{"id":"https://openalex.org/W4417470533","doi":"https://doi.org/10.1109/tce.2025.3645249","title":"Indoor Scene Recognition in Vision-and-Language Navigation","display_name":"Indoor Scene Recognition in Vision-and-Language Navigation","publication_year":2025,"publication_date":"2025-12-18","ids":{"openalex":"https://openalex.org/W4417470533","doi":"https://doi.org/10.1109/tce.2025.3645249"},"language":null,"primary_location":{"id":"doi:10.1109/tce.2025.3645249","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tce.2025.3645249","pdf_url":null,"source":{"id":"https://openalex.org/S126824455","display_name":"IEEE Transactions on Consumer Electronics","issn_l":"0098-3063","issn":["0098-3063","1558-4127"],"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 Transactions on Consumer Electronics","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/A5025326577","display_name":"Hongtao Zhang","orcid":"https://orcid.org/0000-0001-9868-1243"},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongtao Zhang","raw_affiliation_strings":["College of Information Science and Technology and the Engineering Research Center of Digitized Textile and Apparel Technology, Ministry of Education, Donghua University, Shanghai, China","College of Information Science and Technology, Donghua University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9868-1243","affiliations":[{"raw_affiliation_string":"College of Information Science and Technology and the Engineering Research Center of Digitized Textile and Apparel Technology, Ministry of Education, Donghua University, Shanghai, China","institution_ids":["https://openalex.org/I181326427"]},{"raw_affiliation_string":"College of Information Science and Technology, Donghua University, Shanghai, China","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070842891","display_name":"Yuankai Qi","orcid":"https://orcid.org/0000-0003-4312-5682"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yuankai Qi","raw_affiliation_strings":["School of Computing, Faculty of Science and Engineering, Macquarie University, Sydney, NSW, Australia","Faculty of Science and Engineering, School of Computing, Macquarie University, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0003-4312-5682","affiliations":[{"raw_affiliation_string":"School of Computing, Faculty of Science and Engineering, Macquarie University, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I99043593"]},{"raw_affiliation_string":"Faculty of Science and Engineering, School of Computing, Macquarie University, Sydney, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061195038","display_name":"Mingbo Zhao","orcid":"https://orcid.org/0000-0003-0381-4360"},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingbo Zhao","raw_affiliation_strings":["College of Information Science and Technology and the Engineering Research Center of Digitized Textile and Apparel Technology, Ministry of Education, Donghua University, Shanghai, China","College of Information Science and Technology, Donghua University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0381-4360","affiliations":[{"raw_affiliation_string":"College of Information Science and Technology and the Engineering Research Center of Digitized Textile and Apparel Technology, Ministry of Education, Donghua University, Shanghai, China","institution_ids":["https://openalex.org/I181326427"]},{"raw_affiliation_string":"College of Information Science and Technology, Donghua University, Shanghai, China","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100673298","display_name":"Yuping Liu","orcid":"https://orcid.org/0009-0006-3203-7360"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuping Liu","raw_affiliation_strings":["Academy for Engineering and Technology, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-3203-7360","affiliations":[{"raw_affiliation_string":"Academy for Engineering and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37765213,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"72","issue":"1","first_page":"1216","last_page":"1222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9535999894142151,"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":0.9535999894142151,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.014499999582767487,"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":0.00419999985024333,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5899999737739563},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4341000020503998},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.414900004863739},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4000999927520752},{"id":"https://openalex.org/keywords/scene-statistics","display_name":"Scene statistics","score":0.3767000138759613},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3522000014781952},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.33970001339912415},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3271999955177307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7716000080108643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6725999712944031},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5899999737739563},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5824000239372253},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4341000020503998},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.414900004863739},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4000999927520752},{"id":"https://openalex.org/C197654239","wikidata":"https://www.wikidata.org/wiki/Q7430757","display_name":"Scene statistics","level":3,"score":0.3767000138759613},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3522000014781952},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33970001339912415},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.30079999566078186},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C117623542","wikidata":"https://www.wikidata.org/wiki/Q621974","display_name":"Automatic target recognition","level":3,"score":0.27810001373291016},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2646999955177307},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tce.2025.3645249","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tce.2025.3645249","pdf_url":null,"source":{"id":"https://openalex.org/S126824455","display_name":"IEEE Transactions on Consumer Electronics","issn_l":"0098-3063","issn":["0098-3063","1558-4127"],"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 Transactions on Consumer Electronics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2847099075","display_name":"\u57fa\u4e8e\u7aef\u5bf9\u7aef\u6df1\u5ea6\u7279\u5f81\u8868\u8fbe\u548c\u56fe\u7f51\u7edc\u6392\u5e8f\u7684\u6d77\u91cf\u56fe\u50cf\u68c0\u7d22\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61971121","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4435577787","display_name":null,"funder_award_id":"2022ZDZX1038","funder_id":"https://openalex.org/F4320333642","funder_display_name":"Scientific Research Foundation of Hunan Provincial Education Department"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320333642","display_name":"Scientific Research Foundation of Hunan Provincial Education Department","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Indoor":[0],"scene":[1,38,164],"recognition":[2,39,165],"is":[3],"a":[4,105,124],"crucial":[5],"component":[6],"in":[7,73,96,133,151,162],"vision-and-language":[8],"navigation":[9],"(VLN),":[10],"which":[11,41],"involves":[12],"guiding":[13],"an":[14],"agent":[15],"to":[16,65],"navigate":[17],"through":[18],"unseen,":[19],"photo-realistic":[20],"environments":[21],"using":[22,110],"natural":[23],"language":[24],"instructions.":[25],"However,":[26],"existing":[27],"researches":[28],"have":[29],"not":[30],"yet":[31],"endowed":[32],"VLN":[33],"agents":[34,72],"with":[35],"robust":[36],"indoor":[37,163],"capabilities,":[40],"are":[42],"essential":[43],"for":[44,115],"enhancing":[45],"the":[46,58,67,88,94,130,134,148],"agent\u2019s":[47],"spatial":[48,68],"perception":[49,69],"and":[50,112,139],"environmental":[51],"understanding.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56,103],"introduce":[57],"Room-to-Room":[59],"Scene":[60],"Recognition":[61],"(R2R-SR)":[62],"dataset,":[63],"designed":[64],"enhance":[66],"capabilities":[70],"of":[71,127],"VLN.":[74],"The":[75,144],"R2R-SR":[76],"dataset":[77],"includes":[78],"7,283":[79],"images":[80],"categorized":[81],"into":[82],"10":[83],"room":[84,101,157],"classes,":[85],"sourced":[86],"from":[87],"Matterport3D":[89],"(MP3D)":[90],"simulator.":[91],"To":[92],"alleviate":[93],"imbalance":[95],"training":[97],"data":[98,116],"distribution":[99],"across":[100,155],"categories,":[102,158],"propose":[104],"panoramic":[106],"environment":[107],"generation":[108],"technique":[109],"Llava":[111],"Stable":[113],"Diffusion":[114],"Augmentation":[117],"(LSDA).":[118],"Our":[119],"proposed":[120],"LSDA-based":[121],"model":[122],"achieves":[123],"Top-1":[125],"accuracy":[126],"75.9%,":[128],"outperforming":[129],"best":[131],"competitors":[132],"convolutional":[135],"neural":[136],"network":[137],"(CNN)":[138],"vision":[140],"transformer":[141],"(ViT)":[142],"domains.":[143],"qualitative":[145],"results":[146],"highlight":[147],"model\u2019s":[149],"proficiency":[150],"identifying":[152],"distinct":[153],"features":[154],"various":[156],"showcasing":[159],"its":[160],"effectiveness":[161],"tasks.":[166]},"counts_by_year":[],"updated_date":"2026-03-26T06:05:38.182114","created_date":"2025-12-18T00:00:00"}