{"id":"https://openalex.org/W3107094551","doi":"https://doi.org/10.1109/tcsvt.2020.3039522","title":"Language-Guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learning","display_name":"Language-Guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learning","publication_year":2020,"publication_date":"2020-11-20","ids":{"openalex":"https://openalex.org/W3107094551","doi":"https://doi.org/10.1109/tcsvt.2020.3039522","mag":"3107094551"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2020.3039522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2020.3039522","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.10972","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101883961","display_name":"Weixia Zhang","orcid":"https://orcid.org/0000-0002-3634-2630"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weixia Zhang","raw_affiliation_strings":["MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3634-2630","affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100704678","display_name":"Chao Ma","orcid":"https://orcid.org/0000-0002-8459-2845"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Ma","raw_affiliation_strings":["MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8459-2845","affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"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":["School of Computer Science, The University of Adelaide, Adelaide, SA, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3631-256X","affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Adelaide, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019708391","display_name":"Xiaokang Yang","orcid":"https://orcid.org/0000-0003-4029-3322"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaokang Yang","raw_affiliation_strings":["MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4029-3322","affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.45,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":{"value":0.94085829,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"31","issue":"9","first_page":"3469","last_page":"3481"},"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":0.9966999888420105,"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":0.9915000200271606,"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":0.8084684610366821},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6525815725326538},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6302381157875061},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5980525016784668},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.5690216422080994},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5486659407615662},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5171353220939636},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5129201412200928},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5096232891082764},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.47871994972229004},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.43347740173339844},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4292263388633728},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.36252039670944214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8084684610366821},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6525815725326538},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6302381157875061},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5980525016784668},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5690216422080994},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5486659407615662},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5171353220939636},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5129201412200928},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5096232891082764},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.47871994972229004},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.43347740173339844},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4292263388633728},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36252039670944214},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2020.3039522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2020.3039522","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2011.10972","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.10972","pdf_url":"https://arxiv.org/pdf/2011.10972","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.10972","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.10972","pdf_url":"https://arxiv.org/pdf/2011.10972","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":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8399999737739563}],"awards":[{"id":"https://openalex.org/G1978429096","display_name":null,"funder_award_id":"U19B2035","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4458413329","display_name":null,"funder_award_id":"61906119","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5404748735","display_name":null,"funder_award_id":"61901262","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G639214180","display_name":null,"funder_award_id":"61527804","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7277996951","display_name":null,"funder_award_id":"2016YFB1001003","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":89,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W648786980","https://openalex.org/W1493086929","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1902237438","https://openalex.org/W1931877416","https://openalex.org/W1985690171","https://openalex.org/W2016589492","https://openalex.org/W2064675550","https://openalex.org/W2099471712","https://openalex.org/W2108598243","https://openalex.org/W2111526438","https://openalex.org/W2118781169","https://openalex.org/W2194775991","https://openalex.org/W2342840547","https://openalex.org/W2542835211","https://openalex.org/W2567015638","https://openalex.org/W2584723080","https://openalex.org/W2607037079","https://openalex.org/W2613718673","https://openalex.org/W2745461083","https://openalex.org/W2755286543","https://openalex.org/W2770129969","https://openalex.org/W2774005037","https://openalex.org/W2778764040","https://openalex.org/W2799263800","https://openalex.org/W2805984364","https://openalex.org/W2884565639","https://openalex.org/W2896050315","https://openalex.org/W2909303996","https://openalex.org/W2926977875","https://openalex.org/W2942608247","https://openalex.org/W2950697717","https://openalex.org/W2955993284","https://openalex.org/W2962744691","https://openalex.org/W2962781483","https://openalex.org/W2962793481","https://openalex.org/W2962887844","https://openalex.org/W2962957031","https://openalex.org/W2963073614","https://openalex.org/W2963521239","https://openalex.org/W2963575117","https://openalex.org/W2963684088","https://openalex.org/W2963726321","https://openalex.org/W2963800628","https://openalex.org/W2963846044","https://openalex.org/W2964121744","https://openalex.org/W2964242925","https://openalex.org/W2964339842","https://openalex.org/W2964343989","https://openalex.org/W2964345285","https://openalex.org/W2964345792","https://openalex.org/W2964487155","https://openalex.org/W2964935470","https://openalex.org/W2966683369","https://openalex.org/W2967502099","https://openalex.org/W2974759213","https://openalex.org/W2981799368","https://openalex.org/W2987914945","https://openalex.org/W3010436080","https://openalex.org/W3023306062","https://openalex.org/W3034500398","https://openalex.org/W3035232877","https://openalex.org/W3109097593","https://openalex.org/W4287803913","https://openalex.org/W4288075590","https://openalex.org/W4288363736","https://openalex.org/W4294149591","https://openalex.org/W4297795161","https://openalex.org/W4298212519","https://openalex.org/W4320013936","https://openalex.org/W6620707391","https://openalex.org/W6621543089","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6640174482","https://openalex.org/W6676947618","https://openalex.org/W6677564776","https://openalex.org/W6704559304","https://openalex.org/W6728610325","https://openalex.org/W6731334075","https://openalex.org/W6746518932","https://openalex.org/W6751885507","https://openalex.org/W6752083267","https://openalex.org/W6753516098","https://openalex.org/W6757724268","https://openalex.org/W6765117743","https://openalex.org/W6770103389"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W17155033"],"abstract_inverted_index":{"The":[0,27],"emerging":[1],"vision-and-language":[2],"navigation":[3,148],"(VLN)":[4],"problem":[5],"aims":[6],"at":[7,158],"learning":[8,100,210,233,251],"to":[9,13,22,41,43,52,72,82,129,185,193,206,216,257],"navigate":[10],"an":[11,163],"agent":[12,39,63,93,128,155,188],"the":[14,23,38,44,48,53,59,62,66,70,73,83,92,96,113,122,127,134,145,151,154,159,187,195,198,209,218,227,242,249],"target":[15,74,160],"location":[16,75,161],"in":[17,267],"unseen":[18],"photo-realistic":[19],"environments":[20],"according":[21],"given":[24],"language":[25,49,79],"instruction.":[26],"main":[28],"challenges":[29],"of":[30,47,85,98,180,212,229,269],"VLN":[31,106],"arise":[32],"mainly":[33],"from":[34,116,133],"two":[35,181,232],"aspects:":[36],"first,":[37],"needs":[40],"attend":[42],"meaningful":[45],"paragraphs":[46],"instruction":[50],"corresponding":[51],"dynamically-varying":[54],"visual":[55,201],"environments;":[56],"second,":[57],"during":[58,121,150],"training":[60,89,123,152,221],"process,":[61,153],"usually":[64],"imitate":[65],"expert":[67],"demonstrations,":[68],"i.e.,":[69],"shortest-path":[71],"specified":[76],"by":[77,111],"associated":[78],"instructions.":[80],"Due":[81],"discrepancy":[84,219],"action":[86,115],"selection":[87],"between":[88,197,220],"and":[90,200,214,222,255,271],"inference,":[91],"solely":[94],"on":[95,241],"basis":[97],"imitation":[99,213],"does":[101],"not":[102],"perform":[103],"well.":[104],"Existing":[105],"approaches":[107,266],"address":[108],"this":[109],"issue":[110],"sampling":[112],"next":[114],"its":[117],"predicted":[118],"probability":[119],"distribution":[120],"process.":[124],"This":[125],"allows":[126],"explore":[130],"diverse":[131],"routes":[132],"environments,":[135],"yielding":[136],"higher":[137],"success":[138],"rates.":[139],"Nevertheless,":[140],"without":[141],"being":[142],"presented":[143],"with":[144,189],"golden":[146],"shortest":[147],"paths":[149],"may":[156],"arrive":[157],"through":[162],"unexpected":[164],"longer":[165],"route.":[166],"To":[167],"overcome":[168],"these":[169,231],"challenges,":[170],"we":[171],"design":[172],"a":[173,190],"cross-modal":[174],"grounding":[175],"module,":[176],"which":[177],"is":[178,253],"composed":[179],"complementary":[182,256],"attention":[183],"mechanisms,":[184],"equip":[186],"better":[191],"ability":[192],"track":[194],"correspondence":[196],"textual":[199],"modalities.":[202],"We":[203,224],"then":[204],"propose":[205],"recursively":[207],"alternate":[208],"schemes":[211,234],"exploration":[215],"narrow":[217],"inference.":[223],"further":[225],"exploit":[226],"advantages":[228],"both":[230],"via":[235],"adversarial":[236],"learning.":[237],"Extensive":[238],"experimental":[239],"results":[240],"Room-to-Room":[243],"(R2R)":[244],"benchmark":[245],"dataset":[246],"demonstrate":[247],"that":[248],"proposed":[250],"scheme":[252],"generalized":[254],"prior":[258],"arts.":[259],"Our":[260],"method":[261],"performs":[262],"well":[263],"against":[264],"state-of-the-art":[265],"terms":[268],"effectiveness":[270],"efficiency.":[272]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2020-12-07T00:00:00"}