{"id":"https://openalex.org/W4410298280","doi":"https://doi.org/10.1109/hri61500.2025.10973846","title":"GestLLM: Advanced Hand Gesture Interpretation via Large Language Models for Human-Robot Interaction","display_name":"GestLLM: Advanced Hand Gesture Interpretation via Large Language Models for Human-Robot Interaction","publication_year":2025,"publication_date":"2025-03-04","ids":{"openalex":"https://openalex.org/W4410298280","doi":"https://doi.org/10.1109/hri61500.2025.10973846"},"language":"en","primary_location":{"id":"doi:10.1109/hri61500.2025.10973846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hri61500.2025.10973846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 20th ACM/IEEE International Conference on Human-Robot Interaction (HRI)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5093826658","display_name":"Oleg Kobzarev","orcid":null},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Oleg Kobzarev","raw_affiliation_strings":["Skolkovo Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Skolkovo Institute of Science and Technology","institution_ids":["https://openalex.org/I125989756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059197603","display_name":"Artem Lykov","orcid":"https://orcid.org/0000-0001-6119-2366"},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Artem Lykov","raw_affiliation_strings":["Skolkovo Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Skolkovo Institute of Science and Technology","institution_ids":["https://openalex.org/I125989756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056458774","display_name":"Dzmitry Tsetserukou","orcid":"https://orcid.org/0000-0001-8055-5345"},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Dzmitry Tsetserukou","raw_affiliation_strings":["Skolkovo Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Skolkovo Institute of Science and Technology","institution_ids":["https://openalex.org/I125989756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I125989756"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1413","last_page":"1417"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9993000030517578,"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":0.9993000030517578,"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/T13382","display_name":"Robotics and Automated Systems","score":0.964900016784668,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9642000198364258,"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/gesture","display_name":"Gesture","score":0.8625408411026001},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7390428185462952},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.6995363235473633},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.6141861081123352},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5778566598892212},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5634262561798096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4465991258621216},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3640095591545105},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1938716173171997}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8625408411026001},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7390428185462952},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.6995363235473633},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.6141861081123352},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5778566598892212},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5634262561798096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4465991258621216},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3640095591545105},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1938716173171997}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hri61500.2025.10973846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hri61500.2025.10973846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 20th ACM/IEEE International Conference on Human-Robot Interaction (HRI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2978665606","https://openalex.org/W2020277666","https://openalex.org/W4287179229","https://openalex.org/W3205513966","https://openalex.org/W3120459843","https://openalex.org/W4366547574","https://openalex.org/W189465620","https://openalex.org/W4366818884","https://openalex.org/W2248308732","https://openalex.org/W4392651289"],"abstract_inverted_index":{"This":[0,48,122,161],"paper":[1,162],"introduces":[2],"GestLLM,":[3],"an":[4],"advanced":[5,174],"system":[6],"for":[7],"human-robot":[8,175],"interaction":[9],"that":[10],"enables":[11],"intuitive":[12,135],"robot":[13,130],"control":[14],"through":[15],"hand":[16,158],"gestures.":[17,47],"Unlike":[18],"conventional":[19],"systems,":[20,55],"which":[21],"rely":[22],"on":[23],"a":[24,43,140,154],"limited":[25],"set":[26],"of":[27,46,129,157],"predefined":[28],"gestures,":[29],"GestLLM":[30,84,138],"leverages":[31],"large":[32],"language":[33,81],"models":[34,91],"and":[35,61,80,127,136,151,167,179],"feature":[36,78],"extraction":[37,79],"via":[38],"MediaPipe":[39],"[1]":[40],"to":[41,64,88,149,153],"interpret":[42],"diverse":[44],"range":[45],"integration":[49],"addresses":[50],"key":[51],"limitations":[52],"in":[53,72,96,144,173],"existing":[54],"such":[56,107],"as":[57,108],"restricted":[58],"gesture":[59],"flexibility":[60,123],"the":[62,109,125],"inability":[63],"recognize":[65],"complex":[66],"or":[67],"unconventional":[68],"gestures":[69,94,103,159],"commonly":[70],"used":[71],"human":[73],"communication.":[74],"By":[75],"combining":[76],"state-of-the-art":[77],"model":[82],"capabilities,":[83],"achieves":[85],"performance":[86],"comparable":[87],"leading":[89],"vision-language":[90],"while":[92],"supporting":[93],"underrepresented":[95],"traditional":[97],"datasets.":[98],"For":[99],"example,":[100],"this":[101],"includes":[102],"from":[104,112],"popular":[105],"culture,":[106],"\u201cVulcan":[110],"salute\u201d":[111],"Star":[113],"Trek,":[114],"without":[115],"any":[116],"additional":[117],"pretraining,":[118],"prompt":[119],"engineering,":[120],"etc.":[121],"enhances":[124],"naturalness":[126],"inclusivity":[128],"control,":[131],"making":[132],"interactions":[133],"more":[134],"user-friendly.":[137],"provides":[139],"significant":[141],"step":[142],"forward":[143],"gesture-based":[145],"interaction,":[146],"enabling":[147],"robots":[148],"understand":[150],"respond":[152],"wide":[155],"variety":[156],"effectively.":[160],"outlines":[163],"its":[164,170],"design,":[165],"implementation,":[166],"evaluation,":[168],"demonstrating":[169],"potential":[171],"applications":[172],"collaboration,":[176],"assistive":[177],"robotics,":[178],"interactive":[180],"entertainment.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}