{"id":"https://openalex.org/W4399509794","doi":"https://doi.org/10.1109/fg59268.2024.10581962","title":"MGRFormer: A Multimodal Transformer Approach for Surgical Gesture Recognition","display_name":"MGRFormer: A Multimodal Transformer Approach for Surgical Gesture Recognition","publication_year":2024,"publication_date":"2024-05-27","ids":{"openalex":"https://openalex.org/W4399509794","doi":"https://doi.org/10.1109/fg59268.2024.10581962"},"language":"en","primary_location":{"id":"doi:10.1109/fg59268.2024.10581962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg59268.2024.10581962","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04603132/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093339745","display_name":"Kevin Feghoul","orcid":null},"institutions":[{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]},{"id":"https://openalex.org/I3018718406","display_name":"Centre Hospitalier Universitaire de Lille","ror":"https://ror.org/02ppyfa04","country_code":"FR","type":"funder","lineage":["https://openalex.org/I3018718406"]},{"id":"https://openalex.org/I154526488","display_name":"Inserm","ror":"https://ror.org/02vjkv261","country_code":"FR","type":"funder","lineage":["https://openalex.org/I154526488"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Kevin Feghoul","raw_affiliation_strings":["Univ. Lille, Inserm, CHU Lille, UMR-S1172 LilNCog,Lille,France,F-59000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Lille, Inserm, CHU Lille, UMR-S1172 LilNCog,Lille,France,F-59000","institution_ids":["https://openalex.org/I154526488","https://openalex.org/I2279609970","https://openalex.org/I3018718406"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031490374","display_name":"Deise Santana Maia","orcid":null},"institutions":[{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]},{"id":"https://openalex.org/I7454413","display_name":"\u00c9cole Centrale de Lille","ror":"https://ror.org/01x441g73","country_code":"FR","type":"education","lineage":["https://openalex.org/I7454413"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Deise Santana Maia","raw_affiliation_strings":["Univ. Lille, CNRS, Centrale Lille, UMR 9189 CRIStAL,Lille,France,F-59000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Lille, CNRS, Centrale Lille, UMR 9189 CRIStAL,Lille,France,F-59000","institution_ids":["https://openalex.org/I7454413","https://openalex.org/I2279609970","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066196909","display_name":"Mehdi El Amrani","orcid":"https://orcid.org/0000-0001-9744-7826"},"institutions":[{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]},{"id":"https://openalex.org/I3018718406","display_name":"Centre Hospitalier Universitaire de Lille","ror":"https://ror.org/02ppyfa04","country_code":"FR","type":"funder","lineage":["https://openalex.org/I3018718406"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mehdi El Amrani","raw_affiliation_strings":["CHU Lille, PRESAGE, Univ. Lille,Department of Digestive Surgery and Transplantation,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CHU Lille, PRESAGE, Univ. Lille,Department of Digestive Surgery and Transplantation,France","institution_ids":["https://openalex.org/I2279609970","https://openalex.org/I3018718406"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017977139","display_name":"Mohamed Daoudi","orcid":"https://orcid.org/0000-0003-4219-7860"},"institutions":[{"id":"https://openalex.org/I7454413","display_name":"\u00c9cole Centrale de Lille","ror":"https://ror.org/01x441g73","country_code":"FR","type":"education","lineage":["https://openalex.org/I7454413"]},{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mohamed Daoudi","raw_affiliation_strings":["Univ. Lille, CNRS, Centrale Lille, UMR 9189 CRIStAL,Lille,France,F-59000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Lille, CNRS, Centrale Lille, UMR 9189 CRIStAL,Lille,France,F-59000","institution_ids":["https://openalex.org/I7454413","https://openalex.org/I2279609970","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036770387","display_name":"Ali Amad","orcid":"https://orcid.org/0000-0002-9029-2910"},"institutions":[{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]},{"id":"https://openalex.org/I3018718406","display_name":"Centre Hospitalier Universitaire de Lille","ror":"https://ror.org/02ppyfa04","country_code":"FR","type":"funder","lineage":["https://openalex.org/I3018718406"]},{"id":"https://openalex.org/I154526488","display_name":"Inserm","ror":"https://ror.org/02vjkv261","country_code":"FR","type":"funder","lineage":["https://openalex.org/I154526488"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ali Amad","raw_affiliation_strings":["Univ. Lille, Inserm, CHU Lille, UMR-S1172 LilNCog,Lille,France,F-59000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Lille, Inserm, CHU Lille, UMR-S1172 LilNCog,Lille,France,F-59000","institution_ids":["https://openalex.org/I154526488","https://openalex.org/I2279609970","https://openalex.org/I3018718406"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5093339745"],"corresponding_institution_ids":["https://openalex.org/I154526488","https://openalex.org/I2279609970","https://openalex.org/I3018718406"],"apc_list":null,"apc_paid":null,"fwci":1.6118,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.82673146,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9976000189781189,"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":0.9976000189781189,"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":0.9332000017166138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.6839150786399841},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6816926002502441},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6363049745559692},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.6116477251052856},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.40144234895706177},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3942485749721527},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34576791524887085},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3271317481994629},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17323875427246094},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1344570815563202}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.6839150786399841},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6816926002502441},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6363049745559692},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.6116477251052856},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.40144234895706177},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3942485749721527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34576791524887085},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3271317481994629},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17323875427246094},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1344570815563202},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/fg59268.2024.10581962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg59268.2024.10581962","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04603132v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04603132","pdf_url":"https://hal.science/hal-04603132/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"18th International Conference on Automatic Face and Gesture Recognition (FG), May 2024, Istanbul, Turkey","raw_type":"Conference papers"},{"id":"pmh:oai:lilloa.univ-lille.fr:20.500.12210/115077","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.12210/115077","pdf_url":null,"source":{"id":"https://openalex.org/S4306402203","display_name":"LillOA (Universit\u00e9 de Lille (University Of Lille))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210123514","host_organization_name":"Centre d'Etudes en Civilisations, Langues et Litt\u00e9ratures Etrang\u00e8res","host_organization_lineage":["https://openalex.org/I4210123514"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04603132v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04603132","pdf_url":"https://hal.science/hal-04603132/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"18th International Conference on Automatic Face and Gesture Recognition (FG), May 2024, Istanbul, Turkey","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4859330304","display_name":null,"funder_award_id":"ANR-16-IDEX-0004 ULNE","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399509794.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2902873204","https://openalex.org/W2185750513","https://openalex.org/W2010878661","https://openalex.org/W3147379364","https://openalex.org/W2026258298","https://openalex.org/W3204639664","https://openalex.org/W2970836791","https://openalex.org/W2805039731","https://openalex.org/W2989699735","https://openalex.org/W4322710567"],"abstract_inverted_index":{"Automatic":[0],"surgical":[1,17,23,49,114],"gesture":[2,50,115],"recognition":[3,51],"has":[4,59],"the":[5,9,46,61,77,99,107,111,122,126],"potential":[6],"to":[7],"revolutionize":[8],"field":[10],"of":[11,22,48,63,73,113],"surgery":[12],"by":[13,53,138],"enhancing":[14],"patient":[15],"care,":[16],"training,":[18],"and":[19,103,125,134],"our":[20,119,130],"understanding":[21],"skills.":[24],"By":[25],"integrating":[26],"kinematic":[27],"data,":[28],"which":[29,81],"precisely":[30],"captures":[31],"hand":[32],"movements,":[33],"with":[34],"video":[35],"data":[36,105],"for":[37,66,110],"contextual":[38,85],"understanding,":[39],"multimodal":[40,95,135],"machine":[41],"learning":[42],"can":[43],"greatly":[44],"enhance":[45],"accuracy":[47],"systems":[52],"capturing":[54],"complementary":[55],"knowledge.":[56],"Recent":[57],"research":[58],"highlighted":[60],"capabilities":[62],"Transformer-based":[64],"models":[65,75],"temporal":[67],"action":[68],"segmentation.":[69],"A":[70],"key":[71],"component":[72],"these":[74],"is":[76],"iterative":[78],"refinement":[79,108],"module,":[80],"enhances":[82],"predictions":[83],"using":[84],"data.":[86],"In":[87],"this":[88],"study,":[89],"we":[90],"propose":[91],"MGRFormer,":[92],"a":[93,139],"novel":[94],"framework":[96],"that":[97,129],"leverages":[98],"interaction":[100],"between":[101],"kinematics":[102],"visual":[104],"at":[106],"stage":[109],"task":[112],"recognition.":[116],"We":[117],"evaluated":[118],"MGRFormer":[120],"on":[121],"VTS":[123],"dataset,":[124],"results":[127],"demonstrated":[128],"approach":[131],"outperformed":[132],"unimodal":[133],"state-of-the-art":[136],"methods":[137],"large":[140],"margin.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2025-10-10T00:00:00"}