{"id":"https://openalex.org/W2964343989","doi":"https://doi.org/10.18653/v1/p19-1655","title":"Are You Looking? Grounding to Multiple Modalities in Vision-and-Language Navigation","display_name":"Are You Looking? Grounding to Multiple Modalities in Vision-and-Language Navigation","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2964343989","doi":"https://doi.org/10.18653/v1/p19-1655","mag":"2964343989"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1655","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1655","pdf_url":null,"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":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/p19-1655","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072304825","display_name":"Ronghang Hu","orcid":"https://orcid.org/0000-0002-5060-9485"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ronghang Hu","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102739620","display_name":"Daniel Fried","orcid":"https://orcid.org/0000-0002-0454-9792"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Fried","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037747070","display_name":"Anna Rohrbach","orcid":"https://orcid.org/0000-0003-1161-6006"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anna Rohrbach","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004921249","display_name":"Dan Klein","orcid":"https://orcid.org/0000-0002-8881-1902"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Klein","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029105520","display_name":"Trevor Darrell","orcid":"https://orcid.org/0000-0001-5453-8533"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trevor Darrell","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075906727","display_name":"Kate Saenko","orcid":"https://orcid.org/0000-0002-7564-7218"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kate Saenko","raw_affiliation_strings":["Boston University"],"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5072304825"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":6.0286,"has_fulltext":false,"cited_by_count":75,"citation_normalized_percentile":{"value":0.97040737,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6551","last_page":"6557"},"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":0.9929999709129333,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9922999739646912,"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/modalities","display_name":"Modalities","score":0.8051965236663818},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.78619384765625},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.5897645950317383},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5717962384223938},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5626243352890015},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5591743588447571},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5423181653022766},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4969337284564972},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48987051844596863},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.42899972200393677},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3888811469078064},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17912578582763672},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12766411900520325}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.8051965236663818},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.78619384765625},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.5897645950317383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5717962384223938},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5626243352890015},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5591743588447571},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5423181653022766},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4969337284564972},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48987051844596863},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42899972200393677},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3888811469078064},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17912578582763672},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12766411900520325},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1655","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1655","pdf_url":null,"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"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1655","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1655","pdf_url":null,"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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1602500555","https://openalex.org/W1933065844","https://openalex.org/W1962416794","https://openalex.org/W2064675550","https://openalex.org/W2105103432","https://openalex.org/W2111526438","https://openalex.org/W2118781169","https://openalex.org/W2133564696","https://openalex.org/W2189089430","https://openalex.org/W2194775991","https://openalex.org/W2236233024","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2567015638","https://openalex.org/W2613718673","https://openalex.org/W2774005037","https://openalex.org/W2795911278","https://openalex.org/W2805984364","https://openalex.org/W2890902815","https://openalex.org/W2898646936","https://openalex.org/W2901725278","https://openalex.org/W2903172725","https://openalex.org/W2909303996","https://openalex.org/W2950697717","https://openalex.org/W2962735233","https://openalex.org/W2962846267","https://openalex.org/W2962884155","https://openalex.org/W2962887844","https://openalex.org/W2963349562","https://openalex.org/W2963575117","https://openalex.org/W2963693848","https://openalex.org/W2963726321","https://openalex.org/W2963800628","https://openalex.org/W2963846044","https://openalex.org/W2963946945","https://openalex.org/W2964199361","https://openalex.org/W2964217371","https://openalex.org/W2964308564","https://openalex.org/W2964339842","https://openalex.org/W2979727876","https://openalex.org/W3084181639","https://openalex.org/W4285719527","https://openalex.org/W4289293738","https://openalex.org/W4297795161"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2185469136","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W2087343574"],"abstract_inverted_index":{"Vision-and-Language":[0],"Navigation":[1],"(VLN)":[2],"requires":[3],"grounding":[4,23,115],"instructions,":[5],"such":[6],"as":[7],"\u201cturn":[8,44],"right":[9],"and":[10,131],"stop":[11],"at":[12,35,134],"the":[13,28,36,50,59,99,107,114,138,144],"door\u201d,":[14],"to":[15,27,112,125],"routes":[16],"in":[17,94],"a":[18,54,118],"visual":[19,41,74,88,92],"environment.":[20],"The":[21],"actual":[22],"can":[24],"connect":[25],"language":[26,61],"environment":[29],"through":[30],"multiple":[31],"modalities,":[32,109],"e.g.":[33],"\u201cstop":[34],"door\u201d":[37],"might":[38,46],"ground":[39],"into":[40,117],"objects,":[42],"while":[43],"right\u201d":[45],"rely":[47],"only":[48,83],"on":[49,98,143],"geometric":[51],"structure":[52],"of":[53,120,140],"route.":[55],"We":[56],"investigate":[57],"where":[58],"natural":[60],"empirically":[62],"grounds":[63],"under":[64],"two":[65],"recent":[66],"state-of-the-art":[67,141],"VLN":[68,145],"models.":[69],"Surprisingly,":[70],"we":[71,110],"discover":[72],"that":[73],"features":[75],"may":[76],"actually":[77],"hurt":[78],"these":[79],"models:":[80],"models":[81,122,142],"which":[82],"use":[84,105],"route":[85],"structure,":[86],"ablating":[87],"features,":[89],"outperform":[90],"their":[91],"counterparts":[93],"unseen":[95],"new":[96],"environments":[97],"benchmark":[100],"Room-to-Room":[101],"dataset.":[102],"To":[103],"better":[104],"all":[106],"available":[108],"propose":[111],"decompose":[113],"procedure":[116],"set":[119],"expert":[121],"with":[123],"access":[124],"different":[126],"modalities":[127],"(including":[128],"object":[129],"detections)":[130],"ensemble":[132],"them":[133],"prediction":[135],"time,":[136],"improving":[137],"performance":[139],"task.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":24},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-22T08:09:32.410652","created_date":"2025-10-10T00:00:00"}
