{"id":"https://openalex.org/W4390479111","doi":"https://doi.org/10.1145/3595916.3626411","title":"Efficient Hand Gesture Recognition using Multi-Task Multi-Modal Learning and Self-Distillation","display_name":"Efficient Hand Gesture Recognition using Multi-Task Multi-Modal Learning and Self-Distillation","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4390479111","doi":"https://doi.org/10.1145/3595916.3626411"},"language":"en","primary_location":{"id":"doi:10.1145/3595916.3626411","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626411","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626411","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626411","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103010065","display_name":"Jieying Li","orcid":"https://orcid.org/0009-0004-5239-968X"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jie-Ying Li","raw_affiliation_strings":["National Tsing Hua University, TW"],"raw_orcid":"https://orcid.org/0009-0004-5239-968X","affiliations":[{"raw_affiliation_string":"National Tsing Hua University, TW","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053293297","display_name":"Herman Prawiro","orcid":"https://orcid.org/0009-0005-7823-7176"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Herman Prawiro","raw_affiliation_strings":["National Tsing Hua University, TW"],"raw_orcid":"https://orcid.org/0009-0005-7823-7176","affiliations":[{"raw_affiliation_string":"National Tsing Hua University, TW","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036237990","display_name":"Chia-Chen Chiang","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chia-Chen Chiang","raw_affiliation_strings":["National Tsing Hua University, TW"],"raw_orcid":"https://orcid.org/0009-0006-4491-4690","affiliations":[{"raw_affiliation_string":"National Tsing Hua University, TW","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101694990","display_name":"Hsin-Yu Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Yu Chang","raw_affiliation_strings":["National Tsing Hua University, TW"],"raw_orcid":"https://orcid.org/0009-0005-3800-8782","affiliations":[{"raw_affiliation_string":"National Tsing Hua University, TW","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063016153","display_name":"Tse\u2013Yu Pan","orcid":"https://orcid.org/0000-0001-8570-1575"},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tse-Yu Pan","raw_affiliation_strings":["National Taiwan University of Science and Technology, TW"],"raw_orcid":"https://orcid.org/0000-0001-8570-1575","affiliations":[{"raw_affiliation_string":"National Taiwan University of Science and Technology, TW","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029346217","display_name":"Chih-Tsun Huang","orcid":"https://orcid.org/0000-0002-0214-6826"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chih-Tsun Huang","raw_affiliation_strings":["National Tsing Hua University, TW"],"raw_orcid":"https://orcid.org/0000-0002-0214-6826","affiliations":[{"raw_affiliation_string":"National Tsing Hua University, TW","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029298215","display_name":"Min\u2010Chun Hu","orcid":"https://orcid.org/0000-0003-1917-2155"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Min-Chun Hu","raw_affiliation_strings":["National Tsing Hua University, TW"],"raw_orcid":"https://orcid.org/0000-0003-1917-2155","affiliations":[{"raw_affiliation_string":"National Tsing Hua University, TW","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4491,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.65491407,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":1.0,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9973999857902527,"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":0.8011288642883301},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6556349396705627},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6481629610061646},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.614754319190979},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.600936233997345},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5253493189811707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4925568699836731},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48080959916114807},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4370354413986206},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3242126405239105},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32230305671691895},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10265687108039856},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.0560743510723114}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8011288642883301},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6556349396705627},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6481629610061646},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.614754319190979},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.600936233997345},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5253493189811707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4925568699836731},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48080959916114807},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4370354413986206},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3242126405239105},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32230305671691895},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10265687108039856},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0560743510723114},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3595916.3626411","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626411","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626411","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3595916.3626411","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626411","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626411","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390479111.pdf","grobid_xml":"https://content.openalex.org/works/W4390479111.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2342662179","https://openalex.org/W2471695703","https://openalex.org/W2507009361","https://openalex.org/W2791526950","https://openalex.org/W2904106524","https://openalex.org/W2963155035","https://openalex.org/W2963363373","https://openalex.org/W2963820951","https://openalex.org/W2987861506","https://openalex.org/W2990152177","https://openalex.org/W3168565360","https://openalex.org/W3210459555","https://openalex.org/W4214612132"],"related_works":["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/W2805039731","https://openalex.org/W2989699735"],"abstract_inverted_index":{"In":[0,123],"this":[1],"paper,":[2],"we":[3,79],"propose":[4],"a":[5,26,65,87,137,140],"lightweight":[6],"model":[7,18,101,108,129],"for":[8,151],"hand":[9,23,56,98],"gesture":[10,57,99,138],"recognition":[11,20,100],"using":[12,25],"an":[13],"RGB":[14],"camera.":[15],"The":[16,41],"proposed":[17,42,97],"enables":[19],"of":[21,125],"first-person":[22],"gestures":[24],"single":[27],"camera":[28],"and":[29,37,48,64,91,106,114,119],"achieves":[30],"near-real-time":[31],"computational":[32,92,126],"performance":[33],"on":[34,116,139],"both":[35],"high-end":[36],"low-end":[38,143],"computing":[39],"devices.":[40],"framework":[43],"utilizes":[44],"multi-task":[45],"multi-modal":[46],"learning":[47],"self-distillation":[49,81],"to":[50,69,74,82,135],"deal":[51],"with":[52,102,142],"the":[53,71,84,96,103,110,117],"challenges":[54],"in":[55,133,153],"recognition.":[58],"We":[59,94],"integrate":[60],"additional":[61],"modalities":[62],"(depth)":[63],"future":[66],"prediction":[67],"mechanism":[68],"enhance":[70],"model\u2019s":[72],"ability":[73],"learn":[75],"spatio-temporal":[76],"information.":[77],"Furthermore,":[78],"employ":[80],"compress":[83],"model,":[85],"achieving":[86],"balance":[88],"between":[89],"accuracy":[90],"efficiency.":[93],"compared":[95],"state-of-the-art":[104],"method,":[105],"our":[107,128],"outperforms":[109],"SOTA":[111],"by":[112],"0.88%":[113],"3.52%":[115],"EgoGesture":[118],"NVGesture":[120],"datasets,":[121],"respectively.":[122],"terms":[124],"efficiency,":[127],"takes":[130],"only":[131],"161ms":[132],"average":[134],"recognize":[136],"device":[141],"GPUs":[144],"(NVIDIA":[145],"Jetson":[146],"TX2),":[147],"which":[148],"is":[149],"acceptable":[150],"interaction":[152],"XR":[154],"applications.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}