{"id":"https://openalex.org/W4403363231","doi":"https://doi.org/10.1109/arso68304.2026.11536136","title":"UNCOM: Zero-Shot Context-Aware Command Understanding for Tabletop Scenarios","display_name":"UNCOM: Zero-Shot Context-Aware Command Understanding for Tabletop Scenarios","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W4403363231","doi":"https://doi.org/10.1109/arso68304.2026.11536136"},"language":"en","primary_location":{"id":"doi:10.1109/arso68304.2026.11536136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/arso68304.2026.11536136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Conference on Advanced Robotics and its Social Impacts (ARSO)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.06355","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028110158","display_name":"Pawe\u0142 Gajewski","orcid":"https://orcid.org/0000-0003-0931-2476"},"institutions":[{"id":"https://openalex.org/I126596746","display_name":"Jagiellonian University","ror":"https://ror.org/03bqmcz70","country_code":"PL","type":"education","lineage":["https://openalex.org/I126596746"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Antonio Galiza Cerdeira Gonzalez","raw_affiliation_strings":["Jagiellonian University,Krakow,Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jagiellonian University,Krakow,Poland","institution_ids":["https://openalex.org/I126596746"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071873967","display_name":"Antonio Galiza Cerdeira Gonzalez","orcid":"https://orcid.org/0000-0003-2869-1715"},"institutions":[{"id":"https://openalex.org/I126596746","display_name":"Jagiellonian University","ror":"https://ror.org/03bqmcz70","country_code":"PL","type":"education","lineage":["https://openalex.org/I126596746"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Pawe\u0142 Gajewski","raw_affiliation_strings":["Jagiellonian University,Krakow,Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jagiellonian University,Krakow,Poland","institution_ids":["https://openalex.org/I126596746"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076074691","display_name":"Bipin Indurkhya","orcid":"https://orcid.org/0000-0002-3798-9209"},"institutions":[{"id":"https://openalex.org/I126596746","display_name":"Jagiellonian University","ror":"https://ror.org/03bqmcz70","country_code":"PL","type":"education","lineage":["https://openalex.org/I126596746"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Bipin Indurkhya","raw_affiliation_strings":["Jagiellonian University,Krakow,Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jagiellonian University,Krakow,Poland","institution_ids":["https://openalex.org/I126596746"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.00201368,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"163","last_page":"168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9984999895095825,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9984999895095825,"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/T10789","display_name":"Interactive and Immersive Displays","score":0.9804999828338623,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T12222","display_name":"IoT-based Smart Home Systems","score":0.9611999988555908,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/context","display_name":"Context (archaeology)","score":0.6728453636169434},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5597213506698608},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4728715121746063},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.37647271156311035},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.32693466544151306},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08876293897628784}],"concepts":[{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6728453636169434},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5597213506698608},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4728715121746063},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.37647271156311035},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32693466544151306},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08876293897628784},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/arso68304.2026.11536136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/arso68304.2026.11536136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Conference on Advanced Robotics and its Social Impacts (ARSO)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.06355","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.06355","pdf_url":"https://arxiv.org/pdf/2410.06355","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:arXiv.org:2410.06355","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2410.06355","pdf_url":"https://arxiv.org/pdf/2410.06355","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.06355","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.06355","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.06355","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.06355","pdf_url":"https://arxiv.org/pdf/2410.06355","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403363231.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"UNCOM,":[3],"a":[4,64,112,120],"novel":[5],"hybrid":[6],"framework":[7],"for":[8,35,40,50],"interpreting":[9],"natural":[10,79],"human":[11],"commands":[12,97],"in":[13,44,111],"tabletop":[14],"scenarios.":[15],"The":[16,87,150],"system":[17,110,143],"integrates":[18],"multiple":[19],"sources":[20],"of":[21,124,141],"information":[22],"-":[23,29],"speech,":[24],"gestures,":[25],"and":[26,69,84,92,115,147,155],"scene":[27],"context":[28],"to":[30,63,144,161],"extract":[31],"structured,":[32],"actionable":[33],"instructions":[34],"robots.":[36],"Addressing":[37],"the":[38,109,139,142,156],"need":[39],"general-purpose":[41],"human-robot":[42,125],"interaction":[43,126],"domestic":[45],"environments,":[46],"UNCOM":[47],"is":[48],"designed":[49],"zero-shot":[51],"operation,":[52],"without":[53],"reliance":[54],"on":[55,119],"predefined":[56],"object":[57,85],"models":[58],"or":[59],"training":[60],"data":[61,122,136,151],"specific":[62],"given":[65],"task.":[66],"Using":[67],"foundational":[68],"task-specific":[70],"deep":[71],"learning":[72],"models,":[73],"it":[74],"allows":[75],"out-of-the-box":[76],"speech":[77],"recognition,":[78],"language":[80],"understanding,":[81],"gesture":[82],"detection,":[83],"segmentation.":[86],"modular":[88],"architecture":[89],"enhances":[90],"transparency":[91],"explainability":[93],"by":[94],"explicitly":[95],"parsing":[96],"into":[98],"object-action-target":[99],"representations,":[100],"enabling":[101],"integration":[102],"with":[103],"symbolic":[104],"robotic":[105],"frameworks.":[106],"We":[107],"demonstrate":[108],"TIAGo++":[113],"robot":[114],"provide":[116],"an":[117,129],"evaluation":[118,153],"real-world":[121],"set":[123],"scenarios;":[127],"achieving":[128],"82.39%":[130],"success":[131],"rate":[132],"over":[133],"our":[134],"benchmark":[135],"set,":[137,152],"highlighting":[138],"robustness":[140],"diversity,":[145],"noise,":[146],"communication":[148],"ambiguity.":[149],"scenarios,":[154],"code":[157],"are":[158],"publicly":[159],"available":[160],"support":[162],"future":[163],"research.":[164]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}