{"id":"https://openalex.org/W7138456349","doi":"https://doi.org/10.1609/aaai.v40i8.37550","title":"CrossVid: A Comprehensive Benchmark for Evaluating Cross-Video Reasoning in Multimodal Large Language Models","display_name":"CrossVid: A Comprehensive Benchmark for Evaluating Cross-Video Reasoning in Multimodal Large Language Models","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138456349","doi":"https://doi.org/10.1609/aaai.v40i8.37550"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i8.37550","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37550","pdf_url":null,"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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i8.37550","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129658179","display_name":"Jingyao Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jingyao Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129657250","display_name":"Jingyun Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingyun Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129733849","display_name":"Molin Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Molin Tan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129708692","display_name":"Haochen Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haochen Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035332982","display_name":"Cilin Yan","orcid":"https://orcid.org/0000-0001-9754-129X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cilin Yan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042998769","display_name":"Likun Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Likun Shi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066854056","display_name":"Jiayin Cai","orcid":"https://orcid.org/0009-0007-8903-212X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiayin Cai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129683584","display_name":"Xiaolong Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaolong Jiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129718896","display_name":"Yao Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao Hu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5129658179"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8463833,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"8","first_page":"6244","last_page":"6252"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9763000011444092,"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":0.9763000011444092,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0032999999821186066,"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/T10028","display_name":"Topic Modeling","score":0.00279999990016222,"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":0.7516000270843506},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5058000087738037},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4449999928474426},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.37139999866485596},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.31850001215934753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7982000112533569},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7516000270843506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5389000177383423},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5058000087738037},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49939998984336853},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.37139999866485596},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34369999170303345},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30709999799728394},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i8.37550","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37550","pdf_url":null,"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"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i8.37550","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37550","pdf_url":null,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Cross-Video":[0],"Reasoning":[1],"(CVR)":[2],"presents":[3],"a":[4,73,106],"significant":[5],"challenge":[6],"in":[7,78,100,214],"video":[8,28,130],"understanding,":[9],"which":[10],"requires":[11],"simultaneous":[12],"understanding":[13,29],"of":[14,24,40,64,76,109,128,171,208],"multiple":[15,199],"videos":[16,59,200],"to":[17,36,46,93,189,192,210],"aggregate":[18],"and":[19,116,125,146,156],"compare":[20,195],"information":[21],"across":[22,198],"groups":[23],"videos.":[25,51],"Most":[26],"existing":[27],"benchmarks":[30,53],"focus":[31],"on":[32,57,153,165],"single-video":[33],"analysis,":[34],"failing":[35],"assess":[37],"the":[38,65,89,123,206],"ability":[39,99],"multimodal":[41],"large":[42],"language":[43],"models":[44],"(MLLMs)":[45],"simultaneously":[47],"reason":[48],"over":[49],"various":[50,154],"Recent":[52],"evaluate":[54,95],"MLLMs'":[55,96],"capabilities":[56],"multi-view":[58],"that":[60,161,179],"capture":[61],"different":[62],"perspectives":[63],"same":[66],"scene.":[67],"However,":[68],"their":[69,190],"limited":[70],"tasks":[71],"hinder":[72],"thorough":[74],"assessment":[75],"MLLMs":[77,182],"diverse":[79],"real-world":[80,129],"CVR":[81,185,217],"scenarios.":[82],"To":[83],"this":[84],"end,":[85],"we":[86,159],"introduce":[87],"CrossVid,":[88,166],"first":[90],"benchmark":[91],"designed":[92],"comprehensively":[94],"spatial-temporal":[97],"reasoning":[98],"cross-video":[101],"contexts.":[102],"Firstly,":[103],"CrossVid":[104,133,209],"encompasses":[105],"wide":[107],"spectrum":[108],"hierarchical":[110],"tasks,":[111,119,186],"comprising":[112],"four":[113],"high-level":[114],"dimensions":[115],"ten":[117],"specific":[118],"thereby":[120],"closely":[121],"reflecting":[122],"complex":[124],"varied":[126],"nature":[127],"understanding.":[131],"Secondly,":[132],"provides":[134],"5,331":[135],"videos,":[136],"along":[137],"with":[138,184],"9,015":[139],"challenging":[140],"question-answering":[141],"pairs,":[142],"spanning":[143],"single-choice,":[144],"multiple-choice,":[145],"open-ended":[147],"question":[148],"formats.":[149],"Through":[150],"extensive":[151],"experiments":[152],"open-source":[155],"closed-source":[157],"MLLMs,":[158],"observe":[160],"Gemini-2.5-Pro":[162],"performs":[163],"best":[164],"achieving":[167],"an":[168],"average":[169],"accuracy":[170],"50.4%.":[172],"Notably,":[173],"our":[174],"in-depth":[175],"case":[176],"study":[177],"demonstrates":[178],"most":[180],"current":[181],"struggle":[183],"primarily":[187],"due":[188],"inability":[191],"integrate":[193],"or":[194],"evidence":[196],"distributed":[197],"for":[201],"reasoning.":[202],"These":[203],"insights":[204],"highlight":[205],"potential":[207],"guide":[211],"future":[212],"advancements":[213],"enhancing":[215],"MLLMs\u2019":[216],"capabilities.":[218]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}