{"id":"https://openalex.org/W4304097971","doi":"https://doi.org/10.1145/3503161.3548281","title":"Target-Driven Structured Transformer Planner for Vision-Language Navigation","display_name":"Target-Driven Structured Transformer Planner for Vision-Language Navigation","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304097971","doi":"https://doi.org/10.1145/3503161.3548281"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548281","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548281","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","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/A5023158258","display_name":"Yusheng Zhao","orcid":"https://orcid.org/0000-0002-5893-504X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yusheng Zhao","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100730367","display_name":"Jinyu Chen","orcid":"https://orcid.org/0009-0002-7106-8312"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinyu Chen","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101436165","display_name":"Chen Gao","orcid":"https://orcid.org/0000-0002-7530-8056"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Gao","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101433884","display_name":"Wenguan Wang","orcid":"https://orcid.org/0000-0002-0802-9567"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wenguan Wang","raw_affiliation_strings":["University of Technology Sydney, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044989027","display_name":"Lirong Yang","orcid":"https://orcid.org/0000-0002-6378-8451"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lirong Yang","raw_affiliation_strings":["Meituan Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100764066","display_name":"Haibing Ren","orcid":"https://orcid.org/0009-0002-5751-7062"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haibing Ren","raw_affiliation_strings":["Meituan Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085989114","display_name":"Huaxia Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huaxia Xia","raw_affiliation_strings":["Meituan Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan Inc., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100330138","display_name":"Si Liu","orcid":"https://orcid.org/0000-0002-9180-2935"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Si Liu","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5023158258"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":2.8079,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.93463449,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4194","last_page":"4203"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9991999864578247,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9977999925613403,"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/planner","display_name":"Planner","score":0.841052770614624},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7861104011535645},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6641062498092651},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.5131364464759827},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.511830747127533},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5109123587608337},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.466114342212677},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4485017657279968},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.43468227982521057},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4329943358898163},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41676628589630127},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3565429449081421},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3267552852630615},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20445993542671204},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10807874798774719}],"concepts":[{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.841052770614624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7861104011535645},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6641062498092651},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5131364464759827},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.511830747127533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5109123587608337},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.466114342212677},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4485017657279968},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43468227982521057},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4329943358898163},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41676628589630127},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3565429449081421},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3267552852630615},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20445993542671204},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10807874798774719},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548281","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548281","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/13"}],"awards":[{"id":"https://openalex.org/G359651204","display_name":null,"funder_award_id":"62122010,61876177","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"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2099618002","https://openalex.org/W2593841437","https://openalex.org/W2594519801","https://openalex.org/W2602275733","https://openalex.org/W2953127211","https://openalex.org/W2962744691","https://openalex.org/W2963800628","https://openalex.org/W2963846044","https://openalex.org/W2964935470","https://openalex.org/W2974759213","https://openalex.org/W2981799368","https://openalex.org/W3009928773","https://openalex.org/W3034201026","https://openalex.org/W3034500398","https://openalex.org/W3034758614","https://openalex.org/W3035232877","https://openalex.org/W3040922163","https://openalex.org/W3092825347","https://openalex.org/W3095974555","https://openalex.org/W3096609285","https://openalex.org/W3098358101","https://openalex.org/W3105274166","https://openalex.org/W3106571068","https://openalex.org/W3106641651","https://openalex.org/W3106806814","https://openalex.org/W3109097593","https://openalex.org/W3109380382","https://openalex.org/W3138516171","https://openalex.org/W3165915253","https://openalex.org/W3174887918","https://openalex.org/W3176495323","https://openalex.org/W3195026654","https://openalex.org/W3206064582","https://openalex.org/W3206064780","https://openalex.org/W4212774754","https://openalex.org/W4214540501","https://openalex.org/W4214700710","https://openalex.org/W4226052928","https://openalex.org/W4312581490","https://openalex.org/W4312749817","https://openalex.org/W6605584388"],"related_works":["https://openalex.org/W2380179524","https://openalex.org/W4283365723","https://openalex.org/W2963001125","https://openalex.org/W2091233881","https://openalex.org/W2352366064","https://openalex.org/W4250820896","https://openalex.org/W2124102101","https://openalex.org/W4250305970","https://openalex.org/W1484550171","https://openalex.org/W1570928019"],"abstract_inverted_index":{"Vision-language":[0],"navigation":[1,25],"is":[2,30,137],"the":[3,20,23,75,94,126],"task":[4],"of":[5,74,129],"directing":[6],"an":[7,66],"embodied":[8],"agent":[9],"to":[10],"navigate":[11],"in":[12,43,80],"3D":[13],"scenes":[14],"with":[15],"natural":[16],"language":[17],"instructions.":[18],"For":[19],"agent,":[21],"inferring":[22],"long-term":[24,76],"target":[26,77],"from":[27],"visual-linguistic":[28],"clues":[29],"crucial":[31],"for":[32,56,71,103],"reliable":[33],"path":[34],"planning,":[35],"which,":[36],"however,":[37],"has":[38],"rarely":[39],"been":[40],"studied":[41],"before":[42],"literature.":[44],"In":[45,83],"this":[46],"article,":[47],"we":[48,64,85],"propose":[49],"a":[50,87,99],"Target-Driven":[51],"Structured":[52,88],"Transformer":[53,89],"Planner":[54,90],"(TD-STP)":[55],"long-horizon":[57],"goal-guided":[58],"and":[59,105,123,131],"room":[60,96],"layout-aware":[61],"navigation.":[62],"Specifically,":[63],"devise":[65],"Imaginary":[67],"Scene":[68],"Tokenization":[69],"mechanism":[70],"explicit":[72],"estimation":[73],"(even":[78],"located":[79],"unexplored":[81],"environments).":[82],"addition,":[84],"design":[86],"which":[91],"elegantly":[92],"incorporates":[93],"explored":[95],"layout":[97],"into":[98],"neural":[100],"attention":[101],"architecture":[102],"structured":[104],"global":[106],"planning.":[107],"Experimental":[108],"results":[109],"demonstrate":[110],"that":[111],"our":[112],"TD-STP":[113],"substantially":[114],"improves":[115],"previous":[116],"best":[117],"methods'":[118],"success":[119],"rate":[120],"by":[121],"2%":[122],"5%":[124],"on":[125],"test":[127],"set":[128],"R2R":[130],"REVERIE":[132],"benchmarks,":[133],"respectively.":[134],"Our":[135],"code":[136],"available":[138],"at":[139],"https://github.com/YushengZhao/TD-STP.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":19}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}