{"id":"https://openalex.org/W7138173137","doi":"https://doi.org/10.1609/aaai.v40i16.38331","title":"OpenScan: A Benchmark for Generalized Open-Vocabulary 3D Scene Understanding","display_name":"OpenScan: A Benchmark for Generalized Open-Vocabulary 3D Scene Understanding","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138173137","doi":"https://doi.org/10.1609/aaai.v40i16.38331"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i16.38331","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38331","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38331/42293","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38331/42293","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129681338","display_name":"Youjun Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Youjun Zhao","raw_affiliation_strings":["City University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127789150","display_name":"Jiaying Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]},{"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"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiaying Lin","raw_affiliation_strings":["City University of Hong Kong\nThe Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong\nThe Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I168719708","https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049664284","display_name":"Shuquan Ye","orcid":"https://orcid.org/0000-0001-5121-8040"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]},{"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":"Shuquan Ye","raw_affiliation_strings":["City University of Hong Kong\nThe Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong\nThe Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129657121","display_name":"Qianshi Pang","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianshi Pang","raw_affiliation_strings":["South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006197413","display_name":"Rynson W. H. Lau","orcid":"https://orcid.org/0000-0002-8957-8129"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Rynson W. H. Lau","raw_affiliation_strings":["City University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5129681338"],"corresponding_institution_ids":["https://openalex.org/I168719708"],"apc_list":null,"apc_paid":null,"fwci":15.5333,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.96492484,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"40","issue":"16","first_page":"13289","last_page":"13296"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8787000179290771,"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":0.8787000179290771,"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":0.03440000116825104,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.007799999788403511,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/benchmark","display_name":"Benchmark (surveying)","score":0.7764999866485596},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7746999859809875},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.7307000160217285},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6743000149726868},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6323000192642212},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6179999709129333},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5740000009536743}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7764999866485596},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7746999859809875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7384999990463257},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7307000160217285},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6743000149726868},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6323000192642212},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6179999709129333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6071000099182129},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5740000009536743},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43369999527931213},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.32260000705718994},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.32030001282691956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2996000051498413},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.29120001196861267},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C42357961","wikidata":"https://www.wikidata.org/wiki/Q213363","display_name":"Open set","level":2,"score":0.26759999990463257}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i16.38331","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38331","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38331/42293","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i16.38331","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38331","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38331/42293","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6103914976119995}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138173137.pdf","grobid_xml":"https://content.openalex.org/works/W7138173137.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Open-vocabulary":[0],"3D":[1,52,66,111],"scene":[2],"understanding":[3],"(OV-3D)":[4],"aims":[5],"to":[6,45,70,140,174],"localize":[7],"and":[8,22,83,95,122,134,170],"classify":[9],"novel":[10],"objects":[11],"beyond":[12,76],"the":[13,27,32,51,72,142,146,165,176],"closed":[14],"set":[15,85],"of":[16,34,86,93,110,145,167],"object":[17,35,77,112,159],"classes.":[18,78],"However,":[19],"existing":[20,168],"approaches":[21],"benchmarks":[23],"primarily":[24],"focus":[25],"on":[26,130],"open":[28,73,82],"vocabulary":[29,74],"problem":[30,75],"within":[31],"context":[33],"classes,":[36],"which":[37,108],"is":[38],"insufficient":[39],"in":[40],"providing":[41],"a":[42,48,59,103,149],"holistic":[43],"evaluation":[44],"what":[46],"extent":[47],"model":[49],"understands":[50],"scene.":[53],"In":[54],"this":[55,99],"paper,":[56],"we":[57,101],"introduce":[58],"more":[60],"challenging":[61],"task":[62],"called":[63],"Generalized":[64],"Open-Vocabulary":[65],"Scene":[67],"Understanding":[68],"(GOV-3D)":[69],"explore":[71,171],"It":[79],"encompasses":[80],"an":[81],"diverse":[84],"generalized":[87],"knowledge,":[88],"expressed":[89],"as":[90],"linguistic":[91,117],"queries":[92],"fine-grained":[94],"object-specific":[96],"attributes.":[97],"To":[98],"end,":[100],"contribute":[102],"new":[104],"benchmark":[105,133],"named":[106],"OpenScan,":[107],"consists":[109],"attributes":[113],"across":[114],"eight":[115],"representative":[116],"aspects,":[118],"including":[119],"affordance,":[120],"property,":[121],"material.":[123],"We":[124,163],"further":[125],"evaluate":[126],"state-of-the-art":[127],"OV-3D":[128],"methods":[129,138],"our":[131],"OpenScan":[132],"discover":[135],"that":[136,151],"these":[137],"struggle":[139],"comprehend":[141],"abstract":[143],"vocabularies":[144],"GOV-3D":[147],"task,":[148],"challenge":[150],"cannot":[152],"be":[153],"addressed":[154],"simply":[155],"by":[156],"scaling":[157],"up":[158],"classes":[160],"during":[161],"training.":[162],"highlight":[164],"limitations":[166],"methodologies":[169],"promising":[172],"directions":[173],"overcome":[175],"identified":[177],"shortcomings.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2026-03-18T00:00:00"}