{"id":"https://openalex.org/W7137938565","doi":"https://doi.org/10.1609/aaai.v40i5.37391","title":"Open-World 3D Scene Graph Generation for Retrieval-Augmented Reasoning","display_name":"Open-World 3D Scene Graph Generation for Retrieval-Augmented Reasoning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137938565","doi":"https://doi.org/10.1609/aaai.v40i5.37391"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i5.37391","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37391","pdf_url":null,"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://doi.org/10.1609/aaai.v40i5.37391","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129677151","display_name":"Yu Fei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Fei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060218731","display_name":"Quan Deng","orcid":"https://orcid.org/0000-0002-3925-5719"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quan Deng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129752557","display_name":"Shengeng Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengeng Tang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129692364","display_name":"Li Yuehua","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Yuehua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129676253","display_name":"Lechao Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lechao Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16381766,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"5","first_page":"3894","last_page":"3902"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9937999844551086,"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":0.9937999844551086,"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/T10028","display_name":"Topic Modeling","score":0.0010999999940395355,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.0006000000284984708,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/scene-graph","display_name":"Scene graph","score":0.7401999831199646},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5509999990463257},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4869999885559082},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.42800000309944153},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4187000095844269},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.3684999942779541},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.35760000348091125},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3465000092983246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7766000032424927},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.7401999831199646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5860999822616577},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5509999990463257},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4869999885559082},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.42800000309944153},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4187000095844269},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3684999942779541},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3465000092983246},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34139999747276306},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.28929999470710754},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2867000102996826},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.2856000065803528},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27900001406669617},{"id":"https://openalex.org/C197654239","wikidata":"https://www.wikidata.org/wiki/Q7430757","display_name":"Scene statistics","level":3,"score":0.265500009059906},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25920000672340393},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i5.37391","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37391","pdf_url":null,"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"},{"id":"pmh:oai:ojs.aaai.org:article/37391","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i5.37391","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37391","pdf_url":null,"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":[{"score":0.4913266599178314,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1050443403","display_name":null,"funder_award_id":"XB2025019","funder_id":"https://openalex.org/F4320324783","funder_display_name":"Liaoning University"},{"id":"https://openalex.org/G3364597423","display_name":null,"funder_award_id":"62472139","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3733350581","display_name":null,"funder_award_id":"2025-MS-163","funder_id":"https://openalex.org/F4320323086","funder_display_name":"Natural Science Foundation of Liaoning Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323086","display_name":"Natural Science Foundation of Liaoning Province","ror":null},{"id":"https://openalex.org/F4320324783","display_name":"Liaoning University","ror":"https://ror.org/03xpwj629"},{"id":"https://openalex.org/F4320329895","display_name":"Liaoning Revitalization Talents Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Open-world":[0],"3D":[1,31,43,146],"scene":[2,44,70,93,147],"understanding":[3],"is":[4],"fundamentally":[5],"challenging":[6],"for":[7,29,144],"vision":[8],"and":[9,18,41,58,77,85,109,121,126],"robotics,":[10],"due":[11],"to":[12,54,99],"the":[13,135],"constraints":[14],"of":[15,137],"closed-vocabulary":[16],"supervision":[17],"static":[19],"annotations.":[20],"To":[21],"address":[22],"this,":[23],"we":[24],"propose":[25],"a":[26,68,87,96],"unified":[27],"framework":[28,62],"Open-World":[30],"Scene":[32],"Graph":[33],"Generation":[34],"with":[35,51,141],"Retrieval-Augmented":[36],"Reasoning,":[37],"which":[38],"enables":[39],"generalizable":[40],"interactive":[42],"understanding.":[45,148],"Our":[46,132],"method":[47,106],"integrates":[48],"vision-language":[49],"models":[50],"retrieval-based":[52,142],"reasoning":[53,89,143],"support":[55,100],"multimodal":[56],"exploration":[57],"language-guided":[59],"interaction.":[60],"The":[61],"comprises":[63],"two":[64],"key":[65],"components:":[66],"(1)":[67],"dynamic":[69],"graph":[71],"generation":[72],"module":[73],"that":[74,91],"detects":[75],"objects":[76],"infers":[78],"semantic":[79],"relationships":[80],"without":[81],"fixed":[82],"label":[83],"sets,":[84],"(2)":[86],"retrieval-augmented":[88],"pipeline":[90],"encodes":[92],"graphs":[94],"into":[95],"vector":[97],"database":[98],"text/image-conditioned":[101],"queries.":[102],"We":[103],"evaluate":[104],"our":[105],"on":[107],"3DSSG":[108],"Replica":[110],"benchmarks":[111],"across":[112],"four":[113],"tasks\u2014scene":[114],"question":[115],"answering,":[116],"visual":[117],"grounding,":[118],"instance":[119],"retrieval,":[120],"task":[122],"planning\u2014demonstrating":[123],"robust":[124],"generalization":[125],"superior":[127],"performance":[128],"in":[129],"diverse":[130],"environments.":[131],"results":[133],"highlight":[134],"effectiveness":[136],"combining":[138],"open-vocabulary":[139],"perception":[140],"scalable":[145]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}