{"id":"https://openalex.org/W2947178363","doi":"https://doi.org/10.18653/v1/p19-1181","title":"Stay on the Path: Instruction Fidelity in Vision-and-Language Navigation","display_name":"Stay on the Path: Instruction Fidelity in Vision-and-Language Navigation","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2947178363","doi":"https://doi.org/10.18653/v1/p19-1181","mag":"2947178363"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1181","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1181","pdf_url":"https://www.aclweb.org/anthology/P19-1181.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1181.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112456155","display_name":"Vihan Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vihan Jain","raw_affiliation_strings":["Google Research","Google (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045876109","display_name":"Gabriel Magalhaes","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gabriel Magalhaes","raw_affiliation_strings":["Google Research","Google (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055207525","display_name":"Alexander Ku","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Ku","raw_affiliation_strings":["Google Research","Google (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103024730","display_name":"Ashish Vaswani","orcid":"https://orcid.org/0000-0002-7794-2085"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashish Vaswani","raw_affiliation_strings":["Google Research","Google (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013936779","display_name":"Eugene Ie","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Ie","raw_affiliation_strings":["Google Research","Google (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048931310","display_name":"Jason Baldridge","orcid":"https://orcid.org/0000-0002-4712-1841"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Baldridge","raw_affiliation_strings":["Google Research","Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5112456155"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.4964006,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.85280452,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1862","last_page":"1872"},"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":0.9965999722480774,"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":0.9962999820709229,"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":0.7980941534042358},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.6739649772644043},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6612058281898499},{"id":"https://openalex.org/keywords/cls-upper-limits","display_name":"CLs upper limits","score":0.5978837609291077},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5736154317855835},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5678116083145142},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5463535785675049},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5072379112243652},{"id":"https://openalex.org/keywords/ideal","display_name":"Ideal (ethics)","score":0.49240052700042725},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.45618879795074463},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4520067572593689},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4351409673690796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.404948353767395},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39842933416366577},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.109961599111557}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7980941534042358},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.6739649772644043},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6612058281898499},{"id":"https://openalex.org/C190729725","wikidata":"https://www.wikidata.org/wiki/Q5012817","display_name":"CLs upper limits","level":2,"score":0.5978837609291077},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5736154317855835},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5678116083145142},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5463535785675049},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5072379112243652},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.49240052700042725},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.45618879795074463},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4520067572593689},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4351409673690796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.404948353767395},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39842933416366577},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.109961599111557},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C119767625","wikidata":"https://www.wikidata.org/wiki/Q618211","display_name":"Optometry","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/p19-1181","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1181","pdf_url":"https://www.aclweb.org/anthology/P19-1181.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1905.12255","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.12255","pdf_url":"https://arxiv.org/pdf/1905.12255","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"mag:2947178363","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1905.12255","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1905.12255","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1905.12255","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1181","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1181","pdf_url":"https://www.aclweb.org/anthology/P19-1181.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8500000238418579,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2947178363.pdf","grobid_xml":"https://content.openalex.org/works/W2947178363.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1602500555","https://openalex.org/W1895577753","https://openalex.org/W1931639407","https://openalex.org/W1933349210","https://openalex.org/W2032338144","https://openalex.org/W2064675550","https://openalex.org/W2131774270","https://openalex.org/W2169528473","https://openalex.org/W2174803659","https://openalex.org/W2250539671","https://openalex.org/W2415494136","https://openalex.org/W2508429489","https://openalex.org/W2512051764","https://openalex.org/W2562608436","https://openalex.org/W2768661419","https://openalex.org/W2772100771","https://openalex.org/W2784820185","https://openalex.org/W2803469966","https://openalex.org/W2805984364","https://openalex.org/W2806168253","https://openalex.org/W2835434549","https://openalex.org/W2884565639","https://openalex.org/W2890809352","https://openalex.org/W2890902815","https://openalex.org/W2899235916","https://openalex.org/W2948008321","https://openalex.org/W2950761309","https://openalex.org/W2963177403","https://openalex.org/W2963575117","https://openalex.org/W2963576560","https://openalex.org/W2963683806","https://openalex.org/W2963693848","https://openalex.org/W2963954913","https://openalex.org/W2964043796","https://openalex.org/W2964935470","https://openalex.org/W2979727876","https://openalex.org/W3084181639"],"related_works":["https://openalex.org/W2951973805","https://openalex.org/W2963800628","https://openalex.org/W2979727876","https://openalex.org/W2964935470","https://openalex.org/W2926977875","https://openalex.org/W3010436080","https://openalex.org/W2963726321","https://openalex.org/W2962744691","https://openalex.org/W2884565639","https://openalex.org/W3035691840","https://openalex.org/W2985026420","https://openalex.org/W3107094551","https://openalex.org/W3106806814","https://openalex.org/W3187185122","https://openalex.org/W2991186560","https://openalex.org/W2987914945","https://openalex.org/W3202077362","https://openalex.org/W3034984114","https://openalex.org/W3207707358","https://openalex.org/W3206919976"],"abstract_inverted_index":{"Advances":[0],"in":[1,21,53,108],"learning":[2],"and":[3,28,35,90,145],"representations":[4],"have":[5,61],"reinvigorated":[6],"work":[7],"that":[8,104,149,151,159],"connects":[9],"language":[10,26,50],"to":[11,31,73,129,135],"other":[12],"modalities.":[13],"A":[14],"particularly":[15],"exciting":[16],"direction":[17],"is":[18],"Vision-and-Language":[19],"Navigation(VLN),":[20],"which":[22],"agents":[23,150,158],"interpret":[24],"natural":[25],"instructions":[27],"visual":[29],"scenes":[30],"move":[32],"through":[33],"environments":[34],"reach":[36],"goals.":[37],"Despite":[38],"recent":[39],"progress,":[40],"current":[41,81],"research":[42],"leaves":[43],"unclear":[44],"how":[45],"much":[46],"of":[47,70,80],"a":[48,92,137],"role":[49],"understanding":[51],"plays":[52],"this":[54],"task,":[55],"especially":[56],"because":[57,118],"dominant":[58],"evaluation":[59],"metrics":[60,82],"focused":[62],"on":[63,161],"goal":[64,162],"completion":[65],"rather":[66],"than":[67],"the":[68,74,84,105,109],"sequence":[69],"actions":[71],"corresponding":[72],"instructions.":[75],"Here,":[76],"we":[77,147],"highlight":[78],"shortcomings":[79],"for":[83,114,154],"Room-to-Room":[85],"dataset":[86,110],"(Anderson":[87],"et":[88],"al.,2018b)":[89],"propose":[91],"new":[93,138],"metric,":[94],"Coverage":[95],"weighted":[96],"by":[97],"Length":[98],"Score":[99],"(CLS).":[100],"We":[101,124],"also":[102],"show":[103,148],"existing":[106,126],"paths":[107,128,134],"are":[111,120],"not":[112],"ideal":[113],"evaluating":[115],"instruction":[116,155],"following":[117],"they":[119],"direct-to-goal":[121],"shortest":[122],"paths.":[123],"join":[125],"short":[127],"form":[130],"more":[131],"challenging":[132],"extended":[133],"create":[136],"data":[139],"set,":[140],"Room-for-Room":[141],"(R4R).":[142],"Using":[143],"R4R":[144],"CLS,":[146],"receive":[152],"rewards":[153],"fidelity":[156],"outperform":[157],"focus":[160],"completion.":[163]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}