{"id":"https://openalex.org/W7168126161","doi":"https://doi.org/10.1145/3803784.3816841","title":"MVSCbench: A Benchmark for Symbolic and Cultural Understanding in Music Videos","display_name":"MVSCbench: A Benchmark for Symbolic and Cultural Understanding in Music Videos","publication_year":2026,"publication_date":"2026-07-13","ids":{"openalex":"https://openalex.org/W7168126161","doi":"https://doi.org/10.1145/3803784.3816841"},"language":null,"primary_location":{"id":"doi:10.1145/3803784.3816841","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3803784.3816841","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Creativity and Cognition","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3803784.3816841","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126927973","display_name":"Sijia Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sijia Gao","raw_affiliation_strings":["Sungkyunkwan University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0000-9810-282X","affiliations":[{"raw_affiliation_string":"Sungkyunkwan University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110630699","display_name":"Byeng-Hee Chang","orcid":"https://orcid.org/0000-0002-3542-3092"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byeng-Hee Chang","raw_affiliation_strings":["Sungkyunkwan University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-3542-3092","affiliations":[{"raw_affiliation_string":"Sungkyunkwan University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I848706"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I848706"],"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":"1410","last_page":"1415"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.26570001244544983,"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":0.26570001244544983,"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/T12214","display_name":"Media Influence and Health","score":0.06629999727010727,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.0649000033736229,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/benchmark","display_name":"Benchmark (surveying)","score":0.6948999762535095},{"id":"https://openalex.org/keywords/hallucinating","display_name":"Hallucinating","score":0.5965999960899353},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.5152000188827515},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.46160000562667847},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4521999955177307},{"id":"https://openalex.org/keywords/the-symbolic","display_name":"The Symbolic","score":0.4401000142097473},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.3758000135421753}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6948999762535095},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6283000111579895},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.5965999960899353},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.5152000188827515},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.46160000562667847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4578000009059906},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4521999955177307},{"id":"https://openalex.org/C2776095079","wikidata":"https://www.wikidata.org/wiki/Q489538","display_name":"The Symbolic","level":2,"score":0.4401000142097473},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3758000135421753},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.3393999934196472},{"id":"https://openalex.org/C115233962","wikidata":"https://www.wikidata.org/wiki/Q1791627","display_name":"Cultural artifact","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3188999891281128},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.3125999867916107},{"id":"https://openalex.org/C114611597","wikidata":"https://www.wikidata.org/wiki/Q373342","display_name":"Popular music","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27709999680519104},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.25850000977516174}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3803784.3816841","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3803784.3816841","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Creativity and Cognition","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3803784.3816841","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3803784.3816841","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Creativity and Cognition","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.43374210596084595,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2802222440","https://openalex.org/W2987940036","https://openalex.org/W3175859344","https://openalex.org/W3176633600","https://openalex.org/W4254185221","https://openalex.org/W4402702917","https://openalex.org/W4404783219","https://openalex.org/W4413147366","https://openalex.org/W7160173378","https://openalex.org/W7162087181"],"related_works":[],"abstract_inverted_index":{"This":[0],"study":[1],"introduces":[2],"MVSCBench,":[3],"the":[4,99],"benchmark":[5,123],"designed":[6],"to":[7,13,103],"evaluate":[8],"multimodal":[9,77],"AI":[10,78],"models\u2019":[11],"ability":[12],"interpret":[14],"symbolic":[15,37,92,126],"and":[16,39,54,68,94,109,127,133],"cultural":[17,40,70,95,128],"meanings":[18],"in":[19,91,114,130],"music":[20,24,29,131],"videos.":[21],"Using":[22],"K-pop":[23],"video":[25,30,52],"clips,":[26],"we":[27,46],"organize":[28],"understanding":[31,129],"into":[32],"three":[33],"stages:":[34],"surface":[35,83],"perception,":[36],"interpretation,":[38],"grounding.":[41,96],"Based":[42],"on":[43,82],"this":[44],"framework,":[45],"construct":[47],"a":[48,121,135],"dataset":[49],"of":[50],"293":[51],"clips":[53],"3,516":[55],"annotations,":[56],"covering":[57],"space,":[58],"artist,":[59],"character":[60],"symbolism,":[61,63,65,67],"object":[62],"literary":[64],"social-historical":[66],"fandom":[69],"symbols.":[71],"The":[72],"results":[73],"show":[74],"that":[75],"current":[76],"models":[79,100],"perform":[80],"well":[81],"perception":[84],"tasks,":[85],"but":[86],"still":[87],"face":[88],"clear":[89],"limitations":[90],"interpretation":[93],"In":[97],"particular,":[98],"often":[101],"struggle":[102],"correctly":[104],"identify":[105],"relevant":[106],"visual":[107],"cues":[108],"frequently":[110],"produce":[111],"hallucinated":[112],"interpretations":[113],"categories":[115],"involving":[116],"deeper":[117],"meanings.":[118],"MVSCBench":[119],"provides":[120],"new":[122],"for":[124,138],"evaluating":[125],"videos":[132],"offers":[134],"useful":[136],"framework":[137],"future":[139],"research.":[140]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-07-14T00:00:00"}
