{"id":"https://openalex.org/W4416062092","doi":"https://doi.org/10.1109/iccv51701.2025.00520","title":"MCAM: Multimodal Causal Analysis Model for Ego-Vehicle-Level Driving Video Understanding","display_name":"MCAM: Multimodal Causal Analysis Model for Ego-Vehicle-Level Driving Video Understanding","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416062092","doi":"https://doi.org/10.1109/iccv51701.2025.00520"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00520","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.06072","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Tongtong Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]},{"id":"https://openalex.org/I168337820","display_name":"Chongqing University of Science and Technology","ror":"https://ror.org/03n3v6d52","country_code":"CN","type":"education","lineage":["https://openalex.org/I168337820"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongtong Cheng","raw_affiliation_strings":["Chongqing University,Department of Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University,Department of Computer Science,China","institution_ids":["https://openalex.org/I158842170","https://openalex.org/I168337820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030391400","display_name":"Raymond Li","orcid":"https://orcid.org/0000-0002-8868-7104"},"institutions":[{"id":"https://openalex.org/I4210134810","display_name":"Chongqing Institute of Geology and Mineral Resources","ror":"https://ror.org/03epp6210","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210134810"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongzhen Li","raw_affiliation_strings":["National Elite Institute of Engineering, Chongqing University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Elite Institute of Engineering, Chongqing University,China","institution_ids":["https://openalex.org/I4210134810"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yixin Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]},{"id":"https://openalex.org/I168337820","display_name":"Chongqing University of Science and Technology","ror":"https://ror.org/03n3v6d52","country_code":"CN","type":"education","lineage":["https://openalex.org/I168337820"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixin Xiong","raw_affiliation_strings":["Chongqing University,Department of Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University,Department of Computer Science,China","institution_ids":["https://openalex.org/I158842170","https://openalex.org/I168337820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042550706","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0002-1772-0915"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]},{"id":"https://openalex.org/I168337820","display_name":"Chongqing University of Science and Technology","ror":"https://ror.org/03n3v6d52","country_code":"CN","type":"education","lineage":["https://openalex.org/I168337820"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Zhang","raw_affiliation_strings":["Chongqing University,Department of Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University,Department of Computer Science,China","institution_ids":["https://openalex.org/I158842170","https://openalex.org/I168337820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378656","display_name":"Jing Wang","orcid":"https://orcid.org/0000-0003-1580-1356"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Wang","raw_affiliation_strings":["College of Computer Science and Technology, National University of Deffense Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Deffense Technology,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100399797","display_name":"Kai Liu","orcid":"https://orcid.org/0000-0001-5865-7724"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]},{"id":"https://openalex.org/I168337820","display_name":"Chongqing University of Science and Technology","ror":"https://ror.org/03n3v6d52","country_code":"CN","type":"education","lineage":["https://openalex.org/I168337820"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Liu","raw_affiliation_strings":["Chongqing University,Department of Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University,Department of Computer Science,China","institution_ids":["https://openalex.org/I158842170","https://openalex.org/I168337820"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"5479","last_page":"5489"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7943999767303467,"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":0.7943999767303467,"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":0.03819999843835831,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.02759999968111515,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.8087000250816345},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.6541000008583069},{"id":"https://openalex.org/keywords/causal-reasoning","display_name":"Causal reasoning","score":0.5860000252723694},{"id":"https://openalex.org/keywords/causality","display_name":"Causality (physics)","score":0.525600016117096},{"id":"https://openalex.org/keywords/causal-analysis","display_name":"Causal analysis","score":0.4546999931335449},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43050000071525574},{"id":"https://openalex.org/keywords/causal-inference","display_name":"Causal inference","score":0.3912000060081482},{"id":"https://openalex.org/keywords/directed-acyclic-graph","display_name":"Directed acyclic graph","score":0.3849000036716461},{"id":"https://openalex.org/keywords/causal-structure","display_name":"Causal structure","score":0.3716999888420105}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.8087000250816345},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7131999731063843},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.6541000008583069},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.5860000252723694},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.525600016117096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5249999761581421},{"id":"https://openalex.org/C2987525970","wikidata":"https://www.wikidata.org/wiki/Q96374569","display_name":"Causal analysis","level":2,"score":0.4546999931335449},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43050000071525574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40529999136924744},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C74197172","wikidata":"https://www.wikidata.org/wiki/Q1195339","display_name":"Directed acyclic graph","level":2,"score":0.3849000036716461},{"id":"https://openalex.org/C163504300","wikidata":"https://www.wikidata.org/wiki/Q2364925","display_name":"Causal structure","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.34040001034736633},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3375000059604645},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28790000081062317},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2662000060081482},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2531999945640564}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00520","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.06072","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.06072","pdf_url":"https://arxiv.org/pdf/2507.06072","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.06072","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.06072","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.06072","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.06072","pdf_url":"https://arxiv.org/pdf/2507.06072","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1174939727","display_name":null,"funder_award_id":"62472055,62172064","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"driving":[1,10,82,91,146],"behavior":[2],"recognition":[3],"and":[4,31,58,114],"reasoning":[5],"are":[6],"critical":[7,101],"for":[8,144],"autonomous":[9,145],"video":[11,139],"understanding.":[12],"However,":[13],"existing":[14],"methods":[15],"often":[16],"tend":[17],"to":[18,25,68,99],"dig":[19],"out":[20],"the":[21,33,112,129],"shallow":[22],"causal,":[23],"fail":[24],"address":[26],"spurious":[27],"correlations":[28],"across":[29],"modalities,":[30],"ignore":[32],"ego-vehicle":[34],"level":[35],"causality":[36],"modeling.":[37],"To":[38],"overcome":[39],"these":[40],"limitations,":[41],"we":[42,62,73,94],"propose":[43],"a":[44,64,75,85,96],"novel":[45],"Multimodal":[46],"Causal":[47],"Analysis":[48],"Model":[49],"(MCAM)":[50],"that":[51,79,118],"constructs":[52],"latent":[53],"causal":[54,76,125,136],"structures":[55],"between":[56],"visual":[57,102],"language":[59],"modalities.":[60],"Firstly,":[61],"design":[63,74],"multi-level":[65],"feature":[66],"extractor":[67],"capture":[69],"long-range":[70],"dependencies.":[71],"Secondly,":[72],"analysis":[77],"module":[78],"dynamically":[80],"models":[81],"scenarios":[83],"using":[84],"directed":[86],"acyclic":[87],"graph":[88],"(DAG)":[89],"of":[90],"states.":[92],"Thirdly,":[93],"utilize":[95],"vision-language":[97],"transformer":[98],"align":[100],"features":[103],"with":[104],"their":[105],"corresponding":[106],"linguistic":[107],"expressions.":[108],"Extensive":[109],"experiments":[110],"on":[111],"BDD-X,":[113],"CoVLA":[115],"datasets":[116],"demonstrate":[117],"MCAM":[119],"achieves":[120],"SOTA":[121],"performance":[122],"in":[123,134],"visual-language":[124],"relationship":[126],"learning.":[127],"Furthermore,":[128],"model":[130],"exhibits":[131],"superior":[132],"capability":[133],"capturing":[135],"characteristics":[137],"within":[138],"sequences,":[140],"showcasing":[141],"its":[142],"effectiveness":[143],"applications.":[147],"The":[148],"code":[149],"is":[150],"available":[151],"at":[152],"https://github.com/SixCorePeach/MCAM.":[153]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}