{"id":"https://openalex.org/W4285102489","doi":"https://doi.org/10.1109/icra46639.2022.9811921","title":"Depth-Aware Vision-and-Language Navigation using Scene Query Attention Network","display_name":"Depth-Aware Vision-and-Language Navigation using Scene Query Attention Network","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W4285102489","doi":"https://doi.org/10.1109/icra46639.2022.9811921"},"language":"en","primary_location":{"id":"doi:10.1109/icra46639.2022.9811921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9811921","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Robotics and Automation (ICRA)","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/A5008661936","display_name":"Sinan Tan","orcid":"https://orcid.org/0000-0003-2035-2479"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sinan Tan","raw_affiliation_strings":["Tsinghua University, the National Research Center for Information Science and Technology,Department of Computer Science and Technology,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, the National Research Center for Information Science and Technology,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111957291","display_name":"Meng-Meng Ge","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengmeng Ge","raw_affiliation_strings":["Tsinghua University, the National Research Center for Information Science and Technology,Department of Computer Science and Technology,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, the National Research Center for Information Science and Technology,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101833400","display_name":"Di Guo","orcid":"https://orcid.org/0000-0002-9816-0103"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Guo","raw_affiliation_strings":["Tsinghua University, the National Research Center for Information Science and Technology,Department of Computer Science and Technology,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, the National Research Center for Information Science and Technology,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041101317","display_name":"Huaping Liu","orcid":"https://orcid.org/0000-0002-4042-6044"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaping Liu","raw_affiliation_strings":["Tsinghua University, the National Research Center for Information Science and Technology,Department of Computer Science and Technology,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, the National Research Center for Information Science and Technology,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055546056","display_name":"Fuchun Sun","orcid":"https://orcid.org/0000-0003-3546-6305"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuchun Sun","raw_affiliation_strings":["Tsinghua University, the National Research Center for Information Science and Technology,Department of Computer Science and Technology,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, the National Research Center for Information Science and Technology,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5008661936"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.1795,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.49240596,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"9390","last_page":"9396"},"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":0.9988999962806702,"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":0.9986000061035156,"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":0.8205327987670898},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6312640309333801},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5823015570640564},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5746454000473022},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5001316070556641},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4909961521625519},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.48062747716903687},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.45665231347084045},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4485437572002411},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.440273255109787},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4266134202480316},{"id":"https://openalex.org/keywords/semantic-mapping","display_name":"Semantic mapping","score":0.41842538118362427}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8205327987670898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6312640309333801},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5823015570640564},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5746454000473022},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5001316070556641},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4909961521625519},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48062747716903687},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.45665231347084045},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4485437572002411},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.440273255109787},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4266134202480316},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.41842538118362427},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra46639.2022.9811921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9811921","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4324903763","display_name":null,"funder_award_id":"62025304","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2772545238","https://openalex.org/W2805984364","https://openalex.org/W2909303996","https://openalex.org/W2926977875","https://openalex.org/W2951973805","https://openalex.org/W2954003188","https://openalex.org/W2959918500","https://openalex.org/W2962744691","https://openalex.org/W2963800628","https://openalex.org/W2964935470","https://openalex.org/W2967186499","https://openalex.org/W2970340522","https://openalex.org/W2974759213","https://openalex.org/W2987914945","https://openalex.org/W3034253961","https://openalex.org/W3034500398","https://openalex.org/W3034578524","https://openalex.org/W3035232877","https://openalex.org/W3040041096","https://openalex.org/W3096609285","https://openalex.org/W3105274166","https://openalex.org/W3106641651","https://openalex.org/W3107069568","https://openalex.org/W3107094551","https://openalex.org/W3109085430","https://openalex.org/W3109097593","https://openalex.org/W3138516171","https://openalex.org/W3158068997","https://openalex.org/W3166807227","https://openalex.org/W3172675210","https://openalex.org/W3174887918","https://openalex.org/W6746700414","https://openalex.org/W6746826305","https://openalex.org/W6751885507","https://openalex.org/W6757290401","https://openalex.org/W6757724268","https://openalex.org/W6760910512","https://openalex.org/W6765108809","https://openalex.org/W6765527290","https://openalex.org/W6774959054","https://openalex.org/W6780443396","https://openalex.org/W6784287907","https://openalex.org/W6786303254","https://openalex.org/W6794832151"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W1974414866","https://openalex.org/W2057568687","https://openalex.org/W2063982682","https://openalex.org/W2338543196","https://openalex.org/W1544691147"],"abstract_inverted_index":{"Vision-and-language":[0],"navigation":[1,20],"(VLN)":[2],"has":[3,43],"been":[4],"an":[5],"important":[6],"task":[7,80],"in":[8,37,69,141,174],"the":[9,38,62,65,78,95,142,154,167,171,178],"field":[10],"of":[11,64,111,114,163],"Robotics":[12],"and":[13,100,127,182],"Computer":[14],"Vision.":[15],"However,":[16],"most":[17,183],"existing":[18,184],"vision-and-language":[19],"models":[21,54,186],"only":[22,56],"use":[23,90,190],"features":[24],"extracted":[25],"from":[26,86],"RGB":[27],"observation":[28],"as":[29],"input,":[30],"while":[31],"robots":[32],"can":[33],"utilize":[34],"depth":[35,50],"sensors":[36],"real":[39],"world.":[40],"Existing":[41],"research":[42],"also":[44],"shown":[45],"that":[46,187],"simply":[47],"adding":[48],"a":[49,58,74,115,124,136,147,160],"stream":[51],"to":[52,61,92],"neural":[53],"could":[55,120],"provide":[57],"marginal":[59],"improvement":[60],"performance":[63],"VLN":[66,79],"task.":[67],"Therefore,":[68],"our":[70],"work,":[71],"we":[72],"develop":[73],"novel":[75],"method":[76,119,181],"for":[77,170],"using":[81],"semantic":[82,96,109],"map":[83,97],"observations":[84],"built":[85],"RGB-D":[87,180],"input.":[88],"We":[89],"vision-pretraining":[91],"efficiently":[93],"encode":[94],"with":[98,123,146,153],"CNN":[99],"scene":[101],"query":[102],"attention":[103],"network":[104],"by":[105],"answering":[106],"queries":[107],"about":[108],"information":[110],"specific":[112],"regions":[113],"scene.":[116],"The":[117],"proposed":[118],"be":[121],"used":[122,151],"simple":[125],"model":[126],"does":[128],"not":[129,189],"require":[130],"large-scale":[131,191],"vision-language":[132,192],"transformer":[133],"pretraining,":[134],"bringing":[135],"more":[137],"than":[138],"10%":[139],"increase":[140],"success":[143,161],"rate":[144,162],"compared":[145],"baseline":[148],"model.":[149],"When":[150],"together":[152],"Speaker-Follower":[155],"training":[156],"technique,":[157],"it":[158],"achieves":[159],"58":[164],"%":[165],"on":[166],"test":[168],"set":[169],"R2R":[172],"dataset":[173],"single-run":[175],"setting,":[176],"outperforming":[177],"previous":[179],"RGB-only":[185],"do":[188],"transformers":[193],"pretraining.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-22T08:09:32.410652","created_date":"2025-10-10T00:00:00"}