{"id":"https://openalex.org/W4408696909","doi":"https://doi.org/10.1109/itsc58415.2024.10920066","title":"ContextVLM: Zero-Shot and Few-Shot Context Understanding for Autonomous Driving Using Vision Language Models","display_name":"ContextVLM: Zero-Shot and Few-Shot Context Understanding for Autonomous Driving Using Vision Language Models","publication_year":2024,"publication_date":"2024-09-24","ids":{"openalex":"https://openalex.org/W4408696909","doi":"https://doi.org/10.1109/itsc58415.2024.10920066"},"language":"en","primary_location":{"id":"doi:10.1109/itsc58415.2024.10920066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc58415.2024.10920066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092850531","display_name":"Shounak Sural","orcid":"https://orcid.org/0009-0007-6537-8716"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shounak Sural","raw_affiliation_strings":["Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,PA,USA,15213"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,PA,USA,15213","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043974480","display_name":"Naren Naren","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naren","raw_affiliation_strings":["Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,PA,USA,15213"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,PA,USA,15213","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104053889","display_name":"Ragunathan Rajkumar","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ragunathan Raj Rajkumar","raw_affiliation_strings":["Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,PA,USA,15213"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,PA,USA,15213","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5092850531"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":1.7877,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.8700216,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"468","last_page":"475"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9940000176429749,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9921000003814697,"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/shot","display_name":"Shot (pellet)","score":0.9179490208625793},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.6679250597953796},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6544454097747803},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6187775135040283},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5113856196403503},{"id":"https://openalex.org/keywords/single-shot","display_name":"Single shot","score":0.4739770293235779},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44935041666030884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4058644771575928},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.20496687293052673},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1426049768924713},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11787942051887512}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.9179490208625793},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.6679250597953796},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6544454097747803},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6187775135040283},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5113856196403503},{"id":"https://openalex.org/C3019835501","wikidata":"https://www.wikidata.org/wiki/Q1310130","display_name":"Single shot","level":2,"score":0.4739770293235779},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44935041666030884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4058644771575928},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.20496687293052673},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1426049768924713},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11787942051887512},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc58415.2024.10920066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc58415.2024.10920066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306108","display_name":"U.S. Department of Transportation","ror":"https://ror.org/02xfw2e90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2150066425","https://openalex.org/W2559264300","https://openalex.org/W2560730294","https://openalex.org/W2986052321","https://openalex.org/W2991485606","https://openalex.org/W3035574168","https://openalex.org/W3198377975","https://openalex.org/W3209100204","https://openalex.org/W4200601092","https://openalex.org/W4226119939","https://openalex.org/W4283395662","https://openalex.org/W4306147865","https://openalex.org/W4327692895","https://openalex.org/W4390872108","https://openalex.org/W4391769656","https://openalex.org/W4394862623","https://openalex.org/W4400650188","https://openalex.org/W6789753369","https://openalex.org/W6791353385","https://openalex.org/W6851592950","https://openalex.org/W6859341508","https://openalex.org/W6871048285"],"related_works":["https://openalex.org/W3142396426","https://openalex.org/W2471333042","https://openalex.org/W2497720472","https://openalex.org/W4292659306","https://openalex.org/W4396643691","https://openalex.org/W4404739899","https://openalex.org/W146529714","https://openalex.org/W4402383816","https://openalex.org/W2316500695","https://openalex.org/W1999226266"],"abstract_inverted_index":{"In":[0,82],"recent":[1],"years,":[2],"there":[3],"has":[4],"been":[5,27],"a":[6,35,112,138,166,172,212,224],"notable":[7],"increase":[8],"in":[9,21,29,57,78,209],"the":[10,30,72,76,90,130],"development":[11],"of":[12,75,92,114,168,191,200,226],"autonomous":[13],"vehicle":[14],"(AV)":[15],"technologies":[16],"aimed":[17],"at":[18],"improving":[19],"safety":[20],"transportation":[22],"systems.":[23],"While":[24],"AVs":[25,39],"have":[26],"deployed":[28],"real-world":[31],"to":[32,40,62,100,132,165,180],"some":[33],"extent,":[34],"full-scale":[36],"deployment":[37],"requires":[38],"robustly":[41],"navigate":[42],"through":[43],"challenges":[44],"like":[45],"heavy":[46],"rain,":[47],"snow,":[48],"low":[49],"lighting,":[50,116],"construction":[51],"zones":[52],"and":[53,118,185],"GPS":[54],"signal":[55],"loss":[56],"tunnels.":[58],"To":[59],"be":[60,125],"able":[61],"handle":[63],"these":[64],"specific":[65],"challenges,":[66],"an":[67,98,122,153,198,221],"AV":[68,99,123,222],"must":[69,124],"reliably":[70,192],"recognize":[71,133],"physical":[73],"attributes":[74,96],"environment":[77],"which":[79],"it":[80],"operates.":[81],"this":[83],"paper,":[84],"we":[85,106,136,170],"define":[86,107],"context":[87,139],"recognition":[88,140],"as":[89],"task":[91],"accurately":[93],"identifying":[94],"environmental":[95,109,134],"for":[97,152],"appropriately":[101],"deal":[102],"with":[103,144,197,223],"them.":[104],"Specifically,":[105],"24":[108],"contexts":[110,182,196],"capturing":[111],"variety":[113,167],"weather,":[115],"traffic":[117],"road":[119],"conditions":[120],"that":[121,176],"aware":[126],"of.":[127],"Motivated":[128],"by":[129],"need":[131],"contexts,":[135,169],"create":[137],"dataset":[141],"called":[142,174],"DrivingContexts":[143],"more":[145,201],"than":[146,202],"1.6":[147],"million":[148],"context-query":[149],"pairs":[150],"relevant":[151,194],"AV.":[154],"Since":[155],"traditional":[156],"supervised":[157],"computer":[158],"vision":[159],"approaches":[160],"do":[161],"not":[162],"scale":[163],"well":[164],"propose":[171],"framework":[173],"ContextVLM":[175,188],"uses":[177],"vision-language":[178],"models":[179],"detect":[181],"using":[183],"zero-":[184],"few-shot":[186],"approaches.":[187],"is":[189],"capable":[190],"detecting":[193],"driving":[195],"accuracy":[199],"95%":[203],"on":[204,211,220],"our":[205],"dataset,":[206],"while":[207],"running":[208],"real-time":[210],"4GB":[213],"Nvidia":[214],"GeForce":[215],"GTX":[216],"1050":[217],"Ti":[218],"GPU":[219],"latency":[225],"10.5":[227],"ms":[228],"per":[229],"query.":[230]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}