{"id":"https://openalex.org/W4415822120","doi":"https://doi.org/10.1109/ro-man63969.2025.11217528","title":"How do Foundation Models Compare to Skeleton-Based Approaches for Gesture Recognition in Human-Robot Interaction?","display_name":"How do Foundation Models Compare to Skeleton-Based Approaches for Gesture Recognition in Human-Robot Interaction?","publication_year":2025,"publication_date":"2025-08-25","ids":{"openalex":"https://openalex.org/W4415822120","doi":"https://doi.org/10.1109/ro-man63969.2025.11217528"},"language":null,"primary_location":{"id":"doi:10.1109/ro-man63969.2025.11217528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man63969.2025.11217528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119524552","display_name":"Stephanie K\u00e4s","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Stephanie K\u00e4s","raw_affiliation_strings":["RWTH Aachen University,Chair for Computer Vision,Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Chair for Computer Vision,Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119524554","display_name":"Anton Burenko","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Anton Burenko","raw_affiliation_strings":["RWTH Aachen University,Chair for Computer Vision,Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Chair for Computer Vision,Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119998734","display_name":"Louis Markert","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Louis Markert","raw_affiliation_strings":["RWTH Aachen University,Chair for Computer Vision,Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Chair for Computer Vision,Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030302140","display_name":"Onur \u00c7ulha","orcid":"https://orcid.org/0000-0002-9192-5476"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Onur Alp \u00c7ulha","raw_affiliation_strings":["RWTH Aachen University,Chair for Computer Vision,Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Chair for Computer Vision,Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dennis Mack","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128710","display_name":"Robert Bosch (United Kingdom)","ror":"https://ror.org/031zzq071","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210128710","https://openalex.org/I889804353"]},{"id":"https://openalex.org/I4210156055","display_name":"Robert Bosch (Netherlands)","ror":"https://ror.org/057aydj06","country_code":"NL","type":"company","lineage":["https://openalex.org/I4210156055","https://openalex.org/I889804353"]},{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE","GB","NL"],"is_corresponding":false,"raw_author_name":"Dennis Mack","raw_affiliation_strings":["Corporate Research & Bosch Center for AI,Robert Bosch GmbH,Renningen and Hildesheim,Germany"],"affiliations":[{"raw_affiliation_string":"Corporate Research & Bosch Center for AI,Robert Bosch GmbH,Renningen and Hildesheim,Germany","institution_ids":["https://openalex.org/I4210156055","https://openalex.org/I889804353","https://openalex.org/I4210128710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084203306","display_name":"Timm Linder","orcid":"https://orcid.org/0000-0001-8532-0262"},"institutions":[{"id":"https://openalex.org/I4210128710","display_name":"Robert Bosch (United Kingdom)","ror":"https://ror.org/031zzq071","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210128710","https://openalex.org/I889804353"]},{"id":"https://openalex.org/I4210156055","display_name":"Robert Bosch (Netherlands)","ror":"https://ror.org/057aydj06","country_code":"NL","type":"company","lineage":["https://openalex.org/I4210156055","https://openalex.org/I889804353"]},{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE","GB","NL"],"is_corresponding":false,"raw_author_name":"Timm Linder","raw_affiliation_strings":["Corporate Research & Bosch Center for AI,Robert Bosch GmbH,Renningen and Hildesheim,Germany"],"affiliations":[{"raw_affiliation_string":"Corporate Research & Bosch Center for AI,Robert Bosch GmbH,Renningen and Hildesheim,Germany","institution_ids":["https://openalex.org/I4210156055","https://openalex.org/I889804353","https://openalex.org/I4210128710"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071006649","display_name":"Bastian Leibe","orcid":"https://orcid.org/0000-0003-4225-0051"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bastian Leibe","raw_affiliation_strings":["RWTH Aachen University,Chair for Computer Vision,Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Chair for Computer Vision,Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5119524552"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":1.5297,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86088584,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"477","last_page":"477"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.6371999979019165,"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"}},"topics":[{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.6371999979019165,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.24619999527931213,"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":0.023800000548362732,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.8726000189781189},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.6765000224113464},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5350000262260437},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.5249999761581421},{"id":"https://openalex.org/keywords/agile-software-development","display_name":"Agile software development","score":0.43650001287460327}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8726000189781189},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7473999857902527},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.6765000224113464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5662000179290771},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5350000262260437},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.5249999761581421},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4397999942302704},{"id":"https://openalex.org/C14185376","wikidata":"https://www.wikidata.org/wiki/Q30232","display_name":"Agile software development","level":2,"score":0.43650001287460327},{"id":"https://openalex.org/C132900626","wikidata":"https://www.wikidata.org/wiki/Q7534733","display_name":"Sketch recognition","level":4,"score":0.43070000410079956},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.30309998989105225},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29600000381469727},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2822999954223633},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25850000977516174}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ro-man63969.2025.11217528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man63969.2025.11217528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313176","display_name":"Robert Bosch","ror":"https://ror.org/02venad53"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1981167598","https://openalex.org/W2018369130","https://openalex.org/W2106996050","https://openalex.org/W2128584216","https://openalex.org/W2161319957","https://openalex.org/W2168392347","https://openalex.org/W2547599103","https://openalex.org/W2592523922","https://openalex.org/W2605010847","https://openalex.org/W2911055311","https://openalex.org/W2911956695","https://openalex.org/W2944006115","https://openalex.org/W2962896489","https://openalex.org/W2963076818","https://openalex.org/W2963150697","https://openalex.org/W2963389958","https://openalex.org/W2970971158","https://openalex.org/W2981311757","https://openalex.org/W3042515967","https://openalex.org/W3124887724","https://openalex.org/W3126321356","https://openalex.org/W3130641941","https://openalex.org/W3157441214","https://openalex.org/W3186300478","https://openalex.org/W3210179512","https://openalex.org/W4200015283","https://openalex.org/W4200099027","https://openalex.org/W4226069291","https://openalex.org/W4316669449","https://openalex.org/W4319301054","https://openalex.org/W4323536993","https://openalex.org/W4380683077","https://openalex.org/W4383066160","https://openalex.org/W4384822009","https://openalex.org/W4386076501","https://openalex.org/W4388823657","https://openalex.org/W4389366350","https://openalex.org/W4390871806","https://openalex.org/W4390872764","https://openalex.org/W4390873156","https://openalex.org/W4390873451","https://openalex.org/W4390874024","https://openalex.org/W4392254668","https://openalex.org/W4393170627","https://openalex.org/W4399423240","https://openalex.org/W4406188408","https://openalex.org/W4408356068","https://openalex.org/W4412722337","https://openalex.org/W4413146669","https://openalex.org/W4413945498"],"related_works":[],"abstract_inverted_index":{"Gestures":[0],"enable":[1],"non-verbal":[2],"human-robot":[3,91],"communication,":[4],"especially":[5],"in":[6,93,148],"noisy":[7],"environments":[8],"like":[9],"agile":[10],"production.":[11],"Traditional":[12],"deep":[13],"learning-based":[14],"gesture":[15,65,100],"recognition":[16,101],"relies":[17],"on":[18,145,158],"task-specific":[19,54,117],"architectures":[20],"using":[21,129],"images,":[22],"videos,":[23],"or":[24],"skeletal":[25],"pose":[26],"estimates":[27],"as":[28,131],"input.":[29],"Meanwhile,":[30],"Vision":[31,36],"Foundation":[32],"Models":[33,38],"(VFMs)":[34],"and":[35,78],"Language":[37],"(VLMs)":[39],"with":[40,114],"their":[41],"strong":[42],"generalization":[43],"abilities":[44],"offer":[45],"potential":[46],"to":[47,96,140],"reduce":[48],"system":[49,126],"complexity":[50],"by":[51,128],"replacing":[52],"dedicated":[53],"modules.":[55],"This":[56],"study":[57],"investigates":[58],"adapting":[59],"such":[60],"models":[61],"for":[62,90,162],"dynamic,":[63],"full-body":[64],"recognition,":[66],"comparing":[67],"V-JEPA":[68,111],"(a":[69,75,80],"state-of-the-art":[70],"VFM),":[71],"Gemini":[72,138],"Flash":[73],"2.0":[74],"multimodal":[76],"VLM),":[77],"HD-GCN":[79,106],"top-performing":[81],"skeleton-based":[82],"approach).":[83],"We":[84],"introduce":[85],"NUGGET,":[86],"a":[87,115,121,132],"dataset":[88],"tailored":[89],"communication":[92],"intralogistics":[94],"environments,":[95],"evaluate":[97],"the":[98,149,153],"different":[99],"approaches.":[102],"In":[103,136],"our":[104],"experiments,":[105],"achieves":[107],"best":[108],"performance,":[109],"but":[110],"comes":[112],"close":[113],"simple,":[116],"classification":[118],"head\u2014thus":[119],"paving":[120],"possible":[122],"way":[123],"towards":[124],"reducing":[125],"complexity,":[127],"it":[130],"shared":[133],"multi-task":[134],"model.":[135],"contrast,":[137],"struggles":[139],"differentiate":[141],"gestures":[142],"based":[143],"solely":[144],"textual":[146],"descriptions":[147],"zero-shot":[150],"setting,":[151],"highlighting":[152],"need":[154],"of":[155],"further":[156],"research":[157],"suitable":[159],"input":[160],"representations":[161],"gestures.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-11-03T00:00:00"}