{"id":"https://openalex.org/W4405156959","doi":"https://doi.org/10.1109/3dv66043.2025.00133","title":"AG-MAE: Anatomically Guided Spatio-Temporal Masked Auto-Encoder for Online Hand Gesture Recognition","display_name":"AG-MAE: Anatomically Guided Spatio-Temporal Masked Auto-Encoder for Online Hand Gesture Recognition","publication_year":2025,"publication_date":"2025-03-25","ids":{"openalex":"https://openalex.org/W4405156959","doi":"https://doi.org/10.1109/3dv66043.2025.00133"},"language":"en","primary_location":{"id":"doi:10.1109/3dv66043.2025.00133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3dv66043.2025.00133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on 3D Vision (3DV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://imt-nord-europe.hal.science/hal-04793721","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5095740332","display_name":"Omar Ikne","orcid":"https://orcid.org/0000-0002-6170-6854"},"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/I205703379","display_name":"Institut Mines-T\u00e9l\u00e9com","ror":"https://ror.org/025vp2923","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Omar Ikne","raw_affiliation_strings":["IMT Nord Europe, Institut Mines-T&#x00E9;l&#x00E9;com, Univ. Lille, Centre for Digital Systems,Lille,France,F-59000","CERI SN - IMT Nord Europe - Centre for Digital Systems (Cit\u00e9 Scientifique, Rue Guglielmo Marconi BP 20145 VILLENEUVE D\u2019ASCQ - France)"],"affiliations":[{"raw_affiliation_string":"IMT Nord Europe, Institut Mines-T&#x00E9;l&#x00E9;com, Univ. Lille, Centre for Digital Systems,Lille,France,F-59000","institution_ids":["https://openalex.org/I2279609970","https://openalex.org/I205703379"]},{"raw_affiliation_string":"CERI SN - IMT Nord Europe - Centre for Digital Systems (Cit\u00e9 Scientifique, Rue Guglielmo Marconi BP 20145 VILLENEUVE D\u2019ASCQ - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050001967","display_name":"Benjamin Allaert","orcid":"https://orcid.org/0000-0002-4291-9803"},"institutions":[{"id":"https://openalex.org/I4210133642","display_name":"IMT Nord Europe","ror":"https://ror.org/042rh9p26","country_code":"FR","type":"education","lineage":["https://openalex.org/I205703379","https://openalex.org/I4210133642"]},{"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/I205703379","display_name":"Institut Mines-T\u00e9l\u00e9com","ror":"https://ror.org/025vp2923","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Benjamin Allaert","raw_affiliation_strings":["IMT Nord Europe, Institut Mines-T&#x00E9;l&#x00E9;com, Univ. Lille, Centre for Digital Systems,Lille,France,F-59000","CERI SN - IMT Nord Europe - Centre for Digital Systems (Cit\u00e9 Scientifique, Rue Guglielmo Marconi BP 20145 VILLENEUVE D\u2019ASCQ - France)","IMT Nord Europe - Ecole nationale sup\u00e9rieure Mines-T\u00e9l\u00e9com Lille Douai (Cit\u00e9 Scientifique, Rue Guglielmo Marconi BP 20145 VILLENEUVE D\u2019ASCQ - France)"],"affiliations":[{"raw_affiliation_string":"IMT Nord Europe, Institut Mines-T&#x00E9;l&#x00E9;com, Univ. Lille, Centre for Digital Systems,Lille,France,F-59000","institution_ids":["https://openalex.org/I2279609970","https://openalex.org/I205703379"]},{"raw_affiliation_string":"CERI SN - IMT Nord Europe - Centre for Digital Systems (Cit\u00e9 Scientifique, Rue Guglielmo Marconi BP 20145 VILLENEUVE D\u2019ASCQ - France)","institution_ids":[]},{"raw_affiliation_string":"IMT Nord Europe - Ecole nationale sup\u00e9rieure Mines-T\u00e9l\u00e9com Lille Douai (Cit\u00e9 Scientifique, Rue Guglielmo Marconi BP 20145 VILLENEUVE D\u2019ASCQ - France)","institution_ids":["https://openalex.org/I4210133642"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030103869","display_name":"Hazem Wannous","orcid":"https://orcid.org/0000-0001-8475-4309"},"institutions":[{"id":"https://openalex.org/I4210115519","display_name":"Centre de Recherche en Informatique","ror":"https://ror.org/020cdve92","country_code":"FR","type":"facility","lineage":["https://openalex.org/I190752583","https://openalex.org/I2746051580","https://openalex.org/I4210091621","https://openalex.org/I4210115519","https://openalex.org/I70768539"]},{"id":"https://openalex.org/I4210133642","display_name":"IMT Nord Europe","ror":"https://ror.org/042rh9p26","country_code":"FR","type":"education","lineage":["https://openalex.org/I205703379","https://openalex.org/I4210133642"]},{"id":"https://openalex.org/I205703379","display_name":"Institut Mines-T\u00e9l\u00e9com","ror":"https://ror.org/025vp2923","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205703379"]},{"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Hazem Wannous","raw_affiliation_strings":["IMT Nord Europe, Institut Mines-T&#x00E9;l&#x00E9;com, Univ. Lille, Centre for Digital Systems,Lille,France,F-59000","IMT Nord Europe - Ecole nationale sup\u00e9rieure Mines-T\u00e9l\u00e9com Lille Douai (Cit\u00e9 Scientifique, Rue Guglielmo Marconi BP 20145 VILLENEUVE D\u2019ASCQ - France)","CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (Universit\u00e9 de Lille - Campus scientifique - B\u00e2timent ESPRIT - Avenue Henri Poincar\u00e9 - 59655 Villeneuve d\u2019Ascq - France)","CERI SN - IMT Nord Europe - Centre for Digital Systems (Cit\u00e9 Scientifique, Rue Guglielmo Marconi BP 20145 VILLENEUVE D\u2019ASCQ - France)"],"affiliations":[{"raw_affiliation_string":"IMT Nord Europe, Institut Mines-T&#x00E9;l&#x00E9;com, Univ. Lille, Centre for Digital Systems,Lille,France,F-59000","institution_ids":["https://openalex.org/I2279609970","https://openalex.org/I205703379"]},{"raw_affiliation_string":"IMT Nord Europe - Ecole nationale sup\u00e9rieure Mines-T\u00e9l\u00e9com Lille Douai (Cit\u00e9 Scientifique, Rue Guglielmo Marconi BP 20145 VILLENEUVE D\u2019ASCQ - France)","institution_ids":["https://openalex.org/I4210133642"]},{"raw_affiliation_string":"CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (Universit\u00e9 de Lille - Campus scientifique - B\u00e2timent ESPRIT - Avenue Henri Poincar\u00e9 - 59655 Villeneuve d\u2019Ascq - France)","institution_ids":["https://openalex.org/I4210115519","https://openalex.org/I2279609970"]},{"raw_affiliation_string":"CERI SN - IMT Nord Europe - Centre for Digital Systems (Cit\u00e9 Scientifique, Rue Guglielmo Marconi BP 20145 VILLENEUVE D\u2019ASCQ - France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5095740332"],"corresponding_institution_ids":["https://openalex.org/I205703379","https://openalex.org/I2279609970"],"apc_list":null,"apc_paid":null,"fwci":3.7499,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90166335,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1406","last_page":"1415"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9994000196456909,"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":0.9994000196456909,"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/T14510","display_name":"Medical Imaging and Analysis","score":0.9412999749183655,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T12740","display_name":"Gait Recognition and Analysis","score":0.9061999917030334,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/computer-science","display_name":"Computer science","score":0.7486580610275269},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.705166757106781},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6412525773048401},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.6038930416107178},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5182754397392273},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5023279190063477},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4765532612800598},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4256821870803833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7486580610275269},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.705166757106781},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6412525773048401},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.6038930416107178},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5182754397392273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5023279190063477},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4765532612800598},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4256821870803833},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/3dv66043.2025.00133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3dv66043.2025.00133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on 3D Vision (3DV)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04793721v1","is_oa":true,"landing_page_url":"https://imt-nord-europe.hal.science/hal-04793721","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"International Conference on 3D Vision, Mar 2025, Singapour, Malaysia","raw_type":"Conference papers"},{"id":"pmh:oai:HAL:hal-05454159v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05454159","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Conference on 3D Vision, Mar 2025, Singapore, Singapore","raw_type":"Conference papers"},{"id":"pmh:oai:lilloa.univ-lille.fr:20.500.12210/119769","is_oa":true,"landing_page_url":null,"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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04793721v1","is_oa":true,"landing_page_url":"https://imt-nord-europe.hal.science/hal-04793721","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"International Conference on 3D Vision, Mar 2025, Singapour, Malaysia","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2537963312","https://openalex.org/W2066003895","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/W2989699735"],"abstract_inverted_index":{"Hand":[0],"gesture":[1,34,109],"recognition":[2],"plays":[3],"a":[4,68,81],"crucial":[5],"role":[6],"in":[7,32],"the":[8,51,58,77,86,116],"domain":[9],"of":[10,54,80,88,118],"computer":[11],"vision,":[12],"as":[13],"it":[14],"enhances":[15],"human-computer":[16],"interaction":[17],"by":[18],"enabling":[19],"intuitive,":[20],"touch-free":[21],"control":[22],"and":[23,40,57,104,121],"communication.":[24],"While":[25],"offline":[26],"methods":[27],"have":[28],"made":[29],"significant":[30],"advances":[31],"isolated":[33],"recognition,":[35],"real-world":[36,125],"applications":[37],"demand":[38],"online":[39,108],"continuous":[41],"processing.":[42],"Skeleton-based":[43],"methods,":[44],"though":[45],"effective,":[46],"face":[47],"challenges":[48],"due":[49],"to":[50,75],"intricate":[52],"nature":[53],"hand":[55,102],"joints":[56],"diverse":[59],"3D":[60,89],"motions":[61],"they":[62],"induce.":[63],"This":[64],"paper":[65],"introduces":[66],"AG-MAE,":[67],"novel":[69],"approach":[70,120],"that":[71],"integrates":[72],"anatomical":[73,94],"constraints":[74],"guide":[76],"self-supervised":[78],"training":[79],"spatio-temporal":[82],"masked":[83],"autoencoder,":[84],"enhancing":[85],"learning":[87],"keypoint":[90],"representations.":[91],"By":[92],"incorporating":[93],"knowledge,":[95],"AG-MAE":[96],"learns":[97],"more":[98],"discriminative":[99],"features":[100],"for":[101,124],"poses":[103],"movements,":[105],"subsequently":[106],"improving":[107],"recognition.":[110],"Evaluation":[111],"on":[112],"standard":[113],"datasets":[114],"demonstrates":[115],"superiority":[117],"our":[119],"its":[122],"potential":[123],"applications.":[126],"Code":[127],"is":[128],"available":[129],"at:":[130],"https://github.com/o-ikne/AG-MAE.git.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
