{"id":"https://openalex.org/W4417049627","doi":"https://doi.org/10.3390/virtualworlds4040058","title":"TSMTFN: Two-Stream Temporal Shift Module Network for Efficient Egocentric Gesture Recognition in Virtual Reality","display_name":"TSMTFN: Two-Stream Temporal Shift Module Network for Efficient Egocentric Gesture Recognition in Virtual Reality","publication_year":2025,"publication_date":"2025-12-04","ids":{"openalex":"https://openalex.org/W4417049627","doi":"https://doi.org/10.3390/virtualworlds4040058"},"language":"en","primary_location":{"id":"doi:10.3390/virtualworlds4040058","is_oa":true,"landing_page_url":"https://doi.org/10.3390/virtualworlds4040058","pdf_url":"https://www.mdpi.com/2813-2084/4/4/58/pdf","source":{"id":"https://openalex.org/S4387280281","display_name":"Virtual Worlds","issn_l":"2813-2084","issn":["2813-2084"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Virtual Worlds","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.mdpi.com/2813-2084/4/4/58/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073031300","display_name":"Muhammad Abrar Hussain","orcid":"https://orcid.org/0009-0007-0863-3346"},"institutions":[{"id":"https://openalex.org/I152238500","display_name":"Chosun University","ror":"https://ror.org/01zt9a375","country_code":"KR","type":"education","lineage":["https://openalex.org/I152238500"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Muhammad Abrar Hussain","raw_affiliation_strings":["Department of Computer Engineering, Chosun University, Dong-gu, Gwangju 61452, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0007-0863-3346","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Chosun University, Dong-gu, Gwangju 61452, Republic of Korea","institution_ids":["https://openalex.org/I152238500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083817509","display_name":"Chanjun Chun","orcid":"https://orcid.org/0000-0003-3361-8360"},"institutions":[{"id":"https://openalex.org/I152238500","display_name":"Chosun University","ror":"https://ror.org/01zt9a375","country_code":"KR","type":"education","lineage":["https://openalex.org/I152238500"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chanjun Chun","raw_affiliation_strings":["Department of Computer Engineering, Chosun University, Dong-gu, Gwangju 61452, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-3361-8360","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Chosun University, Dong-gu, Gwangju 61452, Republic of Korea","institution_ids":["https://openalex.org/I152238500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005406818","display_name":"SeongKi Kim","orcid":"https://orcid.org/0000-0002-2664-3632"},"institutions":[{"id":"https://openalex.org/I152238500","display_name":"Chosun University","ror":"https://ror.org/01zt9a375","country_code":"KR","type":"education","lineage":["https://openalex.org/I152238500"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"SeongKi Kim","raw_affiliation_strings":["Department of Computer Engineering, Chosun University, Dong-gu, Gwangju 61452, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-2664-3632","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Chosun University, Dong-gu, Gwangju 61452, Republic of Korea","institution_ids":["https://openalex.org/I152238500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005406818"],"corresponding_institution_ids":["https://openalex.org/I152238500"],"apc_list":null,"apc_paid":null,"fwci":1.5238,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87268567,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"4","issue":"4","first_page":"58","last_page":"58"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.49390000104904175,"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":0.49390000104904175,"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":0.2838999927043915,"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/T10789","display_name":"Interactive and Immersive Displays","score":0.05380000174045563,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.6146000027656555},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.5914000272750854},{"id":"https://openalex.org/keywords/virtual-reality","display_name":"Virtual reality","score":0.5763000249862671},{"id":"https://openalex.org/keywords/wearable-computer","display_name":"Wearable computer","score":0.5702000260353088},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4320000112056732},{"id":"https://openalex.org/keywords/augmented-reality","display_name":"Augmented reality","score":0.4309999942779541},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.41819998621940613},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.37940001487731934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7986999750137329},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6665999889373779},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.6146000027656555},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.5914000272750854},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.5763000249862671},{"id":"https://openalex.org/C150594956","wikidata":"https://www.wikidata.org/wiki/Q1334829","display_name":"Wearable computer","level":2,"score":0.5702000260353088},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5396999716758728},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4320000112056732},{"id":"https://openalex.org/C153715457","wikidata":"https://www.wikidata.org/wiki/Q254183","display_name":"Augmented reality","level":2,"score":0.4309999942779541},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.41819998621940613},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.3693000078201294},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3596000075340271},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3393000066280365},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C54290928","wikidata":"https://www.wikidata.org/wiki/Q4845080","display_name":"Wearable technology","level":3,"score":0.28600001335144043},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.26930001378059387},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/virtualworlds4040058","is_oa":true,"landing_page_url":"https://doi.org/10.3390/virtualworlds4040058","pdf_url":"https://www.mdpi.com/2813-2084/4/4/58/pdf","source":{"id":"https://openalex.org/S4387280281","display_name":"Virtual Worlds","issn_l":"2813-2084","issn":["2813-2084"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Virtual Worlds","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:f0ba8d0b79c846519bc8adb08428a839","is_oa":true,"landing_page_url":"https://doaj.org/article/f0ba8d0b79c846519bc8adb08428a839","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Virtual Worlds, Vol 4, Iss 4, p 58 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/virtualworlds4040058","is_oa":true,"landing_page_url":"https://doi.org/10.3390/virtualworlds4040058","pdf_url":"https://www.mdpi.com/2813-2084/4/4/58/pdf","source":{"id":"https://openalex.org/S4387280281","display_name":"Virtual Worlds","issn_l":"2813-2084","issn":["2813-2084"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Virtual Worlds","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8730027095","display_name":null,"funder_award_id":"NRF-2023R1A2C1005950","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417049627.pdf","grobid_xml":"https://content.openalex.org/works/W4417049627.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W2770472008","https://openalex.org/W2781400102","https://openalex.org/W2791526950","https://openalex.org/W2884585870","https://openalex.org/W2904106524","https://openalex.org/W2913362834","https://openalex.org/W2963155035","https://openalex.org/W2963524571","https://openalex.org/W2973104987","https://openalex.org/W2990503944","https://openalex.org/W2992308087","https://openalex.org/W2998639786","https://openalex.org/W3044285175","https://openalex.org/W3120863767","https://openalex.org/W4206974629","https://openalex.org/W4226270831","https://openalex.org/W4312097322","https://openalex.org/W4319990484","https://openalex.org/W4382139000","https://openalex.org/W4383555203","https://openalex.org/W4386285324","https://openalex.org/W4391897651","https://openalex.org/W4393067728","https://openalex.org/W4401296603","https://openalex.org/W4404008040","https://openalex.org/W4405056285","https://openalex.org/W4405235318","https://openalex.org/W4406657354","https://openalex.org/W4406714402","https://openalex.org/W4411957336","https://openalex.org/W4412722337","https://openalex.org/W4413038282","https://openalex.org/W4414425396"],"related_works":[],"abstract_inverted_index":{"Egocentric":[0],"hand":[1],"gesture":[2,157,176],"recognition":[3,49,152],"is":[4],"vital":[5],"for":[6,62,71,172],"natural":[7],"human\u2013computer":[8],"interaction":[9],"in":[10,132],"augmented":[11],"and":[12,26,66,84,89,99,112,125,159,169],"virtual":[13],"reality":[14],"(AR/VR)":[15],"systems.":[16],"However,":[17],"most":[18],"deep":[19],"learning":[20],"models":[21],"struggle":[22],"to":[23,80,135],"balance":[24],"accuracy":[25,50,111,115],"efficiency,":[27],"limiting":[28],"real-time":[29,146],"use":[30],"on":[31,76,103,116],"wearable":[32,174],"devices.":[33],"This":[34],"paper":[35],"introduces":[36],"a":[37,67,129],"Two-Stream":[38],"Temporal":[39,58],"Shift":[40,59],"Module":[41],"Transformer":[42],"Fusion":[43],"Network":[44],"(TSMTFN)":[45],"that":[46],"achieves":[47],"high":[48],"with":[51,121],"low":[52],"computational":[53],"cost.":[54],"The":[55,139,148],"model":[56,140],"integrates":[57],"Modules":[60],"(TSMs)":[61],"efficient":[63],"motion":[64],"modeling":[65],"Transformer-based":[68],"fusion":[69],"mechanism":[70],"long-range":[72],"temporal":[73],"understanding,":[74],"operating":[75],"dual":[77],"RGB-D":[78],"streams":[79],"capture":[81],"complementary":[82],"visual":[83],"depth":[85],"cues.":[86],"Training":[87],"stability":[88],"generalization":[90],"are":[91],"enhanced":[92],"through":[93],"full-layer":[94],"training":[95],"from":[96],"epoch":[97],"1":[98],"MixUp/CutMix":[100],"augmentations.":[101],"Evaluated":[102],"the":[104,117],"EgoGesture":[105],"dataset,":[106],"TSMTFN":[107,164],"attained":[108],"96.18%":[109],"top-1":[110],"99.61%":[113],"top-5":[114],"independent":[118],"test":[119],"set":[120],"only":[122],"16":[123],"GFLOPs":[124],"21.3M":[126],"parameters,":[127],"offering":[128],"2.4\u20134.7\u00d7":[130],"reduction":[131],"computation":[133],"compared":[134],"recent":[136],"state-of-the-art":[137],"methods.":[138],"runs":[141],"at":[142],"15.10":[143],"samples/s,":[144],"achieving":[145],"performance.":[147],"results":[149],"demonstrate":[150],"robust":[151],"across":[153],"over":[154],"95%":[155],"of":[156],"classes":[158],"minimal":[160],"inter-class":[161],"confusion,":[162],"establishing":[163],"as":[165],"an":[166],"efficient,":[167],"accurate,":[168],"deployable":[170],"solution":[171],"next-generation":[173],"AR/VR":[175],"interfaces.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-07T13:37:22.277990","created_date":"2025-12-05T00:00:00"}