{"id":"https://openalex.org/W7164860546","doi":"https://doi.org/10.1145/3805622.3810581","title":"CB-CV: A Cluster-Based Cross-Validation Benchmark for Multimodal Video Out-of-Distribution Detection","display_name":"CB-CV: A Cluster-Based Cross-Validation Benchmark for Multimodal Video Out-of-Distribution Detection","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164860546","doi":"https://doi.org/10.1145/3805622.3810581"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810581","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810581","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 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810581","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138654810","display_name":"Ji Zhang","orcid":"https://orcid.org/0009-0006-2775-1914"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ji Zhang","raw_affiliation_strings":["Department of Statistics and Operations Research, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA"],"raw_orcid":"https://orcid.org/0009-0006-2775-1914","affiliations":[{"raw_affiliation_string":"Department of Statistics and Operations Research, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100426938","display_name":"Xiao Luo","orcid":"https://orcid.org/0000-0002-7987-3714"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Luo","raw_affiliation_strings":["Department of Statistics, University of Wisconsin\u2013Madison, Madison, WI, USA"],"raw_orcid":"https://orcid.org/0000-0002-7987-3714","affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Wisconsin\u2013Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125700119","display_name":"Hang Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hang Zhou","raw_affiliation_strings":["Department of Statistics and Operations Research, The University of North Carolina at Chapel Hill, Chapel Hill, NC, USA and School of Data Science and Society, The University of North Carolina at Chapel Hill, Chapel Hill, NC, USA"],"raw_orcid":"https://orcid.org/0009-0003-9535-6287","affiliations":[{"raw_affiliation_string":"Department of Statistics and Operations Research, The University of North Carolina at Chapel Hill, Chapel Hill, NC, USA and School of Data Science and Society, The University of North Carolina at Chapel Hill, Chapel Hill, NC, USA","institution_ids":["https://openalex.org/I114027177"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.69012661,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2543","last_page":"2551"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.7889000177383423,"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"}},"topics":[{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.7889000177383423,"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"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.03139999881386757,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.031099999323487282,"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/robustness","display_name":"Robustness (evolution)","score":0.7978000044822693},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5766000151634216},{"id":"https://openalex.org/keywords/ranging","display_name":"Ranging","score":0.515999972820282},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.47040000557899475},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.3831999897956848},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.3695000112056732},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.36890000104904175},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.33899998664855957}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7978000044822693},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6901999711990356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5989000201225281},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5766000151634216},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.515999972820282},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4794999957084656},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.47040000557899475},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.3831999897956848},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.36890000104904175},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3384000062942505},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3361999988555908},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2870999872684479},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.27219998836517334}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810581","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810581","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 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810581","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810581","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 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2016381774","https://openalex.org/W2126579184","https://openalex.org/W2963524571","https://openalex.org/W2990503944","https://openalex.org/W4214769349","https://openalex.org/W4312776478","https://openalex.org/W4386083133","https://openalex.org/W4399929809","https://openalex.org/W4402704561","https://openalex.org/W4402915937","https://openalex.org/W4409014847","https://openalex.org/W4413144720","https://openalex.org/W4415538289","https://openalex.org/W7084978443"],"related_works":[],"abstract_inverted_index":{"Out-of-distribution":[0],"(OOD)":[1],"detection":[2,140,227],"is":[3,136],"crucial":[4],"for":[5,35,219],"applying":[6],"machine":[7],"learning":[8],"systems":[9],"in":[10],"open-world":[11],"scenarios.":[12],"However,":[13],"existing":[14],"multimodal":[15,224],"video":[16,225],"OOD":[17,24,110,226],"benchmarks":[18],"typically":[19],"construct":[20],"in-distribution":[21],"(ID)":[22],"and":[23,91,104,192,212],"splits":[25],"via":[26,93],"sequential":[27,129],"class":[28,78],"partitioning,":[29],"which":[30],"does":[31],"not":[32],"explicitly":[33],"account":[34],"feature-space":[36,74],"relationships":[37],"between":[38],"categories.":[39],"This":[40,134],"limitation":[41],"may":[42],"inadvertently":[43],"introduce":[44],"semantic":[45],"ambiguity":[46],"when":[47],"similar":[48],"classes":[49,72],"are":[50,80],"assigned":[51],"to":[52,128,172,178],"opposite":[53],"sides":[54],"of":[55,139,159,197,209,223],"the":[56,101,105,109,121,157,160,207,221],"split.":[57],"In":[58,76],"this":[59,189],"paper,":[60],"we":[61],"propose":[62],"Cluster-Based":[63],"Cross-Validation":[64],"(CB-CV),":[65],"an":[66,194],"alternative":[67,229],"evaluation":[68,211],"protocol":[69],"that":[70],"organizes":[71],"by":[73,125],"similarity.":[75],"CB-CV,":[77],"prototypes":[79],"derived":[81],"from":[82,169],"a":[83,216],"dual-stream":[84],"backbone,":[85],"clustered":[86],"based":[87],"on":[88],"inter-class":[89],"distances,":[90],"evaluated":[92],"leave-one-cluster-out":[94],"cross-validation,":[95],"where":[96],"each":[97],"cluster":[98],"serves":[99],"as":[100,215],"ID":[102],"set":[103],"remaining":[106],"clusters":[107],"form":[108],"set.":[111],"Across":[112],"1,701":[113],"pipeline":[114],"configurations":[115],"spanning":[116],"three":[117],"datasets,":[118],"CB-CV":[119,187,214],"increases":[120],"mean":[122],"ID\u2013OOD":[123],"distance":[124,135],"18.5%":[126],"compared":[127],"partitioning":[130],"(p":[131],"<":[132],"0.001).":[133],"moderately":[137],"predictive":[138],"performance":[141],"overall":[142],"(r":[143],"=":[144],"\u22120.600":[145],"with":[146],"False":[147],"Positive":[148,153],"Rate":[149,154],"at":[150],"95%":[151],"True":[152],"(FPR95)),":[155],"but":[156],"strength":[158],"relationship":[161],"varies":[162],"widely":[163],"across":[164,184],"methods":[165],"(FPR95":[166],"correlations":[167],"ranging":[168],"\u2212":[170,173],"0.73":[171],"0.25),":[174],"indicating":[175],"method-dependent":[176],"sensitivity":[177,190],"split":[179],"structure.":[180],"By":[181],"reporting":[182],"results":[183,205],"multiple":[185],"folds,":[186],"makes":[188],"explicit":[191],"offers":[193],"additional":[195],"characterization":[196],"robustness":[198,222],"under":[199,228],"structured":[200],"distributional":[201,230],"shifts.":[202],"Together,":[203],"these":[204],"highlight":[206],"importance":[208],"structure-aware":[210],"position":[213],"complementary":[217],"benchmark":[218],"assessing":[220],"structures.":[231]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-06-16T00:00:00"}