{"id":"https://openalex.org/W7138096632","doi":"https://doi.org/10.1609/aaai.v40i6.42434","title":"RoadSceneVQA: Benchmarking Visual Question Answering in Roadside Perception Systems for Intelligent Transportation System","display_name":"RoadSceneVQA: Benchmarking Visual Question Answering in Roadside Perception Systems for Intelligent Transportation System","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138096632","doi":"https://doi.org/10.1609/aaai.v40i6.42434"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i6.42434","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42434","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/42434/46395","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://ojs.aaai.org/index.php/AAAI/article/download/42434/46395","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129689336","display_name":"Runwei Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Runwei Guan","raw_affiliation_strings":["Information Hub, The Hong Kong University of Science and Technology (Guangzhou)\nInstitute of Deep Perception Technology, JITRI"],"affiliations":[{"raw_affiliation_string":"Information Hub, The Hong Kong University of Science and Technology (Guangzhou)\nInstitute of Deep Perception Technology, JITRI","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066365804","display_name":"Rongsheng Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongsheng Hu","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129725013","display_name":"Shangshu Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangshu Chen","raw_affiliation_strings":["National Research Center of Cultural Industries, Central China Normal University"],"affiliations":[{"raw_affiliation_string":"National Research Center of Cultural Industries, Central China Normal University","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117113813","display_name":"Ningyuan Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ningyuan Xiao","raw_affiliation_strings":["Information Hub, The Hong Kong University of Science and Technology (Guangzhou)"],"affiliations":[{"raw_affiliation_string":"Information Hub, The Hong Kong University of Science and Technology (Guangzhou)","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129691706","display_name":"Xue Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xue Xia","raw_affiliation_strings":["Information Hub, The Hong Kong University of Science and Technology (Guangzhou)"],"affiliations":[{"raw_affiliation_string":"Information Hub, The Hong Kong University of Science and Technology (Guangzhou)","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129642489","display_name":"Jiayang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiayang Liu","raw_affiliation_strings":["Information Hub, The Hong Kong University of Science and Technology (Guangzhou)"],"affiliations":[{"raw_affiliation_string":"Information Hub, The Hong Kong University of Science and Technology (Guangzhou)","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129724471","display_name":"Beibei Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Beibei Chen","raw_affiliation_strings":["School of Marxism, Jilin University"],"affiliations":[{"raw_affiliation_string":"School of Marxism, Jilin University","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129658157","display_name":"Ziren Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ziren Tang","raw_affiliation_strings":["Information Hub, The Hong Kong University of Science and Technology (Guangzhou)"],"affiliations":[{"raw_affiliation_string":"Information Hub, The Hong Kong University of Science and Technology (Guangzhou)","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104264340","display_name":"Ningwei Ouyang","orcid":null},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ningwei Ouyang","raw_affiliation_strings":["School of Advanced Technology, Xi'an Jiaotong-Liverpool University"],"affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi'an Jiaotong-Liverpool University","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129678323","display_name":"Shaofeng Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shaofeng Liang","raw_affiliation_strings":["Information Hub, The Hong Kong University of Science and Technology (Guangzhou)"],"affiliations":[{"raw_affiliation_string":"Information Hub, The Hong Kong University of Science and Technology (Guangzhou)","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129678213","display_name":"Yuxuan Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuxuan Fan","raw_affiliation_strings":["Information Hub, The Hong Kong University of Science and Technology (Guangzhou)"],"affiliations":[{"raw_affiliation_string":"Information Hub, The Hong Kong University of Science and Technology (Guangzhou)","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129730749","display_name":"Wanjie Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanjie Sun","raw_affiliation_strings":["School of Remote Sensing and Information Engineering, Wuhan University"],"affiliations":[{"raw_affiliation_string":"School of Remote Sensing and Information Engineering, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129642390","display_name":"Yutao Yue","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yutao Yue","raw_affiliation_strings":["Information Hub, The Hong Kong University of Science and Technology (Guangzhou)\nInstitute of Deep Perception Technology, JITRI"],"affiliations":[{"raw_affiliation_string":"Information Hub, The Hong Kong University of Science and Technology (Guangzhou)\nInstitute of Deep Perception Technology, JITRI","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":13,"corresponding_author_ids":["https://openalex.org/A5129689336"],"corresponding_institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40597015,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"6","first_page":"4366","last_page":"4375"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8335999846458435,"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":0.8335999846458435,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.11209999769926071,"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":0.014000000432133675,"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/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.6334999799728394},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6180999875068665},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5974000096321106},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5924999713897705},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5586000084877014},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5060999989509583},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4805000126361847},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.478300005197525},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.42320001125335693},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.41850000619888306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7501000165939331},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.6334999799728394},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6180999875068665},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5974000096321106},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5924999713897705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5819000005722046},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5586000084877014},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5060999989509583},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4805000126361847},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.478300005197525},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4519999921321869},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4359000027179718},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.42320001125335693},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.41850000619888306},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.39340001344680786},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3865000009536743},{"id":"https://openalex.org/C87833898","wikidata":"https://www.wikidata.org/wiki/Q1060280","display_name":"Advanced driver assistance systems","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.36959999799728394},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.3488999903202057},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3481999933719635},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C47796450","wikidata":"https://www.wikidata.org/wiki/Q508378","display_name":"Intelligent transportation system","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31700000166893005},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.29109999537467957},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C9616225","wikidata":"https://www.wikidata.org/wiki/Q3929429","display_name":"Semantic reasoner","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.25459998846054077},{"id":"https://openalex.org/C2985695025","wikidata":"https://www.wikidata.org/wiki/Q4323994","display_name":"Road traffic","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C171018156","wikidata":"https://www.wikidata.org/wiki/Q7370306","display_name":"Rotation formalisms in three dimensions","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i6.42434","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42434","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/42434/46395","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.v40i6.42434","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42434","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/42434/46395","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138096632.pdf","grobid_xml":"https://content.openalex.org/works/W7138096632.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Current":[0],"roadside":[1,45],"perception":[2,181],"systems":[3],"mainly":[4],"focus":[5],"on":[6,154],"instance-level":[7],"perception,":[8],"which":[9],"fall":[10],"short":[11],"in":[12,23,91,178],"enabling":[13],"interaction":[14,73],"via":[15,146],"natural":[16],"language":[17],"and":[18,34,59,72,86,95,129,149,156,168,182],"reasoning":[19,102,166,183],"about":[20],"traffic":[21,60,76,93,180],"behaviors":[22],"context.":[24],"To":[25,98],"bridge":[26],"this":[27],"gap,":[28],"we":[29,110,134],"introduce":[30],"RoadSceneVQA,":[31],"a":[32,116],"large-scale":[33],"richly":[35],"annotated":[36],"visual":[37],"question":[38],"answering":[39],"(VQA)":[40],"dataset":[41,48],"specifically":[42],"tailored":[43],"for":[44],"scenarios.":[46],"The":[47],"comprises":[49],"34,736":[50],"diverse":[51],"QA":[52],"pairs":[53],"collected":[54],"under":[55],"varying":[56],"weather,":[57],"illumination,":[58],"conditions,":[61],"targeting":[62],"not":[63],"only":[64],"object":[65],"attributes":[66],"but":[67],"also":[68],"the":[69,101,136,143,161,172],"intent,":[70],"legality,":[71],"patterns":[74],"of":[75,104],"participants.":[77],"RoadSceneVQA":[78,155],"challenges":[79],"models":[80],"to":[81,141,174],"perform":[82],"both":[83,165],"explicit":[84],"recognition":[85],"implicit":[87],"commonsense":[88],"reasoning,":[89],"grounded":[90],"real-world":[92],"rules":[94],"contextual":[96],"dependencies.":[97],"fully":[99],"exploit":[100],"potential":[103],"Multi-modal":[105],"Large":[106],"Language":[107],"Models":[108],"(MLLMs),":[109],"further":[111],"propose":[112,135],"CogniAnchor":[113],"Fusion":[114],"(CAF),":[115],"vision-language":[117],"fusion":[118],"module":[119],"inspired":[120],"by":[121],"human-like":[122],"scene":[123],"anchoring":[124],"mechanisms.":[125],"CAF":[126],"enables":[127],"precise":[128],"efficient":[130],"cross-modal":[131],"interaction.":[132],"Moreover,":[133],"Assisted":[137],"Decoupled":[138],"Chain-of-Thought":[139],"(AD-CoT)":[140],"enhance":[142],"reasoned":[144],"thinking":[145],"CoT":[147],"prompting":[148],"multi-task":[150],"learning.":[151],"Experimental":[152],"results":[153],"CODA-LM":[157],"benchmark":[158],"show":[159],"that":[160],"pipeline":[162],"consistently":[163],"improves":[164],"accuracy":[167],"computational":[169],"efficiency,":[170],"allowing":[171],"MLLM":[173],"achieve":[175],"state-of-the-art":[176],"performance":[177],"structural":[179],"tasks.":[184]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}