{"id":"https://openalex.org/W4382699535","doi":"https://doi.org/10.3390/s23136028","title":"Outdoor Vision-and-Language Navigation Needs Object-Level Alignment","display_name":"Outdoor Vision-and-Language Navigation Needs Object-Level Alignment","publication_year":2023,"publication_date":"2023-06-29","ids":{"openalex":"https://openalex.org/W4382699535","doi":"https://doi.org/10.3390/s23136028","pmid":"https://pubmed.ncbi.nlm.nih.gov/37447877"},"language":"en","primary_location":{"id":"doi:10.3390/s23136028","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23136028","pdf_url":"https://www.mdpi.com/1424-8220/23/13/6028/pdf?version=1688032223","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/23/13/6028/pdf?version=1688032223","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051470569","display_name":"Y. Sun","orcid":"https://orcid.org/0009-0003-1523-5689"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]},{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yanjun Sun","raw_affiliation_strings":["Department of Electronics and Electrical Engineering, Faculty of Science and Technology, Keio University, 3-14-1, Hiyoshi, Kohoku-ku, Yokohama 223-8522, Japan","National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba 305-8560, Japan"],"raw_orcid":"https://orcid.org/0009-0003-1523-5689","affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Engineering, Faculty of Science and Technology, Keio University, 3-14-1, Hiyoshi, Kohoku-ku, Yokohama 223-8522, Japan","institution_ids":["https://openalex.org/I203951103"]},{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba 305-8560, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029961156","display_name":"Yue Qiu","orcid":"https://orcid.org/0000-0002-2181-9475"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yue Qiu","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba 305-8560, Japan"],"raw_orcid":"https://orcid.org/0000-0002-2181-9475","affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba 305-8560, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070908826","display_name":"Yoshimitsu Aoki","orcid":"https://orcid.org/0000-0001-7361-0027"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshimitsu Aoki","raw_affiliation_strings":["Department of Electronics and Electrical Engineering, Faculty of Science and Technology, Keio University, 3-14-1, Hiyoshi, Kohoku-ku, Yokohama 223-8522, Japan"],"raw_orcid":"https://orcid.org/0000-0001-7361-0027","affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Engineering, Faculty of Science and Technology, Keio University, 3-14-1, Hiyoshi, Kohoku-ku, Yokohama 223-8522, Japan","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011507481","display_name":"Hirokatsu Kataoka","orcid":"https://orcid.org/0000-0001-8844-165X"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirokatsu Kataoka","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba 305-8560, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8844-165X","affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba 305-8560, Japan","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5051470569"],"corresponding_institution_ids":["https://openalex.org/I203951103","https://openalex.org/I73613424"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":0.5582,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.67264223,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"23","issue":"13","first_page":"6028","last_page":"6028"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9919999837875366,"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":0.9918000102043152,"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":0.7680796384811401},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.6410899758338928},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5942450165748596},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5810618996620178},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.547728419303894},{"id":"https://openalex.org/keywords/panorama","display_name":"Panorama","score":0.47914737462997437},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4548327624797821},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.45439082384109497},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.4516507685184479},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4311734139919281},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11602598428726196}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7680796384811401},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6410899758338928},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5942450165748596},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5810618996620178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.547728419303894},{"id":"https://openalex.org/C2780580889","wikidata":"https://www.wikidata.org/wiki/Q41363","display_name":"Panorama","level":2,"score":0.47914737462997437},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4548327624797821},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.45439082384109497},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.4516507685184479},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4311734139919281},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11602598428726196},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014785","descriptor_name":"Vision, Ocular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014796","descriptor_name":"Visual Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.3390/s23136028","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23136028","pdf_url":"https://www.mdpi.com/1424-8220/23/13/6028/pdf?version=1688032223","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:37447877","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37447877","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10346337","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10346337","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10346337/pdf/sensors-23-06028.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:cb588ffb3aa94904800a70fdabc7f57d","is_oa":true,"landing_page_url":"https://doaj.org/article/cb588ffb3aa94904800a70fdabc7f57d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 23, Iss 13, p 6028 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/23/13/6028/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s23136028","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors; Volume 23; Issue 13; Pages: 6028","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s23136028","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23136028","pdf_url":"https://www.mdpi.com/1424-8220/23/13/6028/pdf?version=1688032223","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[{"id":"https://openalex.org/G1490461360","display_name":null,"funder_award_id":"JPMJSP2123","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"}],"funders":[{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4382699535.pdf"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2064675550","https://openalex.org/W2117539524","https://openalex.org/W2171792512","https://openalex.org/W2194775991","https://openalex.org/W2636355936","https://openalex.org/W2896457183","https://openalex.org/W2947067399","https://openalex.org/W2947178363","https://openalex.org/W2962784628","https://openalex.org/W2963150697","https://openalex.org/W2963800628","https://openalex.org/W2966715458","https://openalex.org/W2970971581","https://openalex.org/W2979727876","https://openalex.org/W2991416037","https://openalex.org/W2997886377","https://openalex.org/W3003391301","https://openalex.org/W3016001898","https://openalex.org/W3030163527","https://openalex.org/W3034758614","https://openalex.org/W3034984114","https://openalex.org/W3099019594","https://openalex.org/W3100923070","https://openalex.org/W3106129629","https://openalex.org/W3107069568","https://openalex.org/W3109097593","https://openalex.org/W3152079230","https://openalex.org/W3155707959","https://openalex.org/W3169884222","https://openalex.org/W3175443984","https://openalex.org/W3192009892","https://openalex.org/W3205276578","https://openalex.org/W3208220903","https://openalex.org/W4221167437","https://openalex.org/W4285224875","https://openalex.org/W4312436794","https://openalex.org/W6750106230","https://openalex.org/W6759920914"],"related_works":["https://openalex.org/W2393825039","https://openalex.org/W2951694738","https://openalex.org/W3036977332","https://openalex.org/W2352220358","https://openalex.org/W2601489641","https://openalex.org/W1989085122","https://openalex.org/W2370281691","https://openalex.org/W2109399350","https://openalex.org/W3045257361","https://openalex.org/W2051913996"],"abstract_inverted_index":{"In":[0,162],"the":[1,58,69,72,82,119,129,158,227,238,245,258],"field":[2],"of":[3,48,84,153,183,240,247],"embodied":[4,254],"AI,":[5],"vision-and-language":[6],"navigation":[7,79,251],"(VLN)":[8],"is":[9,189,208],"a":[10,24,46,96,147,151,176,209,220],"crucial":[11,191],"and":[12,35,50,67,99,131,169,179,201,213,263],"challenging":[13,221],"multi-modal":[14],"task.":[15],"Specifically,":[16],"outdoor":[17,40,65,222,265],"VLN":[18,41,223],"involves":[19,81],"an":[20,112],"agent":[21,59,120,181],"navigating":[22,91,184],"within":[23],"graph-based":[25],"environment,":[26],"while":[27],"simultaneously":[28],"interpreting":[29],"information":[30,243],"from":[31],"real-world":[32,193],"urban":[33],"environments":[34,66,73],"natural":[36,107],"language":[37],"instructions.":[38],"Existing":[39],"models":[42],"predict":[43],"actions":[44],"using":[45],"combination":[47],"panorama":[49],"instruction":[51],"features.":[52],"However,":[53],"these":[54,133,139],"methods":[55],"may":[56],"cause":[57],"to":[60,62,74,76,92,102,121,164,249],"struggle":[61],"understand":[63],"complicated":[64],"ignore":[68],"details":[70],"in":[71,128,244,253],"fail":[75],"navigate.":[77],"Human":[78],"often":[80],"use":[83],"specific":[85],"objects":[86],"as":[87,141],"reference":[88],"landmarks":[89,134,140],"when":[90],"unfamiliar":[93],"places,":[94],"providing":[95],"more":[97,123,177,210,261],"rational":[98],"efficient":[100,264],"approach":[101,215],"navigation.":[103,136,266],"Inspired":[104],"by":[105,229],"this":[106],"human":[108],"behavior,":[109],"we":[110],"propose":[111],"object-level":[113,242],"alignment":[114],"module":[115],"(OAlM),":[116],"which":[117],"guides":[118],"focus":[122],"on":[124,219,231],"object":[125,167],"tokens":[126],"mentioned":[127],"instructions":[130],"recognize":[132],"during":[135],"By":[137],"treating":[138],"sub-goals,":[142],"our":[143,171,206,214],"method":[144],"effectively":[145],"decomposes":[146],"long-range":[148],"path":[149],"into":[150],"series":[152],"shorter":[154],"paths,":[155],"ultimately":[156],"improving":[157],"agent's":[159],"overall":[160],"performance.":[161],"addition":[163],"enabling":[165],"better":[166],"recognition":[168],"alignment,":[170],"proposed":[172],"OAlM":[173,207],"also":[174],"fosters":[175],"robust":[178],"adaptable":[180],"capable":[182],"complex":[185],"environments.":[186],"This":[187],"adaptability":[188],"particularly":[190],"for":[192,260],"applications":[194],"where":[195],"environmental":[196],"conditions":[197],"can":[198],"be":[199],"unpredictable":[200],"varied.":[202],"Experimental":[203],"results":[204,236],"show":[205],"object-focused":[211],"model,":[212],"outperforms":[216],"all":[217],"metrics":[218],"Touchdown":[224],"dataset,":[225],"exceeding":[226],"baseline":[228],"3.19%":[230],"task":[232],"completion":[233],"(TC).":[234],"These":[235],"highlight":[237],"potential":[239],"leveraging":[241],"form":[246],"sub-goals":[248],"improve":[250],"performance":[252],"AI":[255],"systems,":[256],"paving":[257],"way":[259],"advanced":[262]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-18T10:00:31.954636","created_date":"2025-10-10T00:00:00"}
