{"id":"https://openalex.org/W7138477525","doi":"https://doi.org/10.1609/aaai.v40i7.37441","title":"STRIDE-QA: Visual Question Answering Dataset for Spatiotemporal Reasoning in Urban Driving Scenes","display_name":"STRIDE-QA: Visual Question Answering Dataset for Spatiotemporal Reasoning in Urban Driving Scenes","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138477525","doi":"https://doi.org/10.1609/aaai.v40i7.37441"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i7.37441","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37441","pdf_url":null,"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://doi.org/10.1609/aaai.v40i7.37441","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028611774","display_name":"Keishi Ishihara","orcid":null},"institutions":[{"id":"https://openalex.org/I125680101","display_name":"Turing Institute","ror":"https://ror.org/02x2mw849","country_code":"GB","type":"facility","lineage":["https://openalex.org/I125680101"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Keishi Ishihara","raw_affiliation_strings":["Turing Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Turing Inc","institution_ids":["https://openalex.org/I125680101"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129701017","display_name":"Kento Sasaki","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kento Sasaki","raw_affiliation_strings":["Turing Inc.\nUniversity of Tsukuba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Turing Inc.\nUniversity of Tsukuba","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129680687","display_name":"Tsubasa Takahashi","orcid":null},"institutions":[{"id":"https://openalex.org/I125680101","display_name":"Turing Institute","ror":"https://ror.org/02x2mw849","country_code":"GB","type":"facility","lineage":["https://openalex.org/I125680101"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tsubasa Takahashi","raw_affiliation_strings":["Turing Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Turing Inc","institution_ids":["https://openalex.org/I125680101"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002464121","display_name":"Daiki Shiono","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093896","display_name":"Tohoku University Hospital","ror":"https://ror.org/00kcd6x60","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I4210093896"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daiki Shiono","raw_affiliation_strings":["Turing Inc.\nTohoku University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Turing Inc.\nTohoku University","institution_ids":["https://openalex.org/I4210093896"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129697143","display_name":"Yu Yamaguchi","orcid":null},"institutions":[{"id":"https://openalex.org/I125680101","display_name":"Turing Institute","ror":"https://ror.org/02x2mw849","country_code":"GB","type":"facility","lineage":["https://openalex.org/I125680101"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yu Yamaguchi","raw_affiliation_strings":["Turing Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Turing Inc","institution_ids":["https://openalex.org/I125680101"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":29.4755,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.9985755,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"40","issue":"7","first_page":"5257","last_page":"5266"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.992900013923645,"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":0.992900013923645,"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":0.0019000000320374966,"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":0.0006000000284984708,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.6452999711036682},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.6055999994277954},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5577999949455261},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5529000163078308},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5357000231742859},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.47859999537467957},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.4361000061035156},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.36419999599456787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7135000228881836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6517000198364258},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6452999711036682},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6055999994277954},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5577999949455261},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5529000163078308},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5357000231742859},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.47859999537467957},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.4361000061035156},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4027999937534332},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.32739999890327454},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i7.37441","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37441","pdf_url":null,"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"},{"id":"pmh:oai:ojs.aaai.org:article/37441","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37441","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i7.37441","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37441","pdf_url":null,"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":[{"score":0.7559292912483215,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"(VLMs)":[2],"have":[3],"been":[4],"applied":[5],"to":[6,9,31,170],"autonomous":[7,189],"driving":[8,66],"support":[10],"decision-making":[11],"in":[12,68,84,159,165],"complex":[13],"real-world":[14],"scenarios.":[15],"However,":[16],"their":[17],"training":[18],"on":[19,143,150],"static,":[20],"web-sourced":[21],"image-text":[22],"pairs":[23,91],"fundamentally":[24],"limits":[25],"the":[26,77,111],"precise":[27],"spatiotemporal":[28,82],"reasoning":[29,55,83,119],"required":[30],"understand":[32],"and":[33,72,108,117,129,162],"predict":[34],"dynamic":[35],"traffic":[36],"scenes.":[37],"We":[38],"address":[39],"this":[40],"critical":[41],"gap":[42],"with":[43,140],"STRIDE-QA,":[44],"a":[45,179],"large-scale":[46],"visual":[47],"question":[48],"answering":[49],"(VQA)":[50],"dataset":[51,80,112],"for":[52,81,182,187],"physically":[53],"grounded":[54],"from":[56,61,173],"an":[57],"ego-centric":[58,118],"perspective.":[59],"Constructed":[60],"100":[62],"hours":[63],"of":[64],"multi-sensor":[65],"data":[67],"Tokyo,":[69],"capturing":[70],"diverse":[71],"challenging":[73],"conditions,":[74],"STRIDE-QA":[75,151,177],"is":[76],"largest":[78],"VQA":[79],"urban":[85],"driving,":[86],"offering":[87],"16":[88],"M":[89],"QA":[90,123],"over":[92],"270":[93],"K":[94],"frames.":[95],"Grounded":[96],"by":[97],"dense,":[98],"automatically":[99],"generated":[100],"annotations":[101],"including":[102],"3D":[103],"bounding":[104],"boxes,":[105],"segmentation":[106],"masks,":[107],"multi-object":[109],"tracks,":[110],"uniquely":[113],"supports":[114],"both":[115],"object-centric":[116],"through":[120],"three":[121],"novel":[122],"tasks":[124],"that":[125,135],"require":[126],"spatial":[127,160],"localization":[128,161],"temporal":[130],"prediction.":[131],"Our":[132],"benchmarks":[133],"demonstrate":[134],"existing":[136],"VLMs":[137,148,186],"struggle":[138],"significantly,":[139],"near-zero":[141,171],"scores":[142,172],"prediction":[144],"consistency.":[145],"In":[146],"contrast,":[147],"fine-tuned":[149],"exhibit":[152],"dramatic":[153],"performance":[154],"gains,":[155],"achieving":[156],"55%":[157],"success":[158],"28%":[163],"consistency":[164],"future":[166],"motion":[167],"prediction,":[168],"compared":[169],"general-purpose":[174],"VLMs.":[175],"Therefore,":[176],"establishes":[178],"comprehensive":[180],"foundation":[181],"developing":[183],"more":[184],"reliable":[185],"safety-critical":[188],"systems.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}