{"id":"https://openalex.org/W4311001206","doi":"https://doi.org/10.48550/arxiv.2212.04385","title":"BEVBert: Multimodal Map Pre-training for Language-guided Navigation","display_name":"BEVBert: Multimodal Map Pre-training for Language-guided Navigation","publication_year":2022,"publication_date":"2022-12-08","ids":{"openalex":"https://openalex.org/W4311001206","doi":"https://doi.org/10.48550/arxiv.2212.04385"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2212.04385","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2212.04385","pdf_url":"https://arxiv.org/pdf/2212.04385","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2212.04385","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101399813","display_name":"Dong Un An","orcid":"https://orcid.org/0000-0002-1347-8535","observed_orcids":["https://orcid.org/0000-0002-1347-8535"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"An, Dong","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences","School of Future Technology , UCAS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Future Technology , UCAS","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070842891","display_name":"Yuankai Qi","orcid":"https://orcid.org/0000-0003-4312-5682","observed_orcids":["https://orcid.org/0000-0003-4312-5682"]},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I4405259444","https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qi, Yuankai","raw_affiliation_strings":["Australian Institute for Machine Learning , University of Adelaide"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Institute for Machine Learning , University of Adelaide","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Li, Yangguang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401727009","display_name":"Sensetime (China)","ror":"https://ror.org/049wsmj07","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401727009"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Yangguang","raw_affiliation_strings":["SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":["https://openalex.org/I4401727009"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100715214","display_name":"Yan Huang","orcid":"https://orcid.org/0000-0002-1363-5318","observed_orcids":["https://orcid.org/0000-0002-1363-5318"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Yan","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115602506","display_name":"Liang Wang","orcid":"https://orcid.org/0000-0001-5224-8647","observed_orcids":["https://orcid.org/0000-0001-5224-8647","https://orcid.org/0000-0002-5247-6727"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Liang","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111885963","display_name":"Tieniu Tan","orcid":"https://orcid.org/0000-0002-1808-2169","observed_orcids":["https://orcid.org/0000-0002-1808-2169","https://orcid.org/0000-0003-4054-5649"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tan, Tieniu","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences","Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102006926","display_name":"Jing Shao","orcid":"https://orcid.org/0000-0002-2500-2366","observed_orcids":["https://orcid.org/0000-0002-2500-2366"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shao, Jing","raw_affiliation_strings":["Shanghai AI Laboratory https ://github.com/ MarSaKi / VLN-BEVBert"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory https ://github.com/ MarSaKi / VLN-BEVBert","institution_ids":["https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9643999934196472,"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":0.9643999934196472,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.012199999764561653,"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/T11904","display_name":"Spatial Cognition and Navigation","score":0.007000000216066837,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/vision-and-language-navigation","display_name":"vision-and-language navigation","score":0.9810000061988831},{"id":"https://openalex.org/keywords/language-guided-navigation","display_name":"language-guided navigation","score":0.8360000252723694},{"id":"https://openalex.org/keywords/topological-maps","display_name":"topological maps","score":0.9089999794960022},{"id":"https://openalex.org/keywords/long-term-planning","display_name":"long-term planning","score":0.7020000219345093}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7480584979057312},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5375158190727234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.531825602054596},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4985809326171875},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4950851500034332},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4707905352115631},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4547036588191986},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3301128149032593},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09394314885139465},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2212.04385","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2212.04385","pdf_url":"https://arxiv.org/pdf/2212.04385","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2212.04385","doi":"https://doi.org/10.48550/arxiv.2212.04385","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2212.04385","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2212.04385","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2212.04385","pdf_url":"https://arxiv.org/pdf/2212.04385","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.6499999761581421}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611","https://openalex.org/W2996078371"],"abstract_inverted_index":{"Large-scale":[0],"pre-training":[1,15,50,108,135],"has":[2],"shown":[3],"promising":[4],"results":[5],"on":[6,101,145],"the":[7,26,35,88,102,123,130,133,140],"vision-and-language":[8],"navigation":[9,76,125],"(VLN)":[10],"task.":[11],"However,":[12],"most":[13],"existing":[14],"methods":[16],"employ":[17],"discrete":[18],"panoramas":[19],"to":[20,28,66,110],"learn":[21,111],"visual-textual":[22],"associations.":[23],"This":[24,83],"requires":[25],"model":[27],"implicitly":[29],"correlate":[30],"incomplete,":[31],"duplicate":[32],"observations":[33,70],"within":[34],"panoramas,":[36],"which":[37,116],"may":[38],"impair":[39],"an":[40],"agent's":[41],"spatial":[42],"understanding.":[43],"Thus,":[44],"we":[45,60,105],"propose":[46],"a":[47,62,79,107,112],"new":[48],"map-based":[49,134],"paradigm":[51],"that":[52],"is":[53],"spatial-aware":[54,118],"for":[55,92,137],"use":[56],"in":[57,78],"VLN.":[58],"Concretely,":[59],"build":[61],"local":[63],"metric":[64],"map":[65,114],"explicitly":[67],"aggregate":[68],"incomplete":[69],"and":[71,96,139],"remove":[72],"duplicates,":[73],"while":[74],"modeling":[75],"dependency":[77],"global":[80],"topological":[81],"map.":[82],"hybrid":[84,103],"design":[85],"can":[86],"balance":[87],"demand":[89],"of":[90,132],"VLN":[91,147],"both":[93],"short-term":[94],"reasoning":[95,120],"long-term":[97],"planning.":[98],"Then,":[99],"based":[100],"map,":[104],"devise":[106],"framework":[109],"multimodal":[113],"representation,":[115],"enhances":[117],"cross-modal":[119],"thereby":[121],"facilitating":[122],"language-guided":[124],"goal.":[126],"Extensive":[127],"experiments":[128],"demonstrate":[129],"effectiveness":[131],"route":[136],"VLN,":[138],"proposed":[141],"method":[142],"achieves":[143],"state-of-the-art":[144],"four":[146],"benchmarks.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":14}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}
