{"id":"https://openalex.org/W4415536943","doi":"https://doi.org/10.1145/3746027.3755463","title":"Robust Understanding of Human-robot Social Interactions through Multimodal Distillation","display_name":"Robust Understanding of Human-robot Social Interactions through Multimodal Distillation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536943","doi":"https://doi.org/10.1145/3746027.3755463"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3755463","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755463","pdf_url":null,"source":null,"license":null,"license_id":null,"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":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.gla.ac.uk/view/author/73089.html>,","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064144453","display_name":"Tongfei Bian","orcid":"https://orcid.org/0000-0001-5944-4157"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tongfei Bian","raw_affiliation_strings":["School of Computer Science, University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-5944-4157","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058798824","display_name":"Mathieu Chollet","orcid":"https://orcid.org/0000-0001-9858-6844"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mathieu Chollet","raw_affiliation_strings":["School of Computer Science, University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-9858-6844","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021354054","display_name":"Tanaya Guha","orcid":"https://orcid.org/0000-0003-2167-4891"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tanaya Guha","raw_affiliation_strings":["School of Computer Science, University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-2167-4891","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7882870"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5726","last_page":"5734"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.998199999332428,"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":0.998199999332428,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.9958000183105469,"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/robustness","display_name":"Robustness (evolution)","score":0.43470001220703125},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.39739999175071716},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.3871000111103058},{"id":"https://openalex.org/keywords/complete-information","display_name":"Complete information","score":0.3855000138282776},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.36399999260902405},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.2985000014305115},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.2838999927043915}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7233999967575073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.595300018787384},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5292999744415283},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.43470001220703125},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.39739999175071716},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.3855000138282776},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.36399999260902405},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3278999924659729},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2838999927043915},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C130064352","wikidata":"https://www.wikidata.org/wiki/Q853725","display_name":"Social relation","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C79416737","wikidata":"https://www.wikidata.org/wiki/Q2305519","display_name":"Social learning","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755463","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755463","pdf_url":null,"source":null,"license":null,"license_id":null,"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:eprints.gla.ac.uk:359988","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/73089.html>,","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"}],"best_oa_location":{"id":"pmh:oai:eprints.gla.ac.uk:359988","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/73089.html>,","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2737707020","https://openalex.org/W2902105678","https://openalex.org/W2975151577","https://openalex.org/W3035561807","https://openalex.org/W3120349130","https://openalex.org/W3164089640","https://openalex.org/W4220949815","https://openalex.org/W4308432400","https://openalex.org/W4311808540","https://openalex.org/W4318711323","https://openalex.org/W4387664657","https://openalex.org/W4388037600","https://openalex.org/W4388622914","https://openalex.org/W4394606408"],"related_works":[],"abstract_inverted_index":{"There":[0],"is":[1,74,92,171,192],"a":[2,78,103,121],"growing":[3],"need":[4,27],"for":[5],"social":[6,30,45,84,155],"robots":[7],"and":[8,16,32,49,90,96,111,189],"intelligent":[9],"agents":[10,26],"that":[11,40,82,117,140],"can":[12],"effectively":[13],"interact":[14],"with":[15,106,159],"support":[17],"users.":[18],"For":[19],"the":[20,25,182,195],"interactions":[21,43,85],"to":[22,28,58,120,161],"be":[23,59],"seamless,":[24],"analyse":[29],"scenes":[31],"behavioural":[33],"cues":[34],"from":[35],"their":[36],"(robot\u2019s)":[37],"perspective.":[38],"Works":[39],"model":[41,105,123,170,184],"human-agent":[42],"in":[44,61,67,179,185],"situations":[46],"are":[47,54],"few;":[48],"even":[50,158],"those":[51],"existing":[52],"ones":[53],"computationally":[55],"too":[56],"intensive":[57],"deployed":[60],"real":[62],"time":[63],"or":[64],"perform":[65],"poorly":[66],"real-world":[68],"scenarios":[69],"when":[70],"only":[71],"limited":[72],"information":[73,98],"available.":[75],"We":[76,101],"propose":[77],"knowledge":[79,119],"distillation":[80],"framework":[81],"models":[83],"through":[86],"various":[87],"multimodal":[88,107],"cues,":[89],"yet":[91],"robust":[93],"against":[94],"incomplete":[95],"noisy":[97],"during":[99],"inference.":[100],"train":[102],"teacher":[104,183,196],"input":[108,165],"(body,":[109],"face":[110],"hand":[112],"gestures,":[113],"gaze,":[114],"raw":[115],"images)":[116],"transfers":[118],"student":[122,142,169],"which":[124],"relies":[125],"solely":[126],"on":[127,132,152],"body":[128],"pose.":[129],"Extensive":[130],"experiments":[131],"two":[133],"publicly":[134],"available":[135],"human-robot":[136],"interaction":[137],"datasets":[138],"demonstrate":[139],"our":[141],"modelachievesan":[143],"average":[144],"accuracy":[145],"gain":[146],"of":[147,163,181,187,194],"14.75%":[148],"over":[149],"competitive":[150],"baselines":[151],"multiple":[153],"downstream":[154],"understanding":[156],"tasks,":[157],"up":[160],"51%":[162],"its":[164,190],"being":[166],"corrupted.":[167],"The":[168],"also":[172],"highly":[173],"efficient":[174],"-":[175],"less":[176],"than":[177],"1%":[178],"size":[180],"terms":[186],"parameters":[188],"latency":[191],"11.9%":[193],"model.":[197]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
