{"id":"https://openalex.org/W7135010041","doi":"https://doi.org/10.1145/3776734.3794486","title":"Seeing Only When Needed: A Multimodal Architecture for Context-Aware Social Dialogue","display_name":"Seeing Only When Needed: A Multimodal Architecture for Context-Aware Social Dialogue","publication_year":2026,"publication_date":"2026-03-12","ids":{"openalex":"https://openalex.org/W7135010041","doi":"https://doi.org/10.1145/3776734.3794486"},"language":"en","primary_location":{"id":"doi:10.1145/3776734.3794486","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3776734.3794486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://biblio.ugent.be/publication/01KTBGX9FG75RZNBTVW9D9D7EV/file/01KTBH3RS05GTHN9TP4RCJP8VN.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071275435","display_name":"Maria J. Pinto-Bernal","orcid":"https://orcid.org/0000-0002-1969-8395"},"institutions":[{"id":"https://openalex.org/I2801227569","display_name":"Ghent University Hospital","ror":"https://ror.org/00xmkp704","country_code":"BE","type":"healthcare","lineage":["https://openalex.org/I2801227569"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Maria Jose Pinto Bernal","raw_affiliation_strings":["Ghent University, Ghent, Belgium"],"raw_orcid":"https://orcid.org/0000-0002-1969-8395","affiliations":[{"raw_affiliation_string":"Ghent University, Ghent, Belgium","institution_ids":["https://openalex.org/I2801227569"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035627933","display_name":"Tony Belpaeme","orcid":"https://orcid.org/0000-0001-5207-7745"},"institutions":[{"id":"https://openalex.org/I2801227569","display_name":"Ghent University Hospital","ror":"https://ror.org/00xmkp704","country_code":"BE","type":"healthcare","lineage":["https://openalex.org/I2801227569"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Tony Belpaeme","raw_affiliation_strings":["Ghent University, Ghent, Belgium"],"raw_orcid":"https://orcid.org/0000-0001-5207-7745","affiliations":[{"raw_affiliation_string":"Ghent University, Ghent, Belgium","institution_ids":["https://openalex.org/I2801227569"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2801227569"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25332854,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"701","last_page":"705"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8705999851226807,"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":0.8705999851226807,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.08749999850988388,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.010400000028312206,"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/hallucinating","display_name":"Hallucinating","score":0.8406000137329102},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5753999948501587},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.5483999848365784},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5239999890327454},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5026000142097473},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4921000003814697},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4505999982357025},{"id":"https://openalex.org/keywords/social-robot","display_name":"Social robot","score":0.40230000019073486}],"concepts":[{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.8406000137329102},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6661999821662903},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6552000045776367},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5753999948501587},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.5483999848365784},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5239999890327454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5052000284194946},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5026000142097473},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4921000003814697},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4505999982357025},{"id":"https://openalex.org/C162947575","wikidata":"https://www.wikidata.org/wiki/Q2005645","display_name":"Social robot","level":5,"score":0.40230000019073486},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.37139999866485596},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3301999866962433},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3197999894618988},{"id":"https://openalex.org/C2781372952","wikidata":"https://www.wikidata.org/wiki/Q737460","display_name":"Visual impairment","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2851000130176544},{"id":"https://openalex.org/C156325361","wikidata":"https://www.wikidata.org/wiki/Q1152864","display_name":"Grounded theory","level":3,"score":0.2847999930381775},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.28029999136924744},{"id":"https://openalex.org/C130064352","wikidata":"https://www.wikidata.org/wiki/Q853725","display_name":"Social relation","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C29081049","wikidata":"https://www.wikidata.org/wiki/Q1364242","display_name":"Image stitching","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.27239999175071716}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3776734.3794486","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3776734.3794486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:01KTBGX9FG75RZNBTVW9D9D7EV","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01KTBGX9FG75RZNBTVW9D9D7EV","pdf_url":"https://biblio.ugent.be/publication/01KTBGX9FG75RZNBTVW9D9D7EV/file/01KTBH3RS05GTHN9TP4RCJP8VN.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"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":"ISBN: 9798400723216","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:archive.ugent.be:01KTBGX9FG75RZNBTVW9D9D7EV","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01KTBGX9FG75RZNBTVW9D9D7EV","pdf_url":"https://biblio.ugent.be/publication/01KTBGX9FG75RZNBTVW9D9D7EV/file/01KTBH3RS05GTHN9TP4RCJP8VN.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"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":"ISBN: 9798400723216","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7135010041.pdf","grobid_xml":"https://content.openalex.org/works/W7135010041.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1558406687","https://openalex.org/W2007570937","https://openalex.org/W2067450646","https://openalex.org/W4389523832","https://openalex.org/W4400679824","https://openalex.org/W4402753774","https://openalex.org/W4403918898","https://openalex.org/W4410296745","https://openalex.org/W4414198362","https://openalex.org/W4415064994","https://openalex.org/W4415822189","https://openalex.org/W4416033814","https://openalex.org/W7131131222"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Vision\u2013Language":[1],"Models":[2],"are":[3],"increasingly":[4],"used":[5],"for":[6],"visually":[7],"grounded":[8,114],"social":[9],"dialogue,":[10],"yet":[11],"most":[12],"systems":[13],"assume":[14],"that":[15,38,102,113],"vision":[16,40],"should":[17],"be":[18],"active":[19],"continuously,":[20],"adding":[21],"computational":[22],"load":[23],"and":[24,112],"increasing":[25],"the":[26,83,103,118],"risk":[27],"of":[28,122],"unnecessary":[29],"or":[30],"hallucinated":[31],"descriptions.":[32],"We":[33],"present":[34],"a":[35,42,55,61,71],"multimodal":[36],"architecture":[37],"treats":[39],"as":[41],"selective,":[43],"context-dependent":[44],"resource.":[45],"A":[46,92],"lightweight":[47],"vision-gating":[48],"module":[49],"triggers":[50],"visual":[51,87],"grounding":[52],"only":[53,79],"when":[54,80],"user":[56],"utterance":[57],"requires":[58],"it,":[59],"while":[60],"complementary":[62],"ambient":[63],"monitoring":[64],"component":[65],"detects":[66],"gradual":[67],"scene":[68,119],"changes":[69],"at":[70],"low":[72],"frame":[73],"rate.":[74],"Both":[75],"pathways":[76],"contribute":[77],"cues":[78],"relevant,":[81],"enabling":[82],"robot":[84],"to":[85],"use":[86],"information":[88],"meaningfully":[89],"without":[90],"overuse.":[91],"preliminary":[93],"evaluation":[94],"with":[95,109,117],"10":[96],"participants":[97],"(\u2248":[98],"95":[99],"minutes)":[100],"shows":[101],"gating":[104],"mechanism":[105],"identified":[106],"vision-relevant":[107],"turns":[108],"93.4%":[110],"accuracy,":[111],"descriptions":[115],"aligned":[116],"in":[120],"90.7%":[121],"cases.":[123]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2026-03-13T00:00:00"}
