{"id":"https://openalex.org/W7135075073","doi":"https://doi.org/10.1145/3776734.3794357","title":"Vision-Language System using Open-Source LLMs for Consent and Instruction Gestures in Medical Interpreter Robots","display_name":"Vision-Language System using Open-Source LLMs for Consent and Instruction Gestures in Medical Interpreter Robots","publication_year":2026,"publication_date":"2026-03-12","ids":{"openalex":"https://openalex.org/W7135075073","doi":"https://doi.org/10.1145/3776734.3794357"},"language":null,"primary_location":{"id":"doi:10.1145/3776734.3794357","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3776734.3794357","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://arrow.tudublin.ie/adaptcon/6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046683105","display_name":"Thanh-Tung Ngo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144925","display_name":"Technological University Dublin","ror":"https://ror.org/04t0qbt32","country_code":"IE","type":"education","lineage":["https://openalex.org/I4210144925"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Thanh-Tung Ngo","raw_affiliation_strings":["Technological University Dublin, Dublin, Ireland"],"raw_orcid":"https://orcid.org/0009-0004-0065-8600","affiliations":[{"raw_affiliation_string":"Technological University Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I4210144925"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078902586","display_name":"Emma Murphy","orcid":"https://orcid.org/0000-0001-6738-3067"},"institutions":[{"id":"https://openalex.org/I4210144925","display_name":"Technological University Dublin","ror":"https://ror.org/04t0qbt32","country_code":"IE","type":"education","lineage":["https://openalex.org/I4210144925"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Emma Murphy","raw_affiliation_strings":["Technological University Dublin, Dublin, Ireland"],"raw_orcid":"https://orcid.org/0000-0001-6738-3067","affiliations":[{"raw_affiliation_string":"Technological University Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I4210144925"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009346892","display_name":"Robert Ross","orcid":"https://orcid.org/0000-0001-7088-273X"},"institutions":[{"id":"https://openalex.org/I4210144925","display_name":"Technological University Dublin","ror":"https://ror.org/04t0qbt32","country_code":"IE","type":"education","lineage":["https://openalex.org/I4210144925"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Robert J. Ross","raw_affiliation_strings":["Technological University Dublin, Dublin, Ireland"],"raw_orcid":"https://orcid.org/0000-0001-7088-273X","affiliations":[{"raw_affiliation_string":"Technological University Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I4210144925"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210144925"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27594108,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"74","last_page":"79"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.33160001039505005,"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"}},"topics":[{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.33160001039505005,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.10520000010728836,"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/T12128","display_name":"AI in Service Interactions","score":0.04619999974966049,"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/interpreter","display_name":"Interpreter","score":0.7397000193595886},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.6830999851226807},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6108999848365784},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.33079999685287476},{"id":"https://openalex.org/keywords/foot","display_name":"Foot (prosody)","score":0.2948000133037567}],"concepts":[{"id":"https://openalex.org/C122783720","wikidata":"https://www.wikidata.org/wiki/Q183065","display_name":"Interpreter","level":2,"score":0.7397000193595886},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.6830999851226807},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6108999848365784},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46299999952316284},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.36469998955726624},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.358599990606308},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34139999747276306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3357999920845032},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.33079999685287476},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.32679998874664307},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.3133000135421753},{"id":"https://openalex.org/C509550671","wikidata":"https://www.wikidata.org/wiki/Q126945","display_name":"Medical education","level":1,"score":0.3089999854564667},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.30630001425743103},{"id":"https://openalex.org/C115076146","wikidata":"https://www.wikidata.org/wiki/Q1651051","display_name":"Foot (prosody)","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C39549134","wikidata":"https://www.wikidata.org/wiki/Q133080","display_name":"Public relations","level":1,"score":0.2912999987602234},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C68122502","wikidata":"https://www.wikidata.org/wiki/Q764527","display_name":"Informed consent","level":3,"score":0.28439998626708984},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2680000066757202},{"id":"https://openalex.org/C162947575","wikidata":"https://www.wikidata.org/wiki/Q2005645","display_name":"Social robot","level":5,"score":0.25619998574256897}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3776734.3794357","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3776734.3794357","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:arrow.tudublin.ie:adaptcon-1005","is_oa":true,"landing_page_url":"https://arrow.tudublin.ie/adaptcon/6","pdf_url":null,"source":{"id":"https://openalex.org/S4377196307","display_name":"Arrow - TU Dublin (Technological University Dublin)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210144925","host_organization_name":"Technological University Dublin","host_organization_lineage":["https://openalex.org/I4210144925"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Conference papers","raw_type":"conferencepaper"}],"best_oa_location":{"id":"pmh:oai:arrow.tudublin.ie:adaptcon-1005","is_oa":true,"landing_page_url":"https://arrow.tudublin.ie/adaptcon/6","pdf_url":null,"source":{"id":"https://openalex.org/S4377196307","display_name":"Arrow - TU Dublin (Technological University Dublin)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210144925","host_organization_name":"Technological University Dublin","host_organization_lineage":["https://openalex.org/I4210144925"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Conference papers","raw_type":"conferencepaper"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1874226381","display_name":null,"funder_award_id":"13/RC/2106_P2","funder_id":"https://openalex.org/F4320336201","funder_display_name":"ADAPT - Centre for Digital Content Technology"}],"funders":[{"id":"https://openalex.org/F4320336201","display_name":"ADAPT - Centre for Digital Content Technology","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W213457136","https://openalex.org/W1897487054","https://openalex.org/W1982643226","https://openalex.org/W2946324343","https://openalex.org/W2967443589","https://openalex.org/W3002310794","https://openalex.org/W3094082662","https://openalex.org/W3124346429","https://openalex.org/W3129573280","https://openalex.org/W3195500026","https://openalex.org/W3198131199","https://openalex.org/W4205643765","https://openalex.org/W4230312136","https://openalex.org/W4310068653","https://openalex.org/W4312674262","https://openalex.org/W4362460422","https://openalex.org/W4385764101","https://openalex.org/W4386066602","https://openalex.org/W4387421378","https://openalex.org/W4387446360","https://openalex.org/W4387446765","https://openalex.org/W4388623205","https://openalex.org/W4392941165","https://openalex.org/W4400822426","https://openalex.org/W4401568411","https://openalex.org/W4402726897","https://openalex.org/W4414281281","https://openalex.org/W6922522607"],"related_works":[],"abstract_inverted_index":{"Effective":[0],"communication":[1],"is":[2],"vital":[3],"in":[4,100,108],"healthcare,":[5],"especially":[6],"across":[7],"language":[8],"barriers,":[9],"where":[10],"non-verbal":[11],"cues":[12],"and":[13,34,36,74,88],"gestures":[14],"are":[15],"critical.":[16],"This":[17],"paper":[18],"presents":[19],"a":[20,50,64,89],"privacy-preserving":[21],"vision-language":[22],"framework":[23],"for":[24,58,71],"medical":[25],"interpreter":[26],"robots":[27],"that":[28],"detects":[29],"specific":[30],"speech":[31,72],"acts":[32,73],"(consent":[33],"instruction)":[35],"generates":[37],"corresponding":[38],"robotic":[39],"gestures.":[40],"Built":[41],"on":[42],"locally":[43],"deployed":[44],"open-source":[45],"models,":[46],"the":[47,104],"system":[48],"utilizes":[49],"Large":[51],"Language":[52],"Model":[53],"(LLM)":[54],"with":[55,76],"few-shot":[56],"prompting":[57],"intent":[59],"detection.":[60],"We":[61],"also":[62],"introduce":[63],"novel":[65],"dataset":[66],"of":[67],"clinical":[68],"conversations":[69],"annotated":[70],"paired":[75],"gesture":[77],"clips.":[78],"Our":[79,93],"identification":[80],"module":[81],"achieved":[82],"0.90":[83],"accuracy,":[84],"0.93":[85],"weighted":[86,91],"precision,":[87],"0.91":[90],"F1-Score.":[92],"approach":[94],"significantly":[95],"improves":[96],"computational":[97],"efficiency":[98],"and,":[99],"user":[101],"studies,":[102],"outperforms":[103],"speech-gesture":[105],"generation":[106],"baseline":[107],"human-likeness":[109],"while":[110],"maintaining":[111],"comparable":[112],"appropriateness.":[113]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2026-03-13T00:00:00"}
