{"id":"https://openalex.org/W3133869372","doi":"https://doi.org/10.1109/cvpr46437.2021.00835","title":"Structured Scene Memory for Vision-Language Navigation","display_name":"Structured Scene Memory for Vision-Language Navigation","publication_year":2021,"publication_date":"2021-06-01","ids":{"openalex":"https://openalex.org/W3133869372","doi":"https://doi.org/10.1109/cvpr46437.2021.00835","mag":"3133869372"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr46437.2021.00835","doi":"https://doi.org/10.1109/cvpr46437.2021.00835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr46437.2021.00835","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.03454","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101837435","display_name":"Hanqing Wang","orcid":"https://orcid.org/0000-0001-9264-1646","observed_orcids":["https://orcid.org/0000-0001-9264-1646"]},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanqing Wang","raw_affiliation_strings":["Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101433884","display_name":"Wenguan Wang","orcid":"https://orcid.org/0000-0002-0802-9567","observed_orcids":["https://orcid.org/0000-0002-0802-9567"]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Wenguan Wang","raw_affiliation_strings":["ETH Zurich","ETH Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101518752","display_name":"Wei Liang","orcid":"https://orcid.org/0000-0002-6509-4699","observed_orcids":["https://orcid.org/0000-0002-6509-4699"]},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Liang","raw_affiliation_strings":["Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032046813","display_name":"Caiming Xiong","orcid":"https://orcid.org/0000-0003-0349-8628","observed_orcids":["https://orcid.org/0000-0003-0349-8628"]},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Caiming Xiong","raw_affiliation_strings":["Salesforce Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Salesforce Research","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023184215","display_name":"Jianbing Shen","orcid":"https://orcid.org/0000-0003-2656-3082","observed_orcids":["https://orcid.org/0000-0003-2656-3082","https://orcid.org/0000-0003-1883-2086","https://orcid.org/0000-0002-4109-8353","https://orcid.org/0000-0003-0193-0384","https://orcid.org/0000-0002-4343-623X"]},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianbing Shen","raw_affiliation_strings":["Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.9757,"has_fulltext":true,"cited_by_count":129,"citation_normalized_percentile":{"value":0.97659755,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"8451","last_page":"8460"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5727999806404114,"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":0.5727999806404114,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.20589999854564667,"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/T11904","display_name":"Spatial Cognition and Navigation","score":0.06350000202655792,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/vision-and-language-navigation","display_name":"vision-and-language navigation","score":0.9950000047683716},{"id":"https://openalex.org/keywords/scene-representation","display_name":"scene representation","score":0.7129999995231628},{"id":"https://openalex.org/keywords/long-term-planning","display_name":"long-term planning","score":0.7670000195503235},{"id":"https://openalex.org/keywords/frontier-based-exploration","display_name":"frontier exploration","score":0.718999981880188},{"id":"https://openalex.org/keywords/robot-navigation","display_name":"robot navigation","score":0.44999998807907104}],"concepts":[{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.8112517595291138},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.77967768907547},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5994716286659241},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5499306917190552},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5204430222511292},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.48048558831214905},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4713670015335083},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.456675261259079},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.43218016624450684},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3903927803039551},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12352070212364197},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08787915110588074},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cvpr46437.2021.00835","doi":"https://doi.org/10.1109/cvpr46437.2021.00835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr46437.2021.00835","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2103.03454","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.03454","pdf_url":"https://arxiv.org/pdf/2103.03454","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2103.03454","doi":"https://doi.org/10.48550/arxiv.2103.03454","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.03454","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.03454","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.03454","pdf_url":"https://arxiv.org/pdf/2103.03454","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311649","display_name":"Ministry of Education","ror":"https://ror.org/036nq5137"},{"id":"https://openalex.org/F4320323110","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3133869372.pdf","grobid_xml":"https://content.openalex.org/works/W3133869372.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W1516027685","https://openalex.org/W1933065844","https://openalex.org/W1979266466","https://openalex.org/W2033819227","https://openalex.org/W2064675550","https://openalex.org/W2067619114","https://openalex.org/W2107667896","https://openalex.org/W2109142140","https://openalex.org/W2118781169","https://openalex.org/W2128990851","https://openalex.org/W2133564696","https://openalex.org/W2151887427","https://openalex.org/W2167839676","https://openalex.org/W2194775991","https://openalex.org/W2336416123","https://openalex.org/W2418628973","https://openalex.org/W2472819217","https://openalex.org/W2593841437","https://openalex.org/W2594903727","https://openalex.org/W2770387316","https://openalex.org/W2772545238","https://openalex.org/W2786472725","https://openalex.org/W2808213243","https://openalex.org/W2884565639","https://openalex.org/W2909303996","https://openalex.org/W2926977875","https://openalex.org/W2947178363","https://openalex.org/W2950527759","https://openalex.org/W2962744691","https://openalex.org/W2962789679","https://openalex.org/W2962812366","https://openalex.org/W2962887844","https://openalex.org/W2963245725","https://openalex.org/W2963726321","https://openalex.org/W2963846044","https://openalex.org/W2964308564","https://openalex.org/W2964339842","https://openalex.org/W2964343989","https://openalex.org/W2964935470","https://openalex.org/W2974759213","https://openalex.org/W2981799368","https://openalex.org/W2983335573","https://openalex.org/W2985026420","https://openalex.org/W2991186560","https://openalex.org/W3007299332","https://openalex.org/W3011144238","https://openalex.org/W3014266552","https://openalex.org/W3023306062","https://openalex.org/W3028588964","https://openalex.org/W3034500398","https://openalex.org/W3035232877","https://openalex.org/W3037881859","https://openalex.org/W3040922163","https://openalex.org/W3092825347","https://openalex.org/W3104753760","https://openalex.org/W3105521436","https://openalex.org/W3106641651","https://openalex.org/W3106806814","https://openalex.org/W3107069568","https://openalex.org/W4394655428"],"related_works":["https://openalex.org/W4401057329","https://openalex.org/W4414683986","https://openalex.org/W7221780794","https://openalex.org/W6929258680","https://openalex.org/W4312618696","https://openalex.org/W4400526991","https://openalex.org/W7134831160","https://openalex.org/W4398157060","https://openalex.org/W7077973791","https://openalex.org/W7147139544"],"abstract_inverted_index":{"Recently,":[0],"numerous":[1],"algorithms":[2,111],"have":[3],"been":[4],"developed":[5],"to":[6,18,42,68,139],"tackle":[7],"the":[8,71,92,124,128],"problem":[9],"of":[10],"vision-language":[11],"navigation":[12,133],"(VLN),":[13],"i.e.,":[14,122],"entailing":[15],"an":[16],"agent":[17],"navigate":[19],"3D":[20],"environments":[21],"through":[22],"following":[23],"linguistic":[24],"instructions.":[25],"However,":[26],"current":[27,105],"VLN":[28,149],"agents":[29],"simply":[30],"store":[31],"their":[32],"past":[33],"experiences/observations":[34],"as":[35,78],"latent":[36],"states":[37],"in":[38,91],"recurrent":[39],"networks,":[40],"failing":[41],"capture":[43],"environment":[44],"layouts":[45],"and":[46,85,88,108,142,153],"make":[47],"long-term":[48],"planning.":[49,144],"To":[50],"address":[51],"these":[52],"limitations,":[53],"we":[54],"propose":[55],"a":[56,79,96,118,130],"crucial":[57],"architecture,":[58],"called":[59],"Structured":[60],"Scene":[61],"Memory":[62],"(SSM).":[63],"It":[64,75],"is":[65,137],"compartmentalized":[66],"enough":[67],"accurately":[69],"memorize":[70],"percepts":[72],"during":[73],"navigation.":[74],"also":[76],"serves":[77],"structured":[80],"scene":[81],"representation,":[82],"which":[83],"captures":[84],"disentangles":[86],"visual":[87],"geometric":[89],"cues":[90],"environment.":[93],"SSM":[94,116],"has":[95],"collect-read":[97],"controller":[98],"that":[99,156],"adaptively":[100],"collects":[101],"information":[102],"for":[103,112],"supporting":[104],"decision":[106,134],"making":[107,135],"mimics":[109],"iterative":[110],"long-range":[113],"reasoning.":[114],"As":[115],"provides":[117],"complete":[119],"action":[120],"space,":[121],"all":[123],"navigable":[125],"places":[126],"on":[127,147,162],"map,":[129],"frontier-exploration":[131],"based":[132],"strategy":[136],"introduced":[138],"enable":[140],"efficient":[141],"global":[143],"Experiment":[145],"results":[146],"two":[148],"datasets":[150],"(i.e.,":[151],"R2R":[152],"R4R)":[154],"show":[155],"our":[157],"method":[158],"achieves":[159],"state-of-the-art":[160],"performance":[161],"several":[163],"metrics.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":26},{"year":2023,"cited_by_count":33},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":9}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-03-15T00:00:00"}
