{"id":"https://openalex.org/W4411553057","doi":"https://doi.org/10.1145/3733566.3734429","title":"SafeDriveQA: Benchmarking Vision Language Model for Safe Driving Assessment","display_name":"SafeDriveQA: Benchmarking Vision Language Model for Safe Driving Assessment","publication_year":2025,"publication_date":"2025-06-23","ids":{"openalex":"https://openalex.org/W4411553057","doi":"https://doi.org/10.1145/3733566.3734429"},"language":"en","primary_location":{"id":"doi:10.1145/3733566.3734429","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3733566.3734429","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th Workshop on Intelligent Cross-Data Analysis and Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3733566.3734429","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026740218","display_name":"Satoshi Yamazaki","orcid":"https://orcid.org/0000-0002-4673-6924"},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Satoshi Yamazaki","raw_affiliation_strings":["NEC Corporation, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-4673-6924","affiliations":[{"raw_affiliation_string":"NEC Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I118347220"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009387675","display_name":"Michiaki Inoue","orcid":"https://orcid.org/0000-0002-5715-2123"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michiaki Inoue","raw_affiliation_strings":["NEC Solution Innovators, Ltd., Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5715-2123","affiliations":[{"raw_affiliation_string":"NEC Solution Innovators, Ltd., Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004684980","display_name":"Mika Sakuma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mika Sakuma","raw_affiliation_strings":["NEC Solution Innovators, Ltd., Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0007-2202-8388","affiliations":[{"raw_affiliation_string":"NEC Solution Innovators, Ltd., Tokyo, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Takahiro Kimoto","orcid":"https://orcid.org/0009-0006-5073-2631"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takahiro Kimoto","raw_affiliation_strings":["NEC Solution Innovators, Ltd., Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0006-5073-2631","affiliations":[{"raw_affiliation_string":"NEC Solution Innovators, Ltd., Tokyo, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5026740218"],"corresponding_institution_ids":["https://openalex.org/I118347220"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11817952,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"27","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9994000196456909,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9994000196456909,"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":0.9951000213623047,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9932000041007996,"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/benchmarking","display_name":"Benchmarking","score":0.8597747087478638},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7014569044113159},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.374967485666275},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.07105875015258789}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8597747087478638},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7014569044113159},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.374967485666275},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.07105875015258789},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3733566.3734429","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3733566.3734429","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th Workshop on Intelligent Cross-Data Analysis and Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3733566.3734429","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3733566.3734429","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th Workshop on Intelligent Cross-Data Analysis and 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/W1985212407","https://openalex.org/W2120346558","https://openalex.org/W2768556371","https://openalex.org/W2885138528","https://openalex.org/W2945911734","https://openalex.org/W2955488403","https://openalex.org/W2991484432","https://openalex.org/W3118635606","https://openalex.org/W3212899624","https://openalex.org/W4283322404","https://openalex.org/W4319300501","https://openalex.org/W4386071839","https://openalex.org/W4393148430","https://openalex.org/W4399564091"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"SafeDriveQA,":[3],"an":[4],"evaluation":[5,100],"benchmark":[6],"utilizing":[7],"synthetic":[8],"driving":[9,21,25,53,84,174],"videos":[10,76,86],"toward":[11],"developing":[12],"a":[13,40,43,129,135],"vision":[14],"language":[15],"model":[16],"(VLM)":[17],"for":[18,172],"automated":[19,173],"safe":[20,24,52],"assessment.":[22],"Defining":[23],"criteria":[26],"based":[27],"on":[28,66,82,183],"the":[29,69,83,88,92,96,108,114,119,139,152,157,163],"ego":[30,93,158],"vehicle":[31],"speed":[32],"and":[33,95,160,176],"distance":[34,89],"from":[35],"surrounding":[36,79,161],"objects,":[37,162],"we":[38,72],"constructs":[39],"dataset":[41],"containing":[42],"question":[44,136,149,185],"answering":[45],"task":[46],"(QA)":[47],"that":[48,61,126,168],"assesses":[49],"compliance":[50],"with":[51,107],"criteria.":[54],"To":[55],"cover":[56],"scenarios":[57],"of":[58,118,132,143],"traffic":[59],"violations":[60],"are":[62,181],"difficult":[63],"to":[64,112],"capture":[65],"video":[67],"in":[68,134,147,179],"real":[70],"world,":[71],"synthetically":[73],"create":[74],"corresponding":[75],"by":[77],"placing":[78],"object":[80],"images":[81],"background":[85],"considering":[87],"relationship":[90],"between":[91,156],"car":[94,159],"placed":[97],"objects.":[98,145],"The":[99,122],"experiment":[101],"using":[102],"SafeDriveQA":[103],"has":[104],"been":[105],"conducted":[106],"commercial":[109],"VLM,":[110],"GPT-4o":[111,127],"demonstrate":[113],"safety":[115],"assessment":[116],"capability":[117],"state-of-the-art":[120],"VLM.":[121],"experimental":[123],"results":[124],"show":[125],"achieves":[128],"high":[130],"accuracy":[131,164,180],"73.6%":[133],"category":[137,150],"asking":[138],"presence":[140],"or":[141],"absence":[142],"target":[144],"However,":[146],"another":[148],"assessing":[151],"3D":[153],"spatial":[154],"relationships":[155],"becomes":[165],"60%,":[166],"indicating":[167],"it":[169],"is":[170],"insufficient":[171],"assessment,":[175],"further":[177],"improvements":[178],"necessary":[182],"this":[184],"category.":[186]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}