{"id":"https://openalex.org/W4412877035","doi":"https://doi.org/10.1145/3711896.3737396","title":"Are Vision LLMs Road-Ready? A Comprehensive Benchmark for Safety-Critical Driving Video Understanding","display_name":"Are Vision LLMs Road-Ready? A Comprehensive Benchmark for Safety-Critical Driving Video Understanding","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4412877035","doi":"https://doi.org/10.1145/3711896.3737396"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3737396","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737396","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737396","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 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737396","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013412391","display_name":"Tong Zeng","orcid":"https://orcid.org/0000-0002-5533-8506"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tong Zeng","raw_affiliation_strings":["Computer Science, Virginia Polytechnic Institute and State University, Blacksburg, VA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5533-8506","affiliations":[{"raw_affiliation_string":"Computer Science, Virginia Polytechnic Institute and State University, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101703933","display_name":"Longfeng Wu","orcid":"https://orcid.org/0000-0001-7422-4398"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Longfeng Wu","raw_affiliation_strings":["Computer Science, Virginia Polytechnic Institute and State University, Blacksburg, VA, USA"],"raw_orcid":"https://orcid.org/0000-0001-7422-4398","affiliations":[{"raw_affiliation_string":"Computer Science, Virginia Polytechnic Institute and State University, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014944362","display_name":"Liang Shi","orcid":"https://orcid.org/0000-0002-9308-333X"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liang Shi","raw_affiliation_strings":["Statistics, Virginia Polytechnic Institute and State University, Blacksburg, VA, USA and Virginia Tech Transportation Institute, Virginia Polytechnic Institute and State University, Blacksburg, VA, USA"],"raw_orcid":"https://orcid.org/0000-0002-9308-333X","affiliations":[{"raw_affiliation_string":"Statistics, Virginia Polytechnic Institute and State University, Blacksburg, VA, USA and Virginia Tech Transportation Institute, Virginia Polytechnic Institute and State University, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022696348","display_name":"Dawei Zhou","orcid":"https://orcid.org/0000-0002-7065-2990"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dawei Zhou","raw_affiliation_strings":["Computer Science, Virginia Polytechnic Institute and State University, Blacksburg, VA, USA"],"raw_orcid":"https://orcid.org/0000-0002-7065-2990","affiliations":[{"raw_affiliation_string":"Computer Science, Virginia Polytechnic Institute and State University, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067896213","display_name":"Feng Guo","orcid":"https://orcid.org/0000-0002-2572-481X"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feng Guo","raw_affiliation_strings":["Statistics, Virginia Polytechnic Institute and State University, Blacksburg, VA, USA and Virginia Tech Transportation Institute, Virginia Polytechnic Institute and State University, Blacksburg, VA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2572-481X","affiliations":[{"raw_affiliation_string":"Statistics, Virginia Polytechnic Institute and State University, Blacksburg, VA, USA and Virginia Tech Transportation Institute, Virginia Polytechnic Institute and State University, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5013412391"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":4.533,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.94963338,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5972","last_page":"5983"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9998000264167786,"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":0.9988999962806702,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7744204998016357},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5349249839782715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3421560525894165},{"id":"https://openalex.org/keywords/transport-engineering","display_name":"Transport engineering","score":0.3366515040397644},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.22326558828353882},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.19967061281204224},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.15768137574195862}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7744204998016357},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5349249839782715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3421560525894165},{"id":"https://openalex.org/C22212356","wikidata":"https://www.wikidata.org/wiki/Q775325","display_name":"Transport engineering","level":1,"score":0.3366515040397644},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.22326558828353882},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.19967061281204224},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.15768137574195862}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3711896.3737396","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737396","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737396","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 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/137724","is_oa":false,"landing_page_url":"https://hdl.handle.net/10919/137724","pdf_url":null,"source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1145/3711896.3737396","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737396","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737396","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 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2291474081","display_name":"Collaborative Research: SCH: CLINICAL ADAPTIVE PERFORMANCE ENHANCEMENT THROUGH HUMAN-AI TEAMING (CAPE-HAT)","funder_award_id":"2406439","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4150318782","display_name":null,"funder_award_id":"17STCIN00001","funder_id":"https://openalex.org/F4320306110","funder_display_name":"U.S. Department of Homeland Security"},{"id":"https://openalex.org/G6111889511","display_name":"CAREER: Long-Tailed Learning in the Open and Dynamic World: Theories, Algorithms, and Applications","funder_award_id":"2339989","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6584218474","display_name":null,"funder_award_id":"HR00112490370","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306110","display_name":"U.S. Department of Homeland Security","ror":"https://ror.org/00jyr0d86"},{"id":"https://openalex.org/F4320307791","display_name":"Cisco Systems","ror":"https://ror.org/03yt1ez60"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412877035.pdf","grobid_xml":"https://content.openalex.org/works/W4412877035.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2294494937","https://openalex.org/W2584524738","https://openalex.org/W2885138528","https://openalex.org/W3035172746","https://openalex.org/W3035292170","https://openalex.org/W4319300501","https://openalex.org/W4382173325","https://openalex.org/W4385568413","https://openalex.org/W4390873312","https://openalex.org/W4391876619","https://openalex.org/W4393148430","https://openalex.org/W4394596424","https://openalex.org/W4401386967","https://openalex.org/W4401863605","https://openalex.org/W4402727142","https://openalex.org/W4402917033","https://openalex.org/W4403002096","https://openalex.org/W4403081466","https://openalex.org/W4403842289","https://openalex.org/W4403843558","https://openalex.org/W4409917521","https://openalex.org/W4410088846","https://openalex.org/W6600669965","https://openalex.org/W6602641848","https://openalex.org/W6604285789","https://openalex.org/W6697176655"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526"],"abstract_inverted_index":{"Vision":[0],"Large":[1],"Language":[2],"Models":[3],"(VLLMs)":[4],"have":[5],"demonstrated":[6],"impressive":[7],"capabilities":[8,118],"in":[9,23,39,58,75,96,119,147],"general":[10],"visual":[11,18],"tasks":[12],"such":[13],"as":[14],"image":[15],"captioning":[16],"and":[17,121],"question":[19],"answering.However,":[20],"their":[21],"effectiveness":[22],"specialized,":[24],"safety-critical":[25,59,77],"domains":[26],"like":[27],"autonomous":[28],"driving":[29,33,50,78,93,100,150],"remains":[30],"largely":[31],"unexplored.Autonomous":[32],"systems":[34],"require":[35],"sophisticated":[36],"scene":[37],"understanding":[38,76,148],"complex":[40,149],"environments,":[41],"yet":[42],"existing":[43],"multimodal":[44],"benchmarks":[45],"primarily":[46],"focus":[47],"on":[48,123],"normal":[49],"conditions,":[51],"failing":[52],"to":[53,69,130,169,178],"adequately":[54],"assess":[55],"VLLMs'":[56,117],"performance":[57,72,135],"scenarios.To":[60,151],"address":[61],"this,":[62],"we":[63,154],"introduce":[64],"DVBench-a":[65],"pioneering":[66],"benchmark":[67],"designed":[68],"evaluate":[70],"the":[71],"of":[73,116,176],"VLLMs":[74],"videos.Built":[79],"around":[80],"a":[81,113],"hierarchical":[82],"ability":[83],"taxonomy":[84],"that":[85],"aligns":[86],"with":[87,107,137,173],"widely":[88],"adopted":[89],"frameworks":[90],"for":[91],"describing":[92],"scenarios":[94],"used":[95],"assessing":[97],"highly":[98],"automated":[99],"systems,":[101],"DVBench":[102],"features":[103],"10,000":[104],"multiple-choice":[105],"questions":[106],"human-annotated":[108],"ground-truth":[109],"answers":[110],",":[111],"enabling":[112],"comprehensive":[114],"evaluation":[115],"perception":[120],"reasoning.Experiments":[122],"14":[124],"state-of-the-art":[125],"VLLMs,":[126],"ranging":[127,166],"from":[128,161,167],"0.5B":[129],"72B":[131],"parameters,":[132],"reveal":[133],"significant":[134],"gaps,":[136],"no":[138],"model":[139],"achieving":[140,163],"over":[141],"40%":[142],"accuracy,":[143],"highlighting":[144],"critical":[145],"limitations":[146],"probe":[152],"adaptability,":[153],"fine-tuned":[155],"selected":[156],"models":[157],"using":[158],"domain-specific":[159],"data":[160],"DVBench,":[162],"accuracy":[164],"gains":[165],"5.24":[168],"10.94":[170],"percentage":[171],"points,":[172],"relative":[174],"improvements":[175],"up":[177],"43.59%.This":[179],"improvement":[180],"underscores":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}