{"id":"https://openalex.org/W3206064582","doi":"https://doi.org/10.1145/3474085.3475282","title":"Neighbor-view Enhanced Model for Vision and Language Navigation","display_name":"Neighbor-view Enhanced Model for Vision and Language Navigation","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3206064582","doi":"https://doi.org/10.1145/3474085.3475282","mag":"3206064582"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475282","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475282","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101399813","display_name":"Dong An","orcid":"https://orcid.org/0000-0002-1347-8535"},"institutions":[{"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":"Dong An","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","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"},"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/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yuankai Qi","raw_affiliation_strings":["University of Adelaide, Adelaide, SA, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Adelaide, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101550628","display_name":"Yan Huang","orcid":"https://orcid.org/0000-0002-8239-7229"},"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/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Huang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060958969","display_name":"Qi Wu","orcid":"https://orcid.org/0000-0003-3631-256X"},"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/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qi Wu","raw_affiliation_strings":["University of Adelaide, Adelaide, SA, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Adelaide, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115602506","display_name":"Liang Wang","orcid":"https://orcid.org/0000-0001-5224-8647"},"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/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"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":"Liang Wang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, CEBSIT, & CAS-AIR, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, CEBSIT, & CAS-AIR, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210097554","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111885963","display_name":"Tieniu Tan","orcid":null},"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/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tieniu Tan","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences & CEBSIT, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences & CEBSIT, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879","https://openalex.org/I4210097554"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":70,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5101","last_page":"5109"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9970999956130981,"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/T10028","display_name":"Topic Modeling","score":0.9958999752998352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8519915342330933},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6738191246986389},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5871288776397705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5756432414054871},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5677140355110168},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5650416612625122},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5063329935073853},{"id":"https://openalex.org/keywords/orientation","display_name":"Orientation (vector space)","score":0.4472372531890869},{"id":"https://openalex.org/keywords/feature-matching","display_name":"Feature matching","score":0.4348299205303192},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38934722542762756},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36724257469177246},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.293509304523468},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09983858466148376}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8519915342330933},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6738191246986389},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5871288776397705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5756432414054871},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5677140355110168},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5650416612625122},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5063329935073853},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.4472372531890869},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.4348299205303192},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38934722542762756},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36724257469177246},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.293509304523468},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09983858466148376},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475282","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475282","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3695300887","display_name":null,"funder_award_id":"61525306, 61633021, 61721004, 61806194, U1803261, and 61976132","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5273665290","display_name":null,"funder_award_id":"Z201100006820079","funder_id":"https://openalex.org/F4320334978","funder_display_name":"Beijing Nova Program"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2523246573","https://openalex.org/W2626778328","https://openalex.org/W2732026016","https://openalex.org/W2747329762","https://openalex.org/W2784458614","https://openalex.org/W2790797399","https://openalex.org/W2805984364","https://openalex.org/W2909303996","https://openalex.org/W2918407751","https://openalex.org/W2926977875","https://openalex.org/W2955993284","https://openalex.org/W2963846044","https://openalex.org/W2964043796","https://openalex.org/W2964339842","https://openalex.org/W2964343989","https://openalex.org/W2964935470","https://openalex.org/W2970340522","https://openalex.org/W2971512641","https://openalex.org/W2971820544","https://openalex.org/W2987914945","https://openalex.org/W3007299332","https://openalex.org/W3013242392","https://openalex.org/W3014266552","https://openalex.org/W3016811308","https://openalex.org/W3029418112","https://openalex.org/W3034500398","https://openalex.org/W3034578524","https://openalex.org/W3035232877","https://openalex.org/W3107069568","https://openalex.org/W3108144224","https://openalex.org/W3109380382","https://openalex.org/W4236965008","https://openalex.org/W4285719527","https://openalex.org/W4365799834","https://openalex.org/W6601048702","https://openalex.org/W6601283680","https://openalex.org/W6605584388"],"related_works":["https://openalex.org/W2350424104","https://openalex.org/W2152949619","https://openalex.org/W1090580760","https://openalex.org/W4365793569","https://openalex.org/W2389991515","https://openalex.org/W2050706403","https://openalex.org/W2395120299","https://openalex.org/W2499438468","https://openalex.org/W2479744187","https://openalex.org/W2360523411"],"abstract_inverted_index":{"Vision":[0],"and":[1,94,114,126,158,182,189],"Language":[2],"Navigation":[3],"(VLN)":[4],"requires":[5],"an":[6,41,138],"agent":[7],"to":[8,10,56,75,98,141],"navigate":[9],"a":[11,24,69,91,95,111,122],"target":[12],"location":[13],"by":[14,27],"following":[15],"natural":[16],"language":[17],"instructions.":[18,151],"Most":[19],"of":[20,30,47,58,61,175],"existing":[21,62],"works":[22],"represent":[23],"navigation":[25,155],"candidate":[26,37],"the":[28,31,36,48,115,143,166,173,176,180],"feature":[29],"corresponding":[32],"single":[33,49],"view":[34,50],"where":[35],"lies":[38],"in.":[39],"However,":[40],"instruction":[42],"may":[43],"mention":[44],"landmarks":[45],"out":[46],"as":[51],"references,":[52],"which":[53],"might":[54],"lead":[55],"failures":[57],"textual-visual":[59,85],"matching":[60],"methods.":[63],"In":[64],"this":[65],"work,":[66],"we":[67],"propose":[68],"multi-module":[70],"Neighbor-View":[71],"Enhanced":[72],"Model":[73],"(NvEM)":[74],"adaptively":[76,129],"incorporate":[77],"visual":[78],"contexts":[79,100],"from":[80,101],"neighbor":[81,102,108,119],"views":[82,109],"for":[83,164],"better":[84],"matching.":[86],"Specifically,":[87],"our":[88],"NvEM":[89,190],"utilizes":[90],"subject":[92,105],"module":[93,97,106,117,140,153],"reference":[96,116],"collect":[99],"views.":[103],"The":[104],"fuses":[107,118],"at":[110,121,200],"global":[112],"level,":[113],"objects":[120],"local":[123],"level.":[124],"Subjects":[125],"references":[127],"are":[128],"determined":[130],"via":[131],"attention":[132],"mechanisms.":[133],"Our":[134,196],"model":[135],"also":[136],"includes":[137],"action":[139,156],"utilize":[142],"strong":[144],"orientation":[145],"guidance":[146],"(e.g.,":[147],"\"turn":[148],"left'')":[149],"in":[150],"Each":[152],"predicts":[154],"separately":[157],"their":[159],"weighted":[160],"sum":[161],"is":[162,198],"used":[163],"predicting":[165],"final":[167],"action.":[168],"Extensive":[169],"experimental":[170],"results":[171],"demonstrate":[172],"effectiveness":[174],"proposed":[177],"method":[178],"on":[179],"R2R":[181],"R4R":[183],"benchmarks":[184],"against":[185],"several":[186],"state-of-the-art":[187],"navigators,":[188],"even":[191],"beats":[192],"some":[193],"pre-training":[194],"ones.":[195],"code":[197],"available":[199],"https://github.com/MarSaKi/NvEM.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}