{"id":"https://openalex.org/W4401416408","doi":"https://doi.org/10.1109/icra57147.2024.10611485","title":"Talk2BEV: Language-enhanced Bird\u2019s-eye View Maps for Autonomous Driving","display_name":"Talk2BEV: Language-enhanced Bird\u2019s-eye View Maps for Autonomous Driving","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401416408","doi":"https://doi.org/10.1109/icra57147.2024.10611485"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10611485","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611485","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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/A5101516181","display_name":"Tushar Choudhary","orcid":"https://orcid.org/0000-0002-9832-1202"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Tushar Choudhary","raw_affiliation_strings":["IIIT Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092130689","display_name":"Vikrant Dewangan","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vikrant Dewangan","raw_affiliation_strings":["IIIT Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013255070","display_name":"Shivam Chandhok","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shivam Chandhok","raw_affiliation_strings":["University of British Columbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093006110","display_name":"Shubham Priyadarshan","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shubham Priyadarshan","raw_affiliation_strings":["IIIT Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060879453","display_name":"Anushka Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anushka Jain","raw_affiliation_strings":["IIIT Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033077069","display_name":"Arun Kumar Singh","orcid":"https://orcid.org/0000-0002-2032-2694"},"institutions":[{"id":"https://openalex.org/I56085075","display_name":"University of Tartu","ror":"https://ror.org/03z77qz90","country_code":"EE","type":"education","lineage":["https://openalex.org/I56085075"]}],"countries":["EE"],"is_corresponding":false,"raw_author_name":"Arun K. Singh","raw_affiliation_strings":["University of Tartu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tartu","institution_ids":["https://openalex.org/I56085075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101988374","display_name":"Siddharth Srivastava","orcid":"https://orcid.org/0000-0003-0388-1790"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siddharth Srivastava","raw_affiliation_strings":["TensorTour Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TensorTour Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047370393","display_name":"Krishna Murthy Jatavallabhula","orcid":"https://orcid.org/0000-0003-4927-3387"},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Krishna Murthy Jatavallabhula","raw_affiliation_strings":["MIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I4210109586"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068014632","display_name":"K. Madhava Krishna","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"K. Madhava Krishna","raw_affiliation_strings":["IIIT Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101516181"],"corresponding_institution_ids":["https://openalex.org/I65181880"],"apc_list":null,"apc_paid":null,"fwci":12.5604,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.99251858,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"16345","last_page":"16352"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9908999800682068,"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":0.968999981880188,"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/computer-science","display_name":"Computer science","score":0.6622599959373474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4219300150871277},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.36632847785949707},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3529972732067108}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6622599959373474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4219300150871277},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36632847785949707},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3529972732067108}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10611485","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611485","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W2340897893","https://openalex.org/W2930283066","https://openalex.org/W2962703144","https://openalex.org/W2965373594","https://openalex.org/W2970603850","https://openalex.org/W3003954087","https://openalex.org/W3035574168","https://openalex.org/W3087858202","https://openalex.org/W3095974555","https://openalex.org/W3104529101","https://openalex.org/W3107521863","https://openalex.org/W3109395584","https://openalex.org/W3140398265","https://openalex.org/W3175234951","https://openalex.org/W3182910454","https://openalex.org/W4214530037","https://openalex.org/W4226326569","https://openalex.org/W4226376247","https://openalex.org/W4307079201","https://openalex.org/W4310629611","https://openalex.org/W4312396550","https://openalex.org/W4312894406","https://openalex.org/W4318718936","https://openalex.org/W4322718191","https://openalex.org/W4366850747","https://openalex.org/W4376312115","https://openalex.org/W4380353763","https://openalex.org/W4382142077","https://openalex.org/W4384918448","https://openalex.org/W4385262477","https://openalex.org/W4385431115","https://openalex.org/W4385473806","https://openalex.org/W4386076180","https://openalex.org/W4386621530","https://openalex.org/W4390137229","https://openalex.org/W4393148430","https://openalex.org/W4395091069","https://openalex.org/W4401414574","https://openalex.org/W4403081466","https://openalex.org/W4403778769","https://openalex.org/W4404788931","https://openalex.org/W6766673545","https://openalex.org/W6774115811","https://openalex.org/W6783441721","https://openalex.org/W6786827990","https://openalex.org/W6811461410","https://openalex.org/W6846989178","https://openalex.org/W6847076894","https://openalex.org/W6849177959","https://openalex.org/W6850625674","https://openalex.org/W6851950068","https://openalex.org/W6852874933","https://openalex.org/W6853116092","https://openalex.org/W6853219587","https://openalex.org/W6854231400","https://openalex.org/W6854308264","https://openalex.org/W6854347851","https://openalex.org/W6854510102","https://openalex.org/W6854866820","https://openalex.org/W6855425132","https://openalex.org/W6855955516","https://openalex.org/W6856594407","https://openalex.org/W6859902353"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"This":[0,57],"work":[1],"introduces":[2],"Talk2BEV,":[3],"a":[4,34,59,65,93,142],"large":[5,94],"vision-language":[6],"model":[7],"(LVLM)<sup":[8],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[9],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[10],"interface":[11],"for":[12,26,48,133],"bird\u2019s-eye":[13],"view":[14,166],"(BEV)":[15],"maps":[16],"commonly":[17],"used":[18],"in":[19,113,131],"autonomous":[20,27,68,134],"driving.":[21],"While":[22],"existing":[23],"perception":[24],"systems":[25],"driving":[28,42,69,135],"scenarios":[29],"have":[30],"largely":[31],"focused":[32],"on":[33,53,85,92,102,169],"pre-defined":[35],"(closed)":[36],"set":[37],"of":[38,67,79,96],"object":[39],"categories":[40],"and":[41,73,82,112,139,154],"scenarios,":[43,136,148],"Talk2BEV":[44,91],"eliminates":[45],"the":[46,77,104,118,123,158,163,167],"need":[47],"BEV-specific":[49],"training,":[50],"relying":[51],"instead":[52],"well-performing":[54],"pre-trained":[55],"LVLMs.":[56],"enables":[58],"single":[60],"system":[61],"to":[62,64,106,117,165],"cater":[63],"variety":[66],"tasks":[70,99],"encompassing":[71,144],"visual":[72,86,119],"spatial":[74],"reasoning,":[75],"predicting":[76],"intents":[78],"traffic":[80],"actors,":[81],"decision-making":[83],"based":[84],"cues.":[87],"We":[88,161],"extensively":[89],"evaluate":[90],"number":[95],"scene":[97],"understanding":[98],"that":[100],"rely":[101],"both":[103],"ability":[105],"interpret":[107],"freeform":[108],"natural":[109],"language":[110],"queries,":[111],"grounding":[114],"these":[115],"queries":[116],"context":[120],"embedded":[121],"into":[122],"language-enhanced":[124],"BEV":[125,147],"map.":[126],"To":[127],"enable":[128],"further":[129],"research":[130],"LVLMs":[132],"we":[137],"develop":[138],"release":[140],"Talk2BEV-Bench,":[141],"benchmark":[143],"1000":[145],"human-annotated":[146],"with":[149],"more":[150],"than":[151],"20,000":[152],"questions":[153],"ground-truth":[155],"responses":[156],"from":[157],"NuScenes":[159],"dataset.":[160],"encourage":[162],"reader":[164],"demos":[168],"our":[170],"project":[171],"page:":[172],"https://llmbev.github.io/talk2bev/":[173]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":38},{"year":2024,"cited_by_count":12}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}