{"id":"https://openalex.org/W7204203441","doi":"https://doi.org/10.18653/2026.emnlp-main.1913","title":"Cultural Moment Benchmark: Evaluating Video Cultural Reasoning and Grounding in Southeast Asia","display_name":"Cultural Moment Benchmark: Evaluating Video Cultural Reasoning and Grounding in Southeast Asia","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204203441","doi":"https://doi.org/10.18653/2026.emnlp-main.1913"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-main.1913","doi":"https://doi.org/10.18653/2026.emnlp-main.1913","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1913","pdf_url":"https://aclanthology.org/2026.emnlp-main.1913.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.emnlp-main.1913.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076041088","display_name":"Burak Satar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Burak Satar","raw_affiliation_strings":["Singapore Management University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University ,","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148094156","display_name":"Zhixin Ma","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhixin Ma","raw_affiliation_strings":["Singapore Management University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University ,","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148065636","display_name":"Cheng Yu-Tong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Cheng Yu-Tong","raw_affiliation_strings":["Singapore Management University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University ,","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148073029","display_name":"Huy Hoang Tran","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huy Hoang Tran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000332791","display_name":"Phuong Anh Nguyen","orcid":"https://orcid.org/0000-0003-1289-3785","observed_orcids":["https://orcid.org/0000-0003-1289-3785"]},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Phuong Anh Nguyen","raw_affiliation_strings":["Singapore Management University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University ,","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133999323","display_name":"Chong Wah Ngo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chong-Wah Ngo","raw_affiliation_strings":["Singapore Management University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University ,","institution_ids":["https://openalex.org/I79891267"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.59630193,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"43574","last_page":"43607"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"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":0.9990000128746033,"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/T12694","display_name":"Categorization, perception, and language","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":9.999999747378752e-05,"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/cultural-concepts","display_name":"cultural concepts","score":0.5550000071525574},{"id":"https://openalex.org/keywords/video-grounding","display_name":"video grounding","score":0.5320000052452087},{"id":"https://openalex.org/keywords/temporal-localization","display_name":"temporal localization","score":0.5600000023841858},{"id":"https://openalex.org/keywords/southeast-asian-culture","display_name":"Southeast Asian culture","score":0.5429999828338623},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.7699999809265137},{"id":"https://openalex.org/keywords/intercultural-knowledge","display_name":"intercultural knowledge","score":0.49000000953674316},{"id":"https://openalex.org/keywords/benchmark-design","display_name":"benchmark design","score":0.6639999747276306},{"id":"https://openalex.org/keywords/failure-mode-analysis","display_name":"failure mode analysis","score":0.5950000286102295}],"concepts":[{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.6258999705314636},{"id":"https://openalex.org/C3019398675","wikidata":"https://www.wikidata.org/wiki/Q11708","display_name":"Southeast asia","level":2,"score":0.5856999754905701},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5694000124931335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4837999939918518},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41819998621940613},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.41019999980926514},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3686999976634979},{"id":"https://openalex.org/C2992975276","wikidata":"https://www.wikidata.org/wiki/Q11042","display_name":"Cultural background","level":4,"score":0.36489999294281006},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3513999879360199},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32919999957084656},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C125209646","wikidata":"https://www.wikidata.org/wiki/Q1338878","display_name":"Cultural diversity","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.28299999237060547},{"id":"https://openalex.org/C2994055011","wikidata":"https://www.wikidata.org/wiki/Q210272","display_name":"Cultural knowledge","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2676999866962433},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.25519999861717224},{"id":"https://openalex.org/C2776095079","wikidata":"https://www.wikidata.org/wiki/Q489538","display_name":"The Symbolic","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.emnlp-main.1913","doi":"https://doi.org/10.18653/2026.emnlp-main.1913","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1913","pdf_url":"https://aclanthology.org/2026.emnlp-main.1913.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2608.23065","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23065","pdf_url":"https://arxiv.org/pdf/2608.23065","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.23065","doi":"https://doi.org/10.48550/arxiv.2608.23065","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.23065","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/2026.emnlp-main.1913","doi":"https://doi.org/10.18653/2026.emnlp-main.1913","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1913","pdf_url":"https://aclanthology.org/2026.emnlp-main.1913.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1482925484","display_name":null,"funder_award_id":"Tier 1","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"},{"id":"https://openalex.org/G6854926366","display_name":null,"funder_award_id":"Tier 2","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"}],"funders":[{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204203441.pdf","grobid_xml":"https://content.openalex.org/works/W7204203441.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W4283752706","https://openalex.org/W4405903187","https://openalex.org/W4406033240","https://openalex.org/W4409368659","https://openalex.org/W4412780451","https://openalex.org/W4412888462","https://openalex.org/W4412944862","https://openalex.org/W4415313783","https://openalex.org/W4416529434","https://openalex.org/W4416780398","https://openalex.org/W4416960213","https://openalex.org/W4416975768","https://openalex.org/W6948369276","https://openalex.org/W7077911270","https://openalex.org/W7106754196","https://openalex.org/W7119523234","https://openalex.org/W7124510818","https://openalex.org/W7125827634","https://openalex.org/W7154234390","https://openalex.org/W7161684814","https://openalex.org/W7165651203","https://openalex.org/W7166874890","https://openalex.org/W7172385553","https://openalex.org/W7220993947"],"related_works":["https://openalex.org/W4414744311","https://openalex.org/W4415016180","https://openalex.org/W7124510818","https://openalex.org/W7168126161","https://openalex.org/W7152643753","https://openalex.org/W3036977033","https://openalex.org/W2897628926","https://openalex.org/W7124221590","https://openalex.org/W4416960213","https://openalex.org/W4417126502"],"abstract_inverted_index":{"Cultural":[0,65],"understanding":[1],"in":[2,41,75,123,211,227],"video":[3,108,144,154],"means":[4],"more":[5,224],"than":[6],"recognizing":[7,33,202],"what":[8,28,48],"is":[9,49,215],"visible;":[10],"it":[11,34,198,203],"requires":[12,261],"grasping":[13],"the":[14,61,64,115,121,167,195,209,222,239],"symbolic":[15],"and":[16,37,110,117,147,164,233,237],"temporal":[17],"significance":[18],"of":[19,120],"cultural":[20,263],"concepts.We":[21],"decompose":[22],"this":[23],"into":[24,55],"three":[25,53,85,136,176,183],"abilities:":[26],"naming":[27,189],"a":[29,56,90,124,131,151,190,255,267,273],"concept":[30,83,99,191],"symbolizes,":[31],"visually":[32],"on":[35,130,150,199,207,221,252],"video,":[36,200],"locating":[38,208],"its":[39],"sub-events":[40],"time.Existing":[42],"videocultural":[43],"benchmarks":[44],"tend":[45],"to":[46,272],"test":[47],"seen,":[50],"collapsing":[51],"these":[52],"abilities":[54,184],"single":[57],"score":[58,171,249],"that":[59,245,259],"hides":[60],"bottleneck.We":[62],"introduce":[63],"Moment":[66],"Benchmark":[67],"(CMB):":[68],"306":[69],"expert-curated":[70],"concepts":[71,253],"from":[72,96,105,254],"seven":[73],"countries":[74],"Southeast":[76],"Asia":[77],"across":[78],"five":[79],"categories.We":[80],"evaluate":[81],"each":[82,127],"through":[84],"stages,":[86],"one":[87],"per":[88],"ability.Given":[89],"description,":[91],"Stage":[92,101,111],"1":[93],"(S1)":[94],"selects":[95,104],"four":[97,106],"candidate":[98,107],"names,":[100],"2":[102],"(S2)":[103],"moments,":[109],"3":[112],"(S3)":[113],"predicts":[114],"start":[116],"end":[118],"times":[119],"moment":[122],"video.To":[125],"keep":[126],"stage":[128],"focused":[129],"distinct":[132],"ability,":[133],"we":[134],"use":[135],"design":[137],"choices:":[138],"semantic-similarity":[139],"distractors":[140],"(S1,":[141],"S2),":[142],"unlabeled":[143],"moments":[145],"(S2),":[146],"free-form":[148],"localization":[149],"different":[152],"example":[153],"(S3).Across":[155],"six":[156],"visionlanguage":[157],"models,":[158],"failure":[159],"modes":[160],"vary":[161],"by":[162],"ability":[163,275],"modality.i)":[165],"Even":[166],"strongest":[168],"closedsource":[169],"models":[170,196],"below":[172,250],"30%":[173],"when":[174],"all":[175],"stages":[177],"must":[178],"be":[179],"correct;":[180],"ii)":[181],"The":[182],"do":[185],"not":[186],"fully":[187],"cascade:":[188],"correctly":[192],"helps":[193],"half":[194],"recognize":[197],"but":[201],"has":[204],"little":[205],"effect":[206],"sub-event":[210],"time;":[212],"iii)":[213],"Audio":[214],"complementary,":[216],"redundant,":[217],"or":[218,276],"distracting":[219,226],"depending":[220],"concept,":[223],"often":[225],"non-Latinscript":[228],"countries;":[229],"removing":[230],"both":[231],"audio":[232],"subtitles":[234],"hurts":[235],"Games":[236],"Music":[238],"most.Our":[240],"14-rater":[241],"human":[242],"study":[243],"shows":[244],"even":[246],"Expert":[247],"raters":[248],"chance":[251],"neighboring":[256],"country,":[257],"indicating":[258],"CMB":[260],"country-specific":[262],"knowledge.CMB":[264],"acts":[265],"as":[266],"diagnostic":[268],"harness,":[269],"attributing":[270],"failures":[271],"specific":[274],"modality.":[277]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-08-26T00:00:00"}