{"id":"https://openalex.org/W4415536568","doi":"https://doi.org/10.1145/3746027.3755088","title":"City-VLM: Towards Multidomain Perception Scene Understanding via Multimodal Incomplete Learning","display_name":"City-VLM: Towards Multidomain Perception Scene Understanding via Multimodal Incomplete Learning","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536568","doi":"https://doi.org/10.1145/3746027.3755088"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755088","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5114594168","display_name":"Penglei Sun","orcid":"https://orcid.org/0009-0005-2290-0944"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Penglei Sun","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-2290-0944","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026663768","display_name":"Yaoxian Song","orcid":"https://orcid.org/0000-0002-8146-2236"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaoxian Song","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8146-2236","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041560675","display_name":"Xiangru Zhu","orcid":"https://orcid.org/0000-0001-7308-3642"},"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":"Xiangru Zhu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7308-3642","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109152867","display_name":"Xiang Liu","orcid":"https://orcid.org/0009-0003-2639-1804"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiang Liu","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guang Zhou)), Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-2639-1804","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guang Zhou)), Guangzhou, China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018867983","display_name":"Qiang Wang","orcid":"https://orcid.org/0000-0002-2986-967X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Wang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2986-967X","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yue Liu","orcid":"https://orcid.org/0009-0006-7445-5632"},"institutions":[{"id":"https://openalex.org/I4210099810","display_name":"XING Technologies (Australia)","ror":"https://ror.org/010s0k503","country_code":"AU","type":"company","lineage":["https://openalex.org/I4210099810"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yue Liu","raw_affiliation_strings":["Terminus Technologies Co., Ltd., Chongqing, China"],"raw_orcid":"https://orcid.org/0009-0006-7445-5632","affiliations":[{"raw_affiliation_string":"Terminus Technologies Co., Ltd., Chongqing, China","institution_ids":["https://openalex.org/I4210099810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053599124","display_name":"Changqun Xia","orcid":"https://orcid.org/0000-0002-9594-5693"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changqun Xia","raw_affiliation_strings":["Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-9594-5693","affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008715397","display_name":"Tiefeng Li","orcid":"https://orcid.org/0000-0003-0265-3454"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiefeng Li","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0265-3454","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397725","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0003-0608-9408"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["The Hong Kong University of Hong Kong (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0608-9408","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Hong Kong (Guangzhou), Guangzhou, China","institution_ids":["https://openalex.org/I37987034","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100730785","display_name":"Xiaowen Chu","orcid":"https://orcid.org/0000-0001-9745-4372"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaowen Chu","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9745-4372","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3448","last_page":"3457"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994000196456909,"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":0.9987000226974487,"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/perception","display_name":"Perception","score":0.5501999855041504},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4787999987602234},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.454800009727478},{"id":"https://openalex.org/keywords/viewpoints","display_name":"Viewpoints","score":0.451200008392334},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.42399999499320984},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.41370001435279846},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4025000035762787},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.3903000056743622}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7666000127792358},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6090999841690063},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5501999855041504},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4805999994277954},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4787999987602234},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.454800009727478},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.451200008392334},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.42399999499320984},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.41370001435279846},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4025000035762787},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39259999990463257},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3903000056743622},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3483000099658966},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C197654239","wikidata":"https://www.wikidata.org/wiki/Q7430757","display_name":"Scene statistics","level":3,"score":0.3407000005245209},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3294000029563904},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.2662000060081482},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C2776010242","wikidata":"https://www.wikidata.org/wiki/Q4677575","display_name":"Active perception","level":3,"score":0.2517000138759613},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755088","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2060816702","https://openalex.org/W2150066425","https://openalex.org/W2460657278","https://openalex.org/W2594519801","https://openalex.org/W2745461083","https://openalex.org/W2963954913","https://openalex.org/W2964339842","https://openalex.org/W2966683369","https://openalex.org/W2980921063","https://openalex.org/W3012111773","https://openalex.org/W3035376925","https://openalex.org/W3035574168","https://openalex.org/W3043557496","https://openalex.org/W3095974555","https://openalex.org/W3107521863","https://openalex.org/W3167095230","https://openalex.org/W3189911029","https://openalex.org/W4205419321","https://openalex.org/W4281643269","https://openalex.org/W4372273245","https://openalex.org/W4385580125","https://openalex.org/W4389523655","https://openalex.org/W4393148430","https://openalex.org/W4395041667","https://openalex.org/W4396982395","https://openalex.org/W4402727764"],"related_works":[],"abstract_inverted_index":{"Scene":[0],"understanding":[1,19,107,164,199],"enables":[2],"intelligent":[3],"agents":[4],"to":[5,34,86,160],"interpret":[6],"and":[7,56,84,90,117,126,142,165,218],"comprehend":[8],"their":[9],"environment.":[10],"While":[11],"existing":[12,60,75,208],"large":[13],"vision-language":[14],"models":[15],"(LVLMs)":[16],"for":[17],"scene":[18,37,106,163,198],"have":[20],"primarily":[21],"focused":[22],"on":[23,194],"indoor":[24,61],"household":[25],"tasks,":[26],"they":[27],"face":[28],"two":[29],"significant":[30],"limitations":[31],"when":[32],"applied":[33],"outdoor":[35,40,82,105,162,197,223],"large-scale":[36],"understanding.":[38],"First,":[39],"scenarios":[41,114],"typically":[42],"encompass":[43],"larger-scale":[44],"environments":[45],"observed":[46],"through":[47],"various":[48],"sensors":[49],"from":[50,71,78,112,135],"multiple":[51,222],"viewpoints":[52],"(e.g.,":[53,190],"bird":[54],"view":[55],"terrestrial":[57],"view),":[58],"while":[59],"LVLMs":[62,76,209],"mainly":[63],"analyze":[64],"single":[65],"visual":[66,92],"modalities":[67],"within":[68],"building-scale":[69],"contexts":[70],"humanoid":[72],"viewpoints.":[73],"Second,":[74],"suffer":[77],"missing":[79],"multidomain":[80,103],"perception":[81,104],"data":[83,148],"struggle":[85],"effectively":[87,145],"integrate":[88],"2D":[89],"3D":[91],"information.":[93],"To":[94,144],"address":[95],"the":[96,101,150,167],"aforementioned":[97],"limitations,":[98],"we":[99,155],"build":[100],"first":[102],"dataset,":[108],"named":[109,169],"SVM-City,":[110],"deriving":[111],"multi-Scale":[113],"with":[115,131],"multi-View":[116],"multi-Modal":[118],"instruction":[119],"tuning":[120],"data.":[121],"It":[122],"contains":[123],"420k":[124],"images":[125],"4,":[127],"811M":[128],"point":[129],"clouds":[130],"567k":[132],"question-answering":[133,211],"pairs":[134],"vehicles,":[136],"low-altitude":[137],"drones,":[138],"high-altitude":[139],"aerial":[140],"planes,":[141],"satellite.":[143],"fuse":[146],"multimodal":[147,158],"in":[149,210],"absence":[151],"of":[152],"one":[153],"modality,":[154],"introduce":[156],"incomplete":[157],"learning":[159],"model":[161],"design":[166],"LVLM":[168],"City-VLM.":[170],"Multimodal":[171],"fusion":[172,188],"is":[173],"realized":[174],"by":[175],"constructed":[176],"as":[177],"a":[178],"joint":[179],"probabilistic":[180],"distribution":[181],"space":[182],"rather":[183],"than":[184],"implementing":[185],"directly":[186],"explicit":[187],"operations":[189],"concatenation).":[191],"Experimental":[192],"results":[193],"three":[195],"typical":[196],"tasks":[200,212],"show":[201],"City-VLM":[202],"achieves":[203],"18.14":[204],"%":[205],"performance":[206,220],"surpassing":[207],"averagely.":[213],"Our":[214],"method":[215],"demonstrates":[216],"pragmatic":[217],"generalization":[219],"across":[221],"scenes.":[224]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}