{"id":"https://openalex.org/W4403510909","doi":"https://doi.org/10.1109/lra.2024.3483042","title":"Enhancing Scene Understanding for Vision-and-Language Navigation by Knowledge Awareness","display_name":"Enhancing Scene Understanding for Vision-and-Language Navigation by Knowledge Awareness","publication_year":2024,"publication_date":"2024-10-17","ids":{"openalex":"https://openalex.org/W4403510909","doi":"https://doi.org/10.1109/lra.2024.3483042"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2024.3483042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3483042","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-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/A5006605583","display_name":"Fang Gao","orcid":"https://orcid.org/0000-0003-1816-5420"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Gao","raw_affiliation_strings":["School of Electrical Engineering, Guangxi University, Nanning, China"],"raw_orcid":"https://orcid.org/0000-0003-1816-5420","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073287273","display_name":"Jingfeng Tang","orcid":"https://orcid.org/0000-0002-7924-976X"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingfeng Tang","raw_affiliation_strings":["School of Electrical Engineering, Guangxi University, Nanning, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100633426","display_name":"Jiabao Wang","orcid":"https://orcid.org/0000-0002-6371-9739"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiabao Wang","raw_affiliation_strings":["School of Electrical Engineering, Guangxi University, Nanning, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shaodong Li","orcid":"https://orcid.org/0000-0002-5034-8721"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaodong Li","raw_affiliation_strings":["School of Electrical Engineering, Guangxi University, Nanning, China"],"raw_orcid":"https://orcid.org/0000-0002-5034-8721","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048818071","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0002-3197-8103"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-3197-8103","affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3124,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81999659,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"9","issue":"12","first_page":"10874","last_page":"10881"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9397000074386597,"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":0.9397000074386597,"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/T12031","display_name":"Speech and dialogue systems","score":0.9297999739646912,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4622589647769928},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4608784019947052},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4104486405849457},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3329436182975769}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4622589647769928},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4608784019947052},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4104486405849457},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3329436182975769}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2024.3483042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3483042","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2745461083","https://openalex.org/W2896457183","https://openalex.org/W2926977875","https://openalex.org/W2951973805","https://openalex.org/W2963800628","https://openalex.org/W2970231061","https://openalex.org/W3004800063","https://openalex.org/W3034500398","https://openalex.org/W3034578524","https://openalex.org/W3034728521","https://openalex.org/W3035232877","https://openalex.org/W3100923070","https://openalex.org/W3107069568","https://openalex.org/W3109085430","https://openalex.org/W3169884222","https://openalex.org/W3172675210","https://openalex.org/W3174887918","https://openalex.org/W3176974620","https://openalex.org/W3192009892","https://openalex.org/W3195026654","https://openalex.org/W3206064582","https://openalex.org/W4205161929","https://openalex.org/W4214700710","https://openalex.org/W4226052928","https://openalex.org/W4312618696","https://openalex.org/W4312938887","https://openalex.org/W4385245566","https://openalex.org/W4385768138","https://openalex.org/W4386065508","https://openalex.org/W4386075539","https://openalex.org/W4390872429","https://openalex.org/W4394698889","https://openalex.org/W4401990649","https://openalex.org/W4402354022","https://openalex.org/W4402354030","https://openalex.org/W6748848655","https://openalex.org/W6751885507","https://openalex.org/W6765527290","https://openalex.org/W6791353385","https://openalex.org/W6803039797"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Vision-and-Language":[0],"Navigation":[1],"(VLN)":[2],"has":[3],"garnered":[4],"widespread":[5],"attention":[6],"and":[7,76,97,110,148,164,201],"research":[8],"interest":[9],"due":[10],"to":[11,33,119,130],"its":[12],"potential":[13],"applications":[14],"in":[15,21,25,78,87,155,188],"real-world":[16],"scenarios.":[17],"Despite":[18],"significant":[19],"progress":[20],"the":[22,48,59,79,120,132,136,149,169,189,198,205,208],"VLN":[23],"field":[24],"recent":[26],"years,":[27],"limitations":[28],"persist.":[29],"Many":[30],"agents":[31],"struggle":[32],"make":[34],"accurate":[35],"decisions":[36],"when":[37],"faced":[38],"with":[39,179],"similar":[40],"candidate":[41],"views":[42],"during":[43],"navigation,":[44],"relying":[45],"solely":[46],"on":[47,197],"overall":[49],"features":[50],"of":[51,61,104,135,207],"these":[52],"views.":[53],"This":[54],"challenge":[55],"primarily":[56],"arises":[57],"from":[58],"lack":[60],"common-sense":[62],"knowledge":[63,70,85,161,177],"about":[64],"room":[65,69,83,111,116,140,159],"layouts.":[66],"Recognizing":[67],"that":[68],"can":[71],"establish":[72],"relationships":[73,94,100],"between":[74,95,101],"rooms":[75,96],"objects":[77,106],"environment,":[80],"we":[81,182,193],"construct":[82],"layout":[84,117,141,160],"described":[86],"natural":[88],"language":[89],"by":[90,138],"leveraging":[91,139],"BLIP-2,":[92],"including":[93],"individual":[98,105],"objects,":[99,102],"attributes":[103],"(such":[107],"as":[108],"color),":[109],"types,":[112],"thus":[113],"providing":[114],"comprehensive":[115],"information":[118,178],"agent.":[121],"We":[122],"propose":[123],"a":[124],"Knowledge-Enhanced":[125],"Scene":[126],"Understanding":[127],"(KESU)":[128],"model":[129],"augment":[131],"agent's":[133,170],"understanding":[134],"environment":[137],"knowledge.":[142],"The":[143],"Instruction":[144],"Augmentation":[145],"Module":[146,153],"(IA)":[147],"Knowledge":[150],"History":[151],"Fusion":[152,186],"(KHF)":[154],"KESU":[156],"respectively":[157],"provide":[158],"for":[162],"instructions":[163],"vision-history":[165],"features,":[166,181],"thereby":[167],"enhancing":[168],"navigation":[171],"abilities.":[172],"To":[173],"more":[174],"effectively":[175],"integrate":[176],"instruction":[180],"introduce":[183],"Dynamic":[184],"Residual":[185],"(DRF)":[187],"IA":[190],"module.":[191],"Finally,":[192],"conduct":[194],"extensive":[195],"experiments":[196],"R2R,":[199],"REVERIE,":[200],"SOON":[202],"datasets,":[203],"demonstrating":[204],"effectiveness":[206],"proposed":[209],"approach.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}