{"id":"https://openalex.org/W4414457909","doi":"https://doi.org/10.1145/3744335.3758495","title":"Understanding Pedestrian Gesture Misrecognition: Insights from Vision-Language Model Reasoning","display_name":"Understanding Pedestrian Gesture Misrecognition: Insights from Vision-Language Model Reasoning","publication_year":2025,"publication_date":"2025-09-22","ids":{"openalex":"https://openalex.org/W4414457909","doi":"https://doi.org/10.1145/3744335.3758495"},"language":"en","primary_location":{"id":"doi:10.1145/3744335.3758495","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3744335.3758495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adjunct Proceedings of the 17th International Conference on Automotive User Interfaces and Interactive Vehicular Applications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.06801","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044409375","display_name":"Tram Thi Minh Tran","orcid":"https://orcid.org/0000-0002-4958-2465"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tram Thi Minh Tran","raw_affiliation_strings":["Design Lab, School of Architecture, Design and Planning, The University of Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4958-2465","affiliations":[{"raw_affiliation_string":"Design Lab, School of Architecture, Design and Planning, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001817278","display_name":"Xinyan Yu","orcid":"https://orcid.org/0000-0001-8299-3381"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xinyan Yu","raw_affiliation_strings":["Design Lab, School of Architecture, Design and Planning, The University of Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8299-3381","affiliations":[{"raw_affiliation_string":"Design Lab, School of Architecture, Design and Planning, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008079113","display_name":"Callum Parker","orcid":"https://orcid.org/0000-0002-2173-9213"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Callum Parker","raw_affiliation_strings":["Design Lab, School of Architecture, Design and Planning, The University of Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-2173-9213","affiliations":[{"raw_affiliation_string":"Design Lab, School of Architecture, Design and Planning, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038732366","display_name":"Julie Stephany Berr\u00edo","orcid":"https://orcid.org/0000-0003-3126-7042"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]},{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Julie Stephany Berr\u00edo Perez","raw_affiliation_strings":["Australian Centre for Field Robotics, The University of Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3126-7042","affiliations":[{"raw_affiliation_string":"Australian Centre for Field Robotics, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602","https://openalex.org/I4210127558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070356056","display_name":"Stewart Worrall","orcid":"https://orcid.org/0000-0001-7940-4742"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]},{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Stewart Worrall","raw_affiliation_strings":["Australian Centre for Field Robotics, The University of Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7940-4742","affiliations":[{"raw_affiliation_string":"Australian Centre for Field Robotics, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602","https://openalex.org/I4210127558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023076293","display_name":"Martin Tomitsch","orcid":"https://orcid.org/0000-0003-1998-2975"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]},{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Martin Tomitsch","raw_affiliation_strings":["Transdisciplinary School, University of Technology Sydney, Sydney, NSW, Australia and Design Lab, School of Architecture, Design and Planning, The University of Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1998-2975","affiliations":[{"raw_affiliation_string":"Transdisciplinary School, University of Technology Sydney, Sydney, NSW, Australia and Design Lab, School of Architecture, Design and Planning, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466","https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":"138","last_page":"144"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11285","display_name":"Hearing Impairment and Communication","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.878000020980835},{"id":"https://openalex.org/keywords/pedestrian","display_name":"Pedestrian","score":0.7585999965667725},{"id":"https://openalex.org/keywords/salience","display_name":"Salience (neuroscience)","score":0.7031999826431274},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4821999967098236},{"id":"https://openalex.org/keywords/wearable-computer","display_name":"Wearable computer","score":0.4627000093460083},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.44040000438690186},{"id":"https://openalex.org/keywords/wearable-technology","display_name":"Wearable technology","score":0.335999995470047}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.878000020980835},{"id":"https://openalex.org/C2777113093","wikidata":"https://www.wikidata.org/wiki/Q221488","display_name":"Pedestrian","level":2,"score":0.7585999965667725},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.7031999826431274},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6819999814033508},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5932999849319458},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4821999967098236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46369999647140503},{"id":"https://openalex.org/C150594956","wikidata":"https://www.wikidata.org/wiki/Q1334829","display_name":"Wearable computer","level":2,"score":0.4627000093460083},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.44040000438690186},{"id":"https://openalex.org/C54290928","wikidata":"https://www.wikidata.org/wiki/Q4845080","display_name":"Wearable technology","level":3,"score":0.335999995470047},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C71611378","wikidata":"https://www.wikidata.org/wiki/Q5165191","display_name":"Contextual design","level":3,"score":0.2971999943256378},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2865000069141388},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.26409998536109924},{"id":"https://openalex.org/C74196892","wikidata":"https://www.wikidata.org/wiki/Q7781188","display_name":"Thematic analysis","level":3,"score":0.2605000138282776},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.25940001010894775}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3744335.3758495","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3744335.3758495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adjunct Proceedings of the 17th International Conference on Automotive User Interfaces and Interactive Vehicular Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.06801","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.06801","pdf_url":"https://arxiv.org/pdf/2508.06801","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.06801","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.06801","pdf_url":"https://arxiv.org/pdf/2508.06801","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/G3364134221","display_name":"Shared-space interactions between people and autonomous vehicles","funder_award_id":"DP220102019","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1541683673","https://openalex.org/W2137409775","https://openalex.org/W2771583656","https://openalex.org/W2807162238","https://openalex.org/W2903870308","https://openalex.org/W3034688679","https://openalex.org/W4296306250","https://openalex.org/W4398184793","https://openalex.org/W4399142101","https://openalex.org/W4399881122","https://openalex.org/W4400729563","https://openalex.org/W4401895018","https://openalex.org/W4402576038","https://openalex.org/W4402753604","https://openalex.org/W4405253513","https://openalex.org/W4408837353","https://openalex.org/W4414198300"],"related_works":[],"abstract_inverted_index":{"Pedestrian":[0],"gestures":[1],"play":[2],"an":[3],"important":[4],"role":[5],"in":[6,10],"traffic":[7],"communication,":[8],"particularly":[9],"interactions":[11],"with":[12,70],"autonomous":[13],"vehicles":[14],"(AVs),":[15],"yet":[16],"their":[17],"subtle,":[18],"ambiguous,":[19],"and":[20,53,93,109,112,124,134,150],"context-dependent":[21],"nature":[22],"poses":[23],"persistent":[24],"challenges":[25,33],"for":[26,101],"machine":[27],"interpretation.":[28],"This":[29,78],"study":[30],"investigates":[31],"these":[32],"by":[34],"using":[35],"GPT-4V,":[36],"a":[37,42,47,60],"vision-language":[38],"model,":[39],"not":[40],"as":[41,46,147],"performance":[43],"benchmark":[44],"but":[45],"diagnostic":[48],"tool":[49],"to":[50,115,138],"reveal":[51],"patterns":[52],"causes":[54],"of":[55,63,73,107],"gesture":[56,87,102],"misrecognition.":[57],"We":[58],"analysed":[59],"public":[61],"dataset":[62],"pedestrian-vehicle":[64],"interactions,":[65],"combining":[66],"manual":[67],"video":[68],"review":[69],"thematic":[71],"analysis":[72],"the":[74,105,132],"model's":[75],"qualitative":[76],"reasoning.":[77],"dual":[79],"approach":[80],"surfaced":[81],"recurring":[82],"factors":[83],"influencing":[84],"misrecognition,":[85],"including":[86,104],"visibility,":[88],"pedestrian":[89],"behaviour,":[90],"interaction":[91],"context,":[92],"environmental":[94],"conditions.":[95],"The":[96],"findings":[97],"suggest":[98],"practical":[99],"considerations":[100],"design,":[103],"value":[106],"salience":[108],"contextual":[110],"redundancy,":[111],"highlight":[113],"opportunities":[114],"improve":[116],"AV":[117],"recognition":[118],"systems":[119],"through":[120],"richer":[121],"context":[122],"modelling":[123],"uncertainty-aware":[125],"interpretations.":[126],"While":[127],"centred":[128],"on":[129],"AV-pedestrian":[130],"interaction,":[131],"method":[133],"insights":[135],"are":[136],"applicable":[137],"other":[139],"domains":[140],"where":[141],"machines":[142],"interpret":[143],"human":[144],"gestures,":[145],"such":[146],"wearable":[148],"AR":[149],"assistive":[151],"technologies.":[152]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
