{"id":"https://openalex.org/W4403791572","doi":"https://doi.org/10.1145/3664647.3681022","title":"3D Question Answering for City Scene Understanding","display_name":"3D Question Answering for City Scene Understanding","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791572","doi":"https://doi.org/10.1145/3664647.3681022"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681022","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-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/A5114594168","display_name":"Penglei Sun","orcid":"https://orcid.org/0009-0005-2290-0944"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Penglei Sun","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"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"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109152867","display_name":"Xiang Liu","orcid":"https://orcid.org/0009-0003-2639-1804"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Liu","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"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/A5019505603","display_name":"Xiaofei Yang","orcid":"https://orcid.org/0000-0003-2458-6774"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofei Yang","raw_affiliation_strings":["Guangzhou University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]},{"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"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"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"],"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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"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":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5114594168"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.735,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72758238,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2156","last_page":"2165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9993000030517578,"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":0.9986000061035156,"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/question-answering","display_name":"Question answering","score":0.6487390995025635},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6294205188751221},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40906864404678345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3812863826751709},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35920917987823486}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6487390995025635},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6294205188751221},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40906864404678345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3812863826751709},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35920917987823486}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3681022","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-158285","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-158285","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2080133951","https://openalex.org/W2102486384","https://openalex.org/W2337783779","https://openalex.org/W2561529111","https://openalex.org/W2594519801","https://openalex.org/W2930283066","https://openalex.org/W2964487155","https://openalex.org/W2967353954","https://openalex.org/W2970641574","https://openalex.org/W2988715931","https://openalex.org/W2997780971","https://openalex.org/W3024031618","https://openalex.org/W3089409752","https://openalex.org/W3119690318","https://openalex.org/W3164336989","https://openalex.org/W3182910454","https://openalex.org/W3203393885","https://openalex.org/W3203597819","https://openalex.org/W4200521614","https://openalex.org/W4205419321","https://openalex.org/W4212774754","https://openalex.org/W4226326569","https://openalex.org/W4226376247","https://openalex.org/W4234552385","https://openalex.org/W4241346584","https://openalex.org/W4288265104","https://openalex.org/W4293868279","https://openalex.org/W4297437765","https://openalex.org/W4310463627","https://openalex.org/W4312586444","https://openalex.org/W4312746993","https://openalex.org/W4312842946","https://openalex.org/W4321366715","https://openalex.org/W4385804899","https://openalex.org/W4386066792","https://openalex.org/W4389474301","https://openalex.org/W4390872495","https://openalex.org/W4393148430","https://openalex.org/W6776977327"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W3204019825"],"abstract_inverted_index":{"3D":[0,21,79,95,169],"multimodal":[1],"question":[2],"answering":[3],"(MQA)":[4],"plays":[5],"a":[6,93,126],"crucial":[7],"role":[8],"in":[9,20,54,161,185],"scene":[10,46,102,111,137],"understanding":[11,47,55],"by":[12],"enabling":[13],"intelligent":[14],"agents":[15],"to":[16,59,109,139,167],"comprehend":[17],"their":[18],"surroundings":[19],"environments.":[22],"While":[23],"existing":[24,50],"research":[25,51],"has":[26,40],"primarily":[27],"focused":[28],"on":[29],"indoor":[30,168],"household":[31],"tasks":[32,116],"and":[33,66,84,113,149,158,172,187],"outdoor":[34],"roadside":[35],"autonomous":[36],"driving":[37],"tasks,":[38],"there":[39],"been":[41],"limited":[42],"exploration":[43],"of":[44,62,155,164],"city-level":[45,101],"tasks.":[48],"Furthermore,":[49],"faces":[52],"challenges":[53],"city":[56,72],"scenes,":[57],"due":[58],"the":[60,71,88,106,118,121,136,141],"absence":[61],"spatial":[63,142],"semantic":[64,112],"information":[65,69],"human-environment":[67,114],"interaction":[68],"at":[70],"level.To":[73],"address":[74],"these":[75],"challenges,":[76],"we":[77,91,124],"investigate":[78],"MQA":[80,96,170],"from":[81],"both":[82],"dataset":[83,89,97,108],"method":[85,122,132],"perspectives.":[86],"From":[87,120],"perspective,":[90,123],"introduce":[92,140],"novel":[94],"named":[98],"<u>City-3DQA</u>":[99],"for":[100],"understanding,":[103],"which":[104,134],"is":[105,147],"first":[107],"incorporate":[110],"interactive":[115],"within":[117],"city.":[119],"propose":[125],"Scene":[127],"graph":[128,138],"enhanced":[129],"City-level":[130],"Understanding":[131],"(<u>Sg-CityU</u>),":[133],"utilizes":[135],"semantic.":[143],"A":[144],"new":[145],"benchmark":[146],"reported":[148],"our":[150],"proposed":[151],"Sg-CityU":[152,180],"achieves":[153],"accuracy":[154],"63.94":[156],"%":[157,160],"63.76":[159],"different":[162],"settings":[163],"City-3DQA.":[165],"Compared":[166],"methods":[171],"zero-shot":[173],"using":[174],"advanced":[175],"large":[176],"language":[177],"models":[178],"(LLMs),":[179],"demonstrates":[181],"state-of-the-art":[182],"(SOTA)":[183],"performance":[184],"robustness":[186],"generalization.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}