{"id":"https://openalex.org/W4415536601","doi":"https://doi.org/10.1145/3746027.3758177","title":"Queryable 3D Scene Representation: A Multi-Modal Framework for Semantic Reasoning and Robotic Task Planning","display_name":"Queryable 3D Scene Representation: A Multi-Modal Framework for Semantic Reasoning and Robotic Task Planning","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536601","doi":"https://doi.org/10.1145/3746027.3758177"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3758177","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758177","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3758177","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100341849","display_name":"Xun Li","orcid":"https://orcid.org/0000-0002-1717-0669"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xun Li","raw_affiliation_strings":["CSIRO, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-1717-0669","affiliations":[{"raw_affiliation_string":"CSIRO, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082533938","display_name":"Rodrigo Santa Cruz","orcid":"https://orcid.org/0000-0002-5273-7296"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Rodrigo Santa Cruz","raw_affiliation_strings":["CSIRO, Pullenvale, QLD, Australia"],"raw_orcid":"https://orcid.org/0000-0002-5273-7296","affiliations":[{"raw_affiliation_string":"CSIRO, Pullenvale, QLD, Australia","institution_ids":["https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069756828","display_name":"Mingze Xi","orcid":"https://orcid.org/0000-0003-1291-4136"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mingze Xi","raw_affiliation_strings":["CSIRO, Canberra, ACT, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1291-4136","affiliations":[{"raw_affiliation_string":"CSIRO, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115580345","display_name":"Hu Zhang","orcid":"https://orcid.org/0009-0009-9892-9515"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hu Zhang","raw_affiliation_strings":["CSIRO, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0009-0009-9892-9515","affiliations":[{"raw_affiliation_string":"CSIRO, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033797530","display_name":"Madhawa Perera","orcid":"https://orcid.org/0009-0009-0928-0380"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Madhawa Perera","raw_affiliation_strings":["CSIRO, Canberra, ACT, Australia"],"raw_orcid":"https://orcid.org/0009-0009-0928-0380","affiliations":[{"raw_affiliation_string":"CSIRO, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389369","display_name":"Ziwei Wang","orcid":"https://orcid.org/0000-0002-0107-7347"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ziwei Wang","raw_affiliation_strings":["CSIRO, Pullenvale, QLD, Australia"],"raw_orcid":"https://orcid.org/0000-0002-0107-7347","affiliations":[{"raw_affiliation_string":"CSIRO, Pullenvale, QLD, Australia","institution_ids":["https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044943407","display_name":"Ahalya Ravendran","orcid":"https://orcid.org/0000-0001-8022-9208"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ahalya Ravendran","raw_affiliation_strings":["CSIRO, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8022-9208","affiliations":[{"raw_affiliation_string":"CSIRO, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068485054","display_name":"Brandon Matthews","orcid":"https://orcid.org/0000-0002-8673-2434"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Brandon J. Matthews","raw_affiliation_strings":["CSIRO, Canberra, ACT, Australia"],"raw_orcid":"https://orcid.org/0000-0002-8673-2434","affiliations":[{"raw_affiliation_string":"CSIRO, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100432901","display_name":"Feng Xu","orcid":"https://orcid.org/0000-0002-3932-1093"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Feng Xu","raw_affiliation_strings":["CSIRO, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-3932-1093","affiliations":[{"raw_affiliation_string":"CSIRO, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022121298","display_name":"Matt Adcock","orcid":"https://orcid.org/0000-0001-6191-9887"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Matt Adcock","raw_affiliation_strings":["CSIRO, Canberra, ACT, Australia"],"raw_orcid":"https://orcid.org/0000-0001-6191-9887","affiliations":[{"raw_affiliation_string":"CSIRO, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053719139","display_name":"Dadong Wang","orcid":"https://orcid.org/0000-0003-0409-2259"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dadong Wang","raw_affiliation_strings":["CSIRO, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0409-2259","affiliations":[{"raw_affiliation_string":"CSIRO, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I1292875679"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039989215","display_name":"Jiajun Liu","orcid":"https://orcid.org/0000-0001-8160-1796"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jiajun Liu","raw_affiliation_strings":["CSIRO, Pullenvale, QLD, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8160-1796","affiliations":[{"raw_affiliation_string":"CSIRO, Pullenvale, QLD, Australia","institution_ids":["https://openalex.org/I1292875679"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1292875679"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12492","last_page":"12500"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9975000023841858,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9975000023841858,"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":0.9954000115394592,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9943000078201294,"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/rendering","display_name":"Rendering (computer graphics)","score":0.5378999710083008},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.5371999740600586},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5246999859809875},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.47510001063346863},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.45170000195503235},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4490000009536743},{"id":"https://openalex.org/keywords/3d-city-models","display_name":"3D city models","score":0.41269999742507935},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4081000089645386},{"id":"https://openalex.org/keywords/semantic-mapping","display_name":"Semantic mapping","score":0.4066999852657318}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8011999726295471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5771999955177307},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5378999710083008},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.5371999740600586},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5246999859809875},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4839000105857849},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.47510001063346863},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.45170000195503235},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4490000009536743},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44690001010894775},{"id":"https://openalex.org/C2778597888","wikidata":"https://www.wikidata.org/wiki/Q172169","display_name":"3D city models","level":3,"score":0.41269999742507935},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4081000089645386},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.4066999852657318},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3695000112056732},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.34380000829696655},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.3343999981880188},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2912999987602234},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2565999925136566}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3758177","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758177","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.20077","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.20077","pdf_url":"https://arxiv.org/pdf/2509.20077","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null}],"best_oa_location":{"id":"doi:10.1145/3746027.3758177","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758177","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2341115255","https://openalex.org/W2737258237","https://openalex.org/W2998702515","https://openalex.org/W3096741513","https://openalex.org/W4200150166","https://openalex.org/W4312433568","https://openalex.org/W4312815172","https://openalex.org/W4385431115","https://openalex.org/W4404238327"],"related_works":[],"abstract_inverted_index":{"To":[0,46],"enable":[1,110],"robots":[2],"to":[3,109],"comprehend":[4],"high-level":[5],"human":[6],"instructions":[7],"and":[8,22,76,88,118,125],"perform":[9],"complex":[10],"tasks,":[11],"a":[12,29,34,58,135],"key":[13],"challenge":[14],"lies":[15],"in":[16,28],"achieving":[17],"comprehensive":[18],"scene":[19,95],"understanding:":[20],"interpreting":[21],"interacting":[23],"with":[24,42,105],"the":[25,51,102],"3D":[26,52,69,85,94],"environment":[27],"meaningful":[30],"way.":[31],"This":[32],"requires":[33],"smart":[35],"map":[36],"that":[37,65],"fuses":[38],"accurate":[39],"geometric":[40],"structure":[41],"rich,":[43],"human-understandable":[44],"semantics.":[45],"address":[47],"this,":[48],"we":[49],"introduce":[50],"Queryable":[53],"Scene":[54],"Representation":[55],"(3D":[56],"QSR),":[57],"novel":[59,73],"framework":[60,103],"built":[61],"on":[62,98],"multimedia":[63],"data":[64,130],"unifies":[66],"three":[67],"complementary":[68],"representations:":[70],"(1)":[71],"3D-consistent":[72],"view":[74],"rendering":[75],"segmentation":[77],"from":[78,84],"panoptic":[79],"reconstruction,":[80],"(2)":[81],"precise":[82],"geometry":[83],"point":[86],"clouds,":[87],"(3)":[89],"structured,":[90],"scalable":[91],"organization":[92],"via":[93],"graphs.":[96],"Built":[97],"an":[99],"object-centric":[100],"design,":[101],"integrates":[104],"large":[106],"vision-language":[107],"models":[108],"semantic":[111,126],"queryability":[112],"by":[113],"linking":[114],"multimodal":[115],"object":[116],"embeddings,":[117],"supporting":[119],"object-level":[120],"retrieval":[121],"of":[122],"geometric,":[123],"visual,":[124],"information.":[127],"The":[128],"retrieved":[129],"are":[131],"then":[132],"loaded":[133],"into":[134],"robotic":[136],"task":[137],"planner":[138],"for":[139],"downstream":[140],"execution.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-25T00:00:00"}
