{"id":"https://openalex.org/W4416261834","doi":"https://doi.org/10.1145/3756884.3765982","title":"Gated Temporal Shifts with Depth-Efficient Channel Attention for Real-Time Hand-Gesture Interaction","display_name":"Gated Temporal Shifts with Depth-Efficient Channel Attention for Real-Time Hand-Gesture Interaction","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W4416261834","doi":"https://doi.org/10.1145/3756884.3765982"},"language":"en","primary_location":{"id":"doi:10.1145/3756884.3765982","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3756884.3765982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 31st ACM Symposium on Virtual Reality Software and Technology","raw_type":"proceedings-article"},"type":"article","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/A5093446588","display_name":"Salah-Eddine Laidoudi","orcid":"https://orcid.org/0009-0002-5209-9893"},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210094080","display_name":"ESME - \u00c9cole d\u2019ing\u00e9nieurs pluridisciplinaires","ror":"https://ror.org/00nf3nv81","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210094080"]},{"id":"https://openalex.org/I4210107733","display_name":"Informatique, BioInformatique, Syst\u00e8mes Complexes","ror":"https://ror.org/01aqxgr98","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I277688954","https://openalex.org/I4210107733","https://openalex.org/I88467170"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Salah eddine Laidoudi","raw_affiliation_strings":["IBISC, Universit\u00e9 Paris-Saclay, Univ Evry, Evry-courcouronnes, France and ESME Research Lab, ESME SUDRIA, Ivry-sur-seine, France","ESME Research Lab (France)"],"raw_orcid":"https://orcid.org/0009-0002-5209-9893","affiliations":[{"raw_affiliation_string":"IBISC, Universit\u00e9 Paris-Saclay, Univ Evry, Evry-courcouronnes, France and ESME Research Lab, ESME SUDRIA, Ivry-sur-seine, France","institution_ids":["https://openalex.org/I4210094080","https://openalex.org/I277688954","https://openalex.org/I4210107733"]},{"raw_affiliation_string":"ESME Research Lab (France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046766094","display_name":"Madjid Ma\u00efdi","orcid":"https://orcid.org/0000-0001-7070-006X"},"institutions":[{"id":"https://openalex.org/I4210094115","display_name":"Laboratoire d'Informatique Algorithmique: Fondements et Applications","ror":"https://ror.org/00pbqgm18","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I204730241","https://openalex.org/I4210094115","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I48825208","display_name":"Universit\u00e9 Paris 8","ror":"https://ror.org/04wez5e68","country_code":"FR","type":"education","lineage":["https://openalex.org/I48825208"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Madjid Maidi","raw_affiliation_strings":["Universit\u00e9 Paris 8 LIASD, Paris, France","LIASD - Laboratoire d'Informatique Avanc\u00e9e de Saint-Denis (Universit\u00e9 Paris 8 Vincennes-Saint-Denis - 2 rue de la Libert\u00e9 - 93526 Saint-Denis cedex - France)"],"raw_orcid":"https://orcid.org/0000-0001-7070-006X","affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris 8 LIASD, Paris, France","institution_ids":["https://openalex.org/I48825208","https://openalex.org/I4210094115"]},{"raw_affiliation_string":"LIASD - Laboratoire d'Informatique Avanc\u00e9e de Saint-Denis (Universit\u00e9 Paris 8 Vincennes-Saint-Denis - 2 rue de la Libert\u00e9 - 93526 Saint-Denis cedex - France)","institution_ids":["https://openalex.org/I48825208"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068108127","display_name":"Samir Otmane","orcid":"https://orcid.org/0000-0003-2221-4264"},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210107733","display_name":"Informatique, BioInformatique, Syst\u00e8mes Complexes","ror":"https://ror.org/01aqxgr98","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I277688954","https://openalex.org/I4210107733","https://openalex.org/I88467170"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Samir Otmane","raw_affiliation_strings":["IBISC, Universit\u00e9 Paris-Saclay, Univ Evry, Evry-courcouronnes, France"],"raw_orcid":"https://orcid.org/0000-0003-2221-4264","affiliations":[{"raw_affiliation_string":"IBISC, Universit\u00e9 Paris-Saclay, Univ Evry, Evry-courcouronnes, France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I4210107733"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5093446588"],"corresponding_institution_ids":["https://openalex.org/I277688954","https://openalex.org/I4210094080","https://openalex.org/I4210107733"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.32868733,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.95169997215271,"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":0.95169997215271,"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":0.019999999552965164,"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":0.01549999974668026,"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/rgb-color-model","display_name":"RGB color model","score":0.6276999711990356},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5784000158309937},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4893999993801117},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.462799996137619},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4381999969482422},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.40139999985694885},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.3846000134944916},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37560001015663147},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.37400001287460327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6996999979019165},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.6276999711990356},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5784000158309937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5722000002861023},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4893999993801117},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47760000824928284},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.462799996137619},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4381999969482422},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.40139999985694885},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.3846000134944916},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.37400001287460327},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.28290000557899475},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2667999863624573},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.262800008058548},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.2547000050544739},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3756884.3765982","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3756884.3765982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 31st ACM Symposium on Virtual Reality Software and Technology","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-05297910v1","is_oa":false,"landing_page_url":"https://univ-evry.hal.science/hal-05297910","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"31st ACM Symposium on Virtual Reality Software and Technology (VRST 2025), Nov 2025, Montreal, Canada","raw_type":"Conference papers"}],"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":[],"abstract_inverted_index":{"We":[0],"introduce":[1,153],"a":[2,18,27,49],"compact":[3],"video-classification":[4],"pipeline":[5],"for":[6,175],"real-time":[7],"dynamic":[8],"hand-gesture":[9],"recognition":[10],"in":[11],"mixed-reality":[12],"(MR)":[13],"settings.":[14],"The":[15,106],"network":[16],"marries":[17],"MobileNetV3":[19,145],"backbone":[20],"with":[21],"two":[22],"purpose-built":[23],"temporal":[24],"components:":[25],"(1)":[26],"Gated":[28],"Discriminative":[29],"Temporal":[30],"Shift":[31],"Module":[32],"(G-DiTSM)":[33],"that":[34,56,131],"inserts":[35],"first-order":[36],"motion":[37],"differences":[38],"and":[39,47,82,111,119,133,139,152,165,179],"learns":[40],"channel-wise":[41],"gates":[42],"to":[43,161],"fuse":[44],"them":[45],"adaptively,":[46],"(2)":[48],"lightweight":[50],"Depth-Efficient":[51],"Channel":[52],"Attention":[53],"(DepthECA)":[54],"block":[55],"recalibrates":[57],"spatial":[58],"features":[59],"on":[60,64,90],"the":[61,75,91,144,156,162,173],"fly.":[62],"Operating":[63],"eight":[65],"sparsely":[66],"sampled":[67],"frames":[68],"per":[69,87],"clip":[70],"(Temporal":[71],"Segment":[72],"Network":[73],"paradigm),":[74],"resulting":[76],"model":[77],"contains":[78],"2.65":[79],"M":[80],"parameters":[81],"requires":[83],"only":[84,183],"0.084":[85],"GFLOPs":[86],"inference.":[88],"Evaluated":[89],"RGB-only":[92],"20BN":[93],"Jester":[94],"benchmark":[95],"(148k":[96],"clips":[97],"spanning":[98],"27":[99],"gesture":[100],"classes)":[101],"recorded":[102],"from":[103],"front-facing":[104],"viewpoints.":[105],"system":[107],"reaches":[108],"95.34%":[109],"Top-1":[110],"99.80%":[112],"Top-5":[113],"accuracy,":[114],"surpassing":[115],"recent":[116],"3D":[117],"CNNs":[118],"transformer":[120],"baselines":[121],"while":[122],"being":[123],"an":[124],"order":[125],"of":[126,168],"magnitude":[127],"lighter.":[128],"Ablations":[129],"confirm":[130],"DepthECA":[132],"G-DiTSM":[134],"provide":[135],"complementary":[136],"gains":[137],"(+18.78%":[138],"+0.93%":[140],"Top-1,":[141],"respectively,":[142],"over":[143],"baseline).":[146],"Because":[147],"all":[148],"components":[149],"are":[150],"plug-and-play":[151],"minimal":[154],"overhead,":[155],"architecture":[157],"is":[158],"well":[159],"suited":[160],"tight":[163],"latency":[164],"power":[166],"budgets":[167],"standalone":[169],"MR":[170],"headsets,":[171],"paving":[172],"way":[174],"natural":[176],"grab,":[177],"rotate,":[178],"command":[180],"interactions":[181],"using":[182],"on-board":[184],"RGB":[185],"cameras":[186]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}