{"id":"https://openalex.org/W4411640067","doi":"https://doi.org/10.1109/tnnls.2025.3581411","title":"Argus: Leveraging Multiview Images for Improved 3-D Scene Understanding With Large Language Models","display_name":"Argus: Leveraging Multiview Images for Improved 3-D Scene Understanding With Large Language Models","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4411640067","doi":"https://doi.org/10.1109/tnnls.2025.3581411","pmid":"https://pubmed.ncbi.nlm.nih.gov/40560695"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3581411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3581411","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.12916","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yifan Xu","orcid":"https://orcid.org/0009-0004-5136-9083"},"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":"Yifan Xu","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-5136-9083","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011133247","display_name":"Chao Zhang","orcid":"https://orcid.org/0009-0008-3780-7453"},"institutions":[{"id":"https://openalex.org/I4210093609","display_name":"Digital China Health (China)","ror":"https://ror.org/00n49pr77","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093609"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Beijing Digital Native Digital City Research Center, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-3780-7453","affiliations":[{"raw_affiliation_string":"Beijing Digital Native Digital City Research Center, Beijing, China","institution_ids":["https://openalex.org/I4210093609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104169853","display_name":"Hanqi Jiang","orcid":"https://orcid.org/0009-0007-2778-959X"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hanqi Jiang","raw_affiliation_strings":["School of Computing, University of Georgia, Athens, GA, USA"],"raw_orcid":"https://orcid.org/0009-0007-2778-959X","affiliations":[{"raw_affiliation_string":"School of Computing, University of Georgia, Athens, GA, USA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaoyan Wang","orcid":"https://orcid.org/0009-0001-3711-3477"},"institutions":[{"id":"https://openalex.org/I4210093609","display_name":"Digital China Health (China)","ror":"https://ror.org/00n49pr77","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093609"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyan Wang","raw_affiliation_strings":["Beijing Digital Native Digital City Research Center, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-3711-3477","affiliations":[{"raw_affiliation_string":"Beijing Digital Native Digital City Research Center, Beijing, China","institution_ids":["https://openalex.org/I4210093609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067770870","display_name":"Ruifei Ma","orcid":"https://orcid.org/0000-0002-2546-3867"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruifei Ma","raw_affiliation_strings":["School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-8481-2906","affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100633409","display_name":"Yiwei Li","orcid":"https://orcid.org/0000-0002-8380-4164"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiwei Li","raw_affiliation_strings":["School of Computing, University of Georgia, Athens, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, University of Georgia, Athens, GA, USA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068480230","display_name":"Zihao Wu","orcid":"https://orcid.org/0000-0001-7483-6570"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zihao Wu","raw_affiliation_strings":["School of Computing, University of Georgia, Athens, GA, USA"],"raw_orcid":"https://orcid.org/0000-0001-7483-6570","affiliations":[{"raw_affiliation_string":"School of Computing, University of Georgia, Athens, GA, USA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103176788","display_name":"Zeju Li","orcid":"https://orcid.org/0009-0009-5453-4394"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zeju Li","raw_affiliation_strings":["Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0009-5453-4394","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xiangde Liu","orcid":"https://orcid.org/0009-0008-0689-8401"},"institutions":[{"id":"https://openalex.org/I4210093609","display_name":"Digital China Health (China)","ror":"https://ror.org/00n49pr77","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093609"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangde Liu","raw_affiliation_strings":["Beijing Digital Native Digital City Research Center, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-0689-8401","affiliations":[{"raw_affiliation_string":"Beijing Digital Native Digital City Research Center, Beijing, China","institution_ids":["https://openalex.org/I4210093609"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":1.0943,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78747868,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"36","issue":"10","first_page":"17679","last_page":"17692"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9969000220298767,"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":0.9968000054359436,"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/argus","display_name":"Argus","score":0.908492922782898},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6609327793121338},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5328982472419739},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.503170907497406},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3839952051639557}],"concepts":[{"id":"https://openalex.org/C2776760603","wikidata":"https://www.wikidata.org/wiki/Q3622471","display_name":"Argus","level":2,"score":0.908492922782898},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6609327793121338},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5328982472419739},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.503170907497406},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3839952051639557},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tnnls.2025.3581411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3581411","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:40560695","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40560695","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 neural networks and learning systems","raw_type":null},{"id":"pmh:oai:arXiv.org:2507.12916","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.12916","pdf_url":"https://arxiv.org/pdf/2507.12916","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.12916","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.12916","pdf_url":"https://arxiv.org/pdf/2507.12916","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1889081078","https://openalex.org/W2560730294","https://openalex.org/W2594519801","https://openalex.org/W2963800628","https://openalex.org/W2963890019","https://openalex.org/W2964339842","https://openalex.org/W2966683369","https://openalex.org/W2979912832","https://openalex.org/W2981422075","https://openalex.org/W3034578524","https://openalex.org/W3034949383","https://openalex.org/W3095974555","https://openalex.org/W3107521863","https://openalex.org/W3182910454","https://openalex.org/W3189447831","https://openalex.org/W3192009892","https://openalex.org/W4225323055","https://openalex.org/W4226376247","https://openalex.org/W4282945631","https://openalex.org/W4290994948","https://openalex.org/W4296566403","https://openalex.org/W4307079201","https://openalex.org/W4312377093","https://openalex.org/W4322718191","https://openalex.org/W4366330503","https://openalex.org/W4367628410","https://openalex.org/W4376122449","https://openalex.org/W4376226279","https://openalex.org/W4376312115","https://openalex.org/W4380558379","https://openalex.org/W4382490555","https://openalex.org/W4382491206","https://openalex.org/W4384918448","https://openalex.org/W4385245566","https://openalex.org/W4385262477","https://openalex.org/W4386066076","https://openalex.org/W4386075583","https://openalex.org/W4386076522","https://openalex.org/W4388854793","https://openalex.org/W4389317971","https://openalex.org/W4390872495","https://openalex.org/W4393149778","https://openalex.org/W4401416853","https://openalex.org/W4401991200","https://openalex.org/W4402427278","https://openalex.org/W4402703032","https://openalex.org/W4402716423","https://openalex.org/W4402727764","https://openalex.org/W4403778769","https://openalex.org/W4404356490"],"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":{"Advancements":[0],"in":[1,11,57,249],"foundation":[2,164],"models":[3,28],"have":[4],"made":[5],"it":[6,168],"possible":[7],"to":[8,24,68,86,189,212],"conduct":[9],"applications":[10],"various":[12,170,250],"downstream":[13,251],"tasks.":[14,192,252],"Especially,":[15],"the":[16,46,75,95,99,185,209,224,237],"new":[17],"era":[18],"has":[19],"witnessed":[20],"a":[21,137,160],"remarkable":[22],"capability":[23,186],"extend":[25],"large":[26,162],"language":[27],"(LLMs)":[29],"for":[30,127,146,223],"tackling":[31],"tasks":[32],"of":[33,51,89,120,187],"3-D":[34,42,47,77,112,139,148,161,180,191,210,229,238],"scene":[35,54,121,149,218],"understanding.":[36],"Current":[37],"methods":[38],"rely":[39],"heavily":[40],"on":[41,131],"point":[43,48,78,102,113,181,230],"clouds,":[44],"but":[45],"cloud":[49],"reconstruction":[50],"an":[52],"indoor":[53],"often":[55],"results":[56],"information":[58,225],"loss.":[59],"Some":[60],"textureless":[61],"planes":[62],"or":[63],"repetitive":[64],"patterns":[65],"are":[66],"prone":[67],"omission":[69],"and":[70,98,115,179,183,196,200,215,232],"manifest":[71],"as":[72,159,172],"voids":[73],"within":[74],"reconstructed":[76,101],"clouds.":[79,103],"Besides,":[80],"objects":[81],"with":[82,111,151,208],"complex":[83],"structures":[84],"tend":[85],"introduce":[87],"distortion":[88],"details":[90],"caused":[91],"by":[92],"misalignments":[93],"between":[94],"captured":[96],"images":[97,107,145,199],"dense":[100],"The":[104],"2-D":[105,176],"multiview":[106,144,177,198],"present":[108],"visual":[109],"consistency":[110],"clouds":[114,231],"provide":[116],"more":[117],"detailed":[118,216],"representations":[119],"components,":[122],"which":[123,206],"can":[124,156],"naturally":[125],"compensate":[126],"these":[128,132],"deficiencies.":[129],"Based":[130],"insights,":[133],"we":[134],"propose":[135],"Argus,":[136],"novel":[138],"multimodal":[140,163],"framework":[141],"that":[142,243],"leverages":[143],"enhanced":[147],"understanding":[150],"LLMs.":[152],"In":[153],"general,":[154],"Argus":[155,193],"be":[157],"treated":[158],"model":[165],"(3D-LMM)":[166],"since":[167],"takes":[169],"modalities":[171],"input":[173],"(text":[174],"instructions,":[175],"images,":[178],"clouds)":[182],"expands":[184],"LLMs":[188,234],"tackle":[190],"involves":[194],"fusing":[195],"integrating":[197],"camera":[201],"poses":[202],"into":[203],"view-as-scene":[204],"features,":[205],"interact":[207],"features":[211],"create":[213],"comprehensive":[214],"3-D-aware":[217],"embeddings.":[219],"Our":[220],"approach":[221],"compensates":[222],"loss":[226],"while":[227],"reconstructing":[228],"helps":[233],"better":[235],"understand":[236],"world.":[239],"Extensive":[240],"experiments":[241],"demonstrate":[242],"our":[244],"method":[245],"outperforms":[246],"existing":[247],"3D-LMMs":[248]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}