{"id":"https://openalex.org/W7126038551","doi":"https://doi.org/10.1109/tpami.2026.3658949","title":"Fine-Grained Alignment Supervision Matters in Vision-and-Language Navigation","display_name":"Fine-Grained Alignment Supervision Matters in Vision-and-Language Navigation","publication_year":2026,"publication_date":"2026-01-29","ids":{"openalex":"https://openalex.org/W7126038551","doi":"https://doi.org/10.1109/tpami.2026.3658949","pmid":"https://pubmed.ncbi.nlm.nih.gov/41610363"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3658949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3658949","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5122905422","display_name":"Keji He","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keji He","raw_affiliation_strings":["Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0001-5136-8444","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100654486","display_name":"Yun Huang","orcid":"https://orcid.org/0000-0003-1549-1669"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Huang","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8239-7229","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124190605","display_name":"Ya Jing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ya Jing","raw_affiliation_strings":["ByteDance AI Lab, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123774479","display_name":"Qi Wu","orcid":null},"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, University of Adelaide, Adelaide, SA, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3631-256X","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Adelaide, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124165967","display_name":"Liang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Wang","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5224-8647","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.2709,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.93816278,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"48","issue":"6","first_page":"6525","last_page":"6540"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9739000201225281,"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":0.9739000201225281,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.003700000001117587,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.003599999938160181,"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/process","display_name":"Process (computing)","score":0.7418000102043152},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7028999924659729},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.64410001039505},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.477400004863739},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.42579999566078186},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4221000075340271}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8050000071525574},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.7418000102043152},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7028999924659729},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.64410001039505},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.477400004863739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4758000075817108},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.42579999566078186},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4230000078678131},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4221000075340271},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3319000005722046},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.274399995803833},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2644999921321869}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2026.3658949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3658949","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41610363","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41610363","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6210606694221497,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1383591865","display_name":null,"funder_award_id":"62276261","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3820018362","display_name":null,"funder_award_id":"tsqn202507043","funder_id":"https://openalex.org/F4320326185","funder_display_name":"Taishan Scholar Foundation of Shandong Province"},{"id":"https://openalex.org/G5156147101","display_name":null,"funder_award_id":"62236010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7461287619","display_name":null,"funder_award_id":"L252033","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G8053739178","display_name":null,"funder_award_id":"62322607","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8601551012","display_name":null,"funder_award_id":"ZR2025QC1566","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null},{"id":"https://openalex.org/F4320326185","display_name":"Taishan Scholar Foundation of Shandong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1933349210","https://openalex.org/W2064675550","https://openalex.org/W2139501017","https://openalex.org/W2194775991","https://openalex.org/W2296073425","https://openalex.org/W2342543219","https://openalex.org/W2732026016","https://openalex.org/W2890502146","https://openalex.org/W2896457183","https://openalex.org/W2926977875","https://openalex.org/W2951973805","https://openalex.org/W2963040148","https://openalex.org/W2963467339","https://openalex.org/W2963758027","https://openalex.org/W2963800628","https://openalex.org/W2963846044","https://openalex.org/W2963966654","https://openalex.org/W2964935470","https://openalex.org/W2981799368","https://openalex.org/W2987914945","https://openalex.org/W3002515698","https://openalex.org/W3034253961","https://openalex.org/W3034500398","https://openalex.org/W3034984754","https://openalex.org/W3100923070","https://openalex.org/W3105521436","https://openalex.org/W3107069568","https://openalex.org/W3108432914","https://openalex.org/W3109085430","https://openalex.org/W3109097593","https://openalex.org/W3172675210","https://openalex.org/W3179213173","https://openalex.org/W3206064582","https://openalex.org/W4200630135","https://openalex.org/W4226052928","https://openalex.org/W4312096566","https://openalex.org/W4312238277","https://openalex.org/W4312434279","https://openalex.org/W4312501707","https://openalex.org/W4312581490","https://openalex.org/W4312618696","https://openalex.org/W4312938887","https://openalex.org/W4385245566","https://openalex.org/W4385574210","https://openalex.org/W4386952228","https://openalex.org/W4387968661","https://openalex.org/W4390871755","https://openalex.org/W4394627367","https://openalex.org/W4394984751","https://openalex.org/W4402944034","https://openalex.org/W7133214964","https://openalex.org/W7133235210","https://openalex.org/W7133238687"],"related_works":[],"abstract_inverted_index":{"The":[0,151],"Vision-and-Language":[1],"Navigation":[2],"(VLN)":[3],"task":[4],"involves":[5],"an":[6],"agent":[7],"navigating":[8],"within":[9],"3D":[10],"indoor":[11],"environments":[12],"based":[13],"on":[14,44,114],"provided":[15],"instructions.":[16],"Achieving":[17],"cross-modal":[18,46,61,164],"alignment":[19,47,62,165],"presents":[20],"one":[21],"of":[22,59,97,108,117],"the":[23,30,38,57,93,98,105,109,115,118,156,162],"most":[24],"critical":[25],"challenges":[26],"in":[27,48,88],"VLN,":[28],"as":[29],"predicted":[31],"trajectory":[32],"needs":[33],"to":[34,55,80,90],"precisely":[35],"align":[36],"with":[37],"given":[39],"instruction.":[40],"This":[41,77],"paper":[42],"focuses":[43],"addressing":[45],"VLN":[49,73],"from":[50,65,101],"a":[51,70,147],"fine-grained":[52,72,83,99,136,157],"perspective.":[53],"Firstly,":[54],"address":[56],"issue":[58],"weak":[60],"supervision":[63,84],"arising":[64],"coarse-grained":[66],"data,":[67,137],"we":[68,103,138],"introduce":[69,146],"human-annotated":[71],"dataset":[74,78],"called":[75],"Landmark-RxR.":[76],"aims":[79],"offer":[81],"precise,":[82],"for":[85,142],"VLN.":[86],"Secondly,":[87],"order":[89],"comprehensively":[91],"demonstrate":[92,154],"potential":[94],"and":[95,130,145],"advantage":[96],"data":[100,124,158],"Landmark-RxR,":[102],"explore":[104],"core":[106],"components":[107,122],"training":[110,119,126],"process":[111],"that":[112,155],"depend":[113],"characteristics":[116],"data.":[120],"These":[121],"include":[123],"augmentation,":[125],"paradigm,":[127],"reward":[128],"shaping,":[129],"navigation":[131],"loss":[132],"design.":[133],"Leveraging":[134],"our":[135],"carefully":[139],"design":[140],"methods":[141],"handling":[143],"them":[144],"novel":[148],"evaluation":[149],"mechanism.":[150],"experimental":[152],"results":[153],"can":[159],"effectively":[160],"improve":[161],"agent's":[163],"ability.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-01-30T00:00:00"}