{"id":"https://openalex.org/W7155367461","doi":"https://doi.org/10.48550/arxiv.2604.20460","title":"CCTVBench: Contrastive Consistency Traffic VideoQA Benchmark for Multimodal LLMs","display_name":"CCTVBench: Contrastive Consistency Traffic VideoQA Benchmark for Multimodal LLMs","publication_year":2026,"publication_date":"2026-04-22","ids":{"openalex":"https://openalex.org/W7155367461","doi":"https://doi.org/10.48550/arxiv.2604.20460"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2604.20460","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.20460","pdf_url":"https://arxiv.org/pdf/2604.20460","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2604.20460","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125729559","display_name":"Xingcheng Zhou","orcid":"https://orcid.org/0000-0003-1178-5221","observed_orcids":["https://orcid.org/0000-0003-1178-5221"]},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zhou, Xingcheng","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134459798","display_name":"Hao Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Guo, Hao","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134440600","display_name":"Rui Song","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Song, Rui","raw_affiliation_strings":["University of California , Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134438552","display_name":"Walter Zimmer","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zimmer, Walter","raw_affiliation_strings":["University of California , Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134243371","display_name":"Mingyu Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Liu, Mingyu","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116057091","display_name":"Andr\u00e9 Schamschurko","orcid":"https://orcid.org/0009-0000-7030-0955","observed_orcids":["https://orcid.org/0009-0000-7030-0955"]},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Schamschurko, Andr\u00e9","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134433052","display_name":"Hu Cao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Cao, Hu","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133172521","display_name":"Alois Knoll","orcid":"https://orcid.org/0000-0003-4840-076X","observed_orcids":["https://orcid.org/0000-0003-4840-076X"]},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Knoll, Alois","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":null,"issue":null,"first_page":null,"last_page":null},"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/T10370","display_name":"Traffic and Road Safety","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":9.999999747378752e-05,"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/multimodal-large-language-models","display_name":"multimodal large language models","score":0.8009999990463257},{"id":"https://openalex.org/keywords/traffic-accident-detection","display_name":"traffic accident detection","score":0.7480000257492065},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"counterfactual reasoning","score":0.6859999895095825},{"id":"https://openalex.org/keywords/hypothesis-rejection","display_name":"hypothesis rejection","score":0.6399999856948853},{"id":"https://openalex.org/keywords/hallucinations","display_name":"hallucinations","score":0.5569999814033508},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.5120000243186951},{"id":"https://openalex.org/keywords/contrastive-decoding","display_name":"contrastive decoding","score":0.800000011920929}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.8539000153541565},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7486000061035156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6674000024795532},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6003999710083008},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5454999804496765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5131999850273132},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5011000037193298},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4666000008583069},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4122999906539917},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38839998841285706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37959998846054077},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C3017944768","wikidata":"https://www.wikidata.org/wiki/Q1450463","display_name":"Poison control","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.274399995803833},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25949999690055847}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2604.20460","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.20460","pdf_url":"https://arxiv.org/pdf/2604.20460","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2604.20460","doi":"https://doi.org/10.48550/arxiv.2604.20460","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.20460","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":"pmh:oai:arXiv.org:2604.20460","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.20460","pdf_url":"https://arxiv.org/pdf/2604.20460","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7155367461.pdf","grobid_xml":"https://content.openalex.org/works/W7155367461.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W3034188691","https://openalex.org/W3106534186","https://openalex.org/W4327810158","https://openalex.org/W4387113775","https://openalex.org/W4387634829","https://openalex.org/W4393148430","https://openalex.org/W4396818380","https://openalex.org/W4400377744","https://openalex.org/W4402670785","https://openalex.org/W4402671548","https://openalex.org/W4402753774","https://openalex.org/W4403784016","https://openalex.org/W4403843558","https://openalex.org/W4404820176","https://openalex.org/W4404988057","https://openalex.org/W4405956131","https://openalex.org/W4406191642","https://openalex.org/W4406780478","https://openalex.org/W4407794264","https://openalex.org/W4409046497","https://openalex.org/W4413144862","https://openalex.org/W4415085804","https://openalex.org/W4416780398","https://openalex.org/W4417097912","https://openalex.org/W6910611565","https://openalex.org/W6948369276","https://openalex.org/W7077911270","https://openalex.org/W7151802991"],"related_works":["https://openalex.org/W7166688180","https://openalex.org/W7140079818","https://openalex.org/W4399399458","https://openalex.org/W7214680184","https://openalex.org/W4405033940","https://openalex.org/W7131398271","https://openalex.org/W7220710607","https://openalex.org/W4287251888","https://openalex.org/W3141656712","https://openalex.org/W7106807532"],"abstract_inverted_index":{"Safety-critical":[0],"traffic":[1],"reasoning":[2],"requires":[3],"contrastive":[4,106,121,142],"consistency:":[5],"models":[6],"must":[7],"detect":[8],"true":[9],"hazards":[10],"when":[11],"an":[12],"accident":[13,37],"occurs,":[14],"and":[15,39,63,77,89,96,104,141],"reliably":[16],"reject":[17],"plausible-but-false":[18],"hypotheses":[19],"under":[20],"near-identical":[21],"counterfactual":[22,41],"scenes.":[23],"We":[24],"present":[25],"CCTVBench,":[26],"a":[27,53,94,113,120,125],"Contrastive":[28],"Consistency":[29],"Traffic":[30],"VideoQA":[31],"Benchmark":[32],"built":[33],"on":[34],"paired":[35],"real":[36],"videos":[38],"world-model-generated":[40],"counterparts,":[42],"together":[43],"with":[44,108],"minimally":[45],"different,":[46],"mutually":[47],"exclusive":[48,127],"hypothesis":[49],"questions.":[50],"CCTVBench":[51],"enforces":[52],"single":[54],"structured":[55],"decision":[56],"pattern":[57],"over":[58],"each":[59],"video":[60,82,91,129],"question":[61,84],"quadruple":[62],"provides":[64],"actionable":[65],"diagnostics":[66],"that":[67],"decompose":[68],"failures":[69],"into":[70],"positive":[71,73],"omission,":[72],"swap,":[74],"negative":[75],"hallucination,":[76],"mutual-exclusivity":[78],"violation,":[79],"while":[80],"separating":[81],"versus":[83],"consistency.":[85,143],"Experiments":[86],"across":[87],"open-source":[88],"proprietary":[90],"LLMs":[92],"reveal":[93],"large":[95],"persistent":[97],"gap":[98],"between":[99],"standard":[100],"per-instance":[101],"QA":[102,140],"metrics":[103],"quadruple-level":[105],"consistency,":[107],"unreliable":[109],"none-of-the-above":[110],"rejection":[111],"as":[112,130],"key":[114],"bottleneck.":[115],"Finally,":[116],"we":[117],"introduce":[118],"C-TCD,":[119],"decoding":[122],"approach":[123],"leveraging":[124],"semantically":[126],"counterpart":[128],"the":[131],"contrast":[132],"input":[133],"at":[134],"inference":[135],"time,":[136],"improving":[137],"both":[138],"instance-level":[139]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-04-24T00:00:00"}