"Pointer (user interface)","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2768000066280365},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2667999863624573},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2565000057220459},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1609/aaai.v40i5.37331","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37331","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37331/41293","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-171646","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-171646","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"},{"id":"pmh:oai:ojs.aaai.org:article/37331","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i5.37331","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37331","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37331/41293","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6545816659927368}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137840380.pdf","grobid_xml":"https://content.openalex.org/works/W7137840380.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Massive":[0],"multi-modality":[1],"datasets":[2,14],"are":[3,77],"fundamental":[4],"to":[5,80,134,161,211,231,249],"the":[6,34,45,216,242],"success":[7],"of":[8,47,112,182],"large":[9,155],"video-language":[10],"models.":[11],"However,":[12],"existing":[13],"often":[15],"focus":[16],"on":[17,203],"providing":[18],"textual":[19],"descriptions":[20,166],"for":[21,49,93,197],"visual":[22,39,86,142],"content,":[23,143],"treating":[24],"audio,":[25],"particularly":[26],"music,":[27],"as":[28,71,75],"weakly":[29],"related":[30],"information.":[31],"This":[32,127,175],"overlooks":[33],"inherent":[35],"semantic":[36],"correlation":[37],"between":[38,85],"narratives":[40],"and":[41,53,90,95,146,171,190,209,214,246],"musical":[42,147],"scores,":[43],"limiting":[44],"development":[46],"models":[48,133],"fine-grained":[50,64,236],"cross-modal":[51],"understanding":[52,208],"generation.":[54],"To":[55,116],"address":[56],"this":[57,118],"gap,":[58],"we":[59,120],"introduce":[60],"VMChill,":[61],"a":[62,82,122,154,168,179,192],"large-scale,":[63],"multimodal":[65,124,173,188,237],"video":[66,104,207],"dataset.":[67],"We":[68,199,239],"leverage":[69],"trailers":[70],"our":[72],"data":[73],"source,":[74],"they":[76],"professionally":[78],"edited":[79],"create":[81],"strong":[83],"synergy":[84],"pacing,":[87],"scene":[88],"transitions,":[89],"background":[91],"music":[92],"narrative":[94],"emotional":[96],"impact.":[97],"Our":[98],"dataset":[99],"comprises":[100],"over":[101],"20":[102],"million":[103,184],"clips":[105,185],"derived":[106],"from":[107,138],"more":[108],"than":[109],"27.1k":[110],"hours":[111],"high-resolution":[113],"trailer":[114],"videos.":[115],"annotate":[117],"data,":[119],"propose":[121],"systematic":[123],"captioning":[125],"framework.":[126],"framework":[128],"first":[129],"employs":[130],"specialized":[131],"unimodal":[132],"extract":[135],"descriptive":[136],"features":[137],"multiple":[139],"perspectives,":[140],"including":[141,206],"motion":[144],"dynamics,":[145],"attributes":[148],"(e.g.,":[149],"genre,":[150],"instruments,":[151],"mood).":[152],"Subsequently,":[153],"language":[156],"model":[157,226],"(LLM)":[158],"is":[159],"utilized":[160],"adaptively":[162],"fuse":[163],"these":[164],"diverse":[165],"into":[167],"single,":[169],"coherent,":[170],"rich":[172],"caption.":[174],"process":[176],"yields":[177],"VMChill-2M,":[178],"high-quality":[180],"subset":[181],"2":[183],"with":[186],"detailed":[187],"annotations,":[189],"VMChill-Test,":[191],"manually":[193],"refined":[194],"test":[195],"set":[196],"evaluation.":[198],"conduct":[200],"extensive":[201],"experiments":[202],"downstream":[204],"tasks,":[205],"generation,":[210],"establish":[212],"benchmarks":[213],"demonstrate":[215],"dataset's":[217],"quality.":[218],"The":[219],"results":[220],"validate":[221],"that":[222],"VMChill":[223],"effectively":[224],"enhances":[225],"performance,":[227],"highlighting":[228],"its":[229],"potential":[230],"facilitate":[232],"future":[233],"research":[234],"in":[235],"learning.":[238],"will":[240],"release":[241],"dataset,":[243],"annotation":[244],"codebase,":[245],"processing":[247],"pipelines":[248],"support":[250],"community":[251],"research.":[252]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}