{"id":"https://openalex.org/W2981799368","doi":"https://doi.org/10.1109/iccv.2019.00750","title":"Transferable Representation Learning in Vision-and-Language Navigation","display_name":"Transferable Representation Learning in Vision-and-Language Navigation","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2981799368","doi":"https://doi.org/10.1109/iccv.2019.00750","mag":"2981799368"},"language":"en","primary_location":{"id":"doi:10.1109/iccv.2019.00750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2019.00750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","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/A5056606858","display_name":"Haoshuo Huang","orcid":"https://orcid.org/0000-0003-3945-3632"},"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":"Haoshuo Huang","raw_affiliation_strings":["Google Research, 1600 Amphitheatre Parkway, Mountain View, CA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, 1600 Amphitheatre Parkway, Mountain View, CA, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","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":false,"raw_author_name":"Vihan Jain","raw_affiliation_strings":["Google Research, 1600 Amphitheatre Parkway, Mountain View, CA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, 1600 Amphitheatre Parkway, Mountain View, CA, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112461374","display_name":"Harsh Mehta","orcid":"https://orcid.org/0000-0002-3428-3008"},"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":"Harsh Mehta","raw_affiliation_strings":["Google Research, 1600 Amphitheatre Parkway, Mountain View, CA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, 1600 Amphitheatre Parkway, Mountain View, CA, 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, 1600 Amphitheatre Parkway, Mountain View, CA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, 1600 Amphitheatre Parkway, Mountain View, CA, 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, 1600 Amphitheatre Parkway, Mountain View, CA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, 1600 Amphitheatre Parkway, Mountain View, CA, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","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, 1600 Amphitheatre Parkway, Mountain View, CA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, 1600 Amphitheatre Parkway, Mountain View, CA, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","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, 1600 Amphitheatre Parkway, Mountain View, CA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, 1600 Amphitheatre Parkway, Mountain View, CA, United States","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5056606858"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":5.9195,"has_fulltext":false,"cited_by_count":88,"citation_normalized_percentile":{"value":0.96989034,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7403","last_page":"7412"},"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":0.9993000030517578,"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":0.9822999835014343,"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":0.77251136302948},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5724571943283081},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5328102111816406},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5250951051712036},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5088996887207031},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4969992935657501},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4435001611709595},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.43343549966812134},{"id":"https://openalex.org/keywords/sequence-learning","display_name":"Sequence learning","score":0.43020206689834595},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34278249740600586},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32173609733581543},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08915519714355469}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.77251136302948},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5724571943283081},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5328102111816406},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5250951051712036},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5088996887207031},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4969992935657501},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4435001611709595},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.43343549966812134},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.43020206689834595},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34278249740600586},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32173609733581543},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08915519714355469},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccv.2019.00750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2019.00750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W1493086929","https://openalex.org/W1514535095","https://openalex.org/W1602500555","https://openalex.org/W1849277567","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1933349210","https://openalex.org/W1984383922","https://openalex.org/W2064675550","https://openalex.org/W2102605133","https://openalex.org/W2117539524","https://openalex.org/W2119717200","https://openalex.org/W2131774270","https://openalex.org/W2174803659","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2302548814","https://openalex.org/W2465999789","https://openalex.org/W2508429489","https://openalex.org/W2512051764","https://openalex.org/W2768661419","https://openalex.org/W2804117224","https://openalex.org/W2805984364","https://openalex.org/W2810821963","https://openalex.org/W2835434549","https://openalex.org/W2842511635","https://openalex.org/W2847843315","https://openalex.org/W2884565639","https://openalex.org/W2901894078","https://openalex.org/W2909303996","https://openalex.org/W2926977875","https://openalex.org/W2949480225","https://openalex.org/W2962744691","https://openalex.org/W2962887844","https://openalex.org/W2962946204","https://openalex.org/W2963109634","https://openalex.org/W2963177403","https://openalex.org/W2963575117","https://openalex.org/W2963576560","https://openalex.org/W2963726321","https://openalex.org/W2963800628","https://openalex.org/W2963846044","https://openalex.org/W2963946945","https://openalex.org/W2963954913","https://openalex.org/W2964339842","https://openalex.org/W2964935470","https://openalex.org/W2967853831","https://openalex.org/W2997886377","https://openalex.org/W3084181639","https://openalex.org/W4249013746","https://openalex.org/W4251072654","https://openalex.org/W4285719527","https://openalex.org/W4297808394","https://openalex.org/W6630875275","https://openalex.org/W6639204139","https://openalex.org/W6685664872","https://openalex.org/W6697921835","https://openalex.org/W6726035275","https://openalex.org/W6750106230","https://openalex.org/W6751885507","https://openalex.org/W6753516098","https://openalex.org/W6756140488","https://openalex.org/W6756557100","https://openalex.org/W6757724268","https://openalex.org/W6759920914","https://openalex.org/W6782391415"],"related_works":["https://openalex.org/W2112284452","https://openalex.org/W3034410548","https://openalex.org/W1982640233","https://openalex.org/W4389011229","https://openalex.org/W3036953692","https://openalex.org/W2883195674","https://openalex.org/W2072736607","https://openalex.org/W2043380470","https://openalex.org/W3080374445","https://openalex.org/W2964790801"],"abstract_inverted_index":{"Vision-and-Language":[0],"Navigation":[1],"(VLN)":[2],"tasks":[3,61],"such":[4],"as":[5,133],"Room-to-Room":[6],"(R2R)":[7],"require":[8],"machine":[9],"agents":[10,38,130],"to":[11,18,24,45,58,73,96],"interpret":[12],"natural":[13],"language":[14,43,56],"instructions":[15],"and":[16,42,55,80],"learn":[17],"act":[19],"in":[20,33,117,131],"visually":[21],"realistic":[22],"environments":[23],"achieve":[25],"navigation":[26],"goals.":[27],"The":[28],"overall":[29],"task":[30],"requires":[31],"competence":[32],"several":[34],"perception":[35],"problems:":[36],"successful":[37],"combine":[39],"spatio-temporal,":[40],"vision":[41,54],"understanding":[44],"produce":[46],"appropriate":[47],"action":[48],"sequences.":[49],"Our":[50],"approach":[51],"adapts":[52],"pre-trained":[53],"representations":[57,70],"relevant":[59],"in-domain":[60],"making":[62],"them":[63],"more":[64],"effective":[65],"for":[66],"VLN.":[67],"Specifically,":[68],"the":[69,85,89,103,107,111,118,124,136],"are":[71,114],"adapted":[72],"solve":[74],"both":[75],"a":[76,97],"cross-modal":[77],"sequence":[78,81,86,98,104],"alignment":[79,87],"coherence":[82,105],"task.":[83],"In":[84,102],"task,":[88,106],"model":[90,108],"determines":[91,109],"whether":[92,110],"an":[93],"instruction":[94],"corresponds":[95],"of":[99],"visual":[100],"frames.":[101],"perceptual":[112],"sequences":[113],"predictive":[115],"sequentially":[116],"instruction-conditioned":[119],"latent":[120],"space.":[121],"By":[122],"transferring":[123],"domain-adapted":[125],"representations,":[126],"we":[127],"improve":[128],"competitive":[129],"R2R":[132],"measured":[134],"by":[135,140],"success":[137],"rate":[138],"weighted":[139],"path":[141],"length":[142],"(SPL)":[143],"metric.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":21},{"year":2019,"cited_by_count":2}],"updated_date":"2026-05-09T13:55:54.758798","created_date":"2025-10-10T00:00:00"}