{"id":"https://openalex.org/W4403791003","doi":"https://doi.org/10.1145/3664647.3681578","title":"Siformer: Feature-isolated Transformer for Efficient Skeleton-based Sign Language Recognition","display_name":"Siformer: Feature-isolated Transformer for Efficient Skeleton-based Sign Language Recognition","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791003","doi":"https://doi.org/10.1145/3664647.3681578"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681578","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://researchmgt.monash.edu/ws/files/668651513/635449284-oa.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005649659","display_name":"Muxin Pu","orcid":null},"institutions":[{"id":"https://openalex.org/I11662577","display_name":"Monash University Malaysia","ror":"https://ror.org/00yncr324","country_code":"MY","type":"education","lineage":["https://openalex.org/I11662577"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Muxin Pu","raw_affiliation_strings":["School of Information Technology, Monash University Malaysia, Subang Jaya, Selangor, Malaysia"],"affiliations":[{"raw_affiliation_string":"School of Information Technology, Monash University Malaysia, Subang Jaya, Selangor, Malaysia","institution_ids":["https://openalex.org/I11662577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046137969","display_name":"Mei Kuan Lim","orcid":"https://orcid.org/0000-0001-8834-9933"},"institutions":[{"id":"https://openalex.org/I11662577","display_name":"Monash University Malaysia","ror":"https://ror.org/00yncr324","country_code":"MY","type":"education","lineage":["https://openalex.org/I11662577"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Mei Kuan Lim","raw_affiliation_strings":["School of Information Technology, Monash University Malaysia, Subang Jaya, Selangor, Malaysia"],"affiliations":[{"raw_affiliation_string":"School of Information Technology, Monash University Malaysia, Subang Jaya, Selangor, Malaysia","institution_ids":["https://openalex.org/I11662577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024635381","display_name":"Chun Yong Chong","orcid":"https://orcid.org/0000-0003-1164-0049"},"institutions":[{"id":"https://openalex.org/I11662577","display_name":"Monash University Malaysia","ror":"https://ror.org/00yncr324","country_code":"MY","type":"education","lineage":["https://openalex.org/I11662577"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Chun Yong Chong","raw_affiliation_strings":["School of Information Technology, Monash University Malaysia, Subang Jaya, Selangor, Malaysia"],"affiliations":[{"raw_affiliation_string":"School of Information Technology, Monash University Malaysia, Subang Jaya, Selangor, Malaysia","institution_ids":["https://openalex.org/I11662577"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005649659"],"corresponding_institution_ids":["https://openalex.org/I11662577"],"apc_list":null,"apc_paid":null,"fwci":2.589,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.89824823,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"9387","last_page":"9396"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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":0.9976000189781189,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9958000183105469,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6744500994682312},{"id":"https://openalex.org/keywords/sign-language","display_name":"Sign language","score":0.623298704624176},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5860821604728699},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.506639301776886},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45878201723098755},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4326876401901245},{"id":"https://openalex.org/keywords/skeleton","display_name":"Skeleton (computer programming)","score":0.4237358272075653},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39418572187423706},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3270331025123596},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3249870538711548},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16147279739379883},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10509440302848816},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08117073774337769},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06899088621139526},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0679541528224945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6744500994682312},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.623298704624176},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5860821604728699},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.506639301776886},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45878201723098755},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4326876401901245},{"id":"https://openalex.org/C18969341","wikidata":"https://www.wikidata.org/wiki/Q1169129","display_name":"Skeleton (computer programming)","level":2,"score":0.4237358272075653},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39418572187423706},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3270331025123596},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3249870538711548},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16147279739379883},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10509440302848816},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08117073774337769},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06899088621139526},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0679541528224945},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3681578","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:monash.edu:publications/e6049e1a-547d-475b-9f5b-e12772ab12d2","is_oa":true,"landing_page_url":"https://research.monash.edu/en/publications/e6049e1a-547d-475b-9f5b-e12772ab12d2","pdf_url":"https://researchmgt.monash.edu/ws/files/668651513/635449284-oa.pdf","source":{"id":"https://openalex.org/S4306402625","display_name":"Monash University Research Portal (Monash University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I56590836","host_organization_name":"Monash University","host_organization_lineage":["https://openalex.org/I56590836"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Pu, M, Lim, M K & Chong, C Y 2024, Siformer : Feature-isolated Transformer for Efficient Skeleton-based Sign Language Recognition. in Y Luo, T Do & Y Yan (eds), Proceedings of the 32nd ACM International Conference on Multimedia. Association for Computing Machinery (ACM), New York NY USA, pp. 9387-9396, ACM International Conference on Multimedia 2024, Melbourne, Victoria, Australia, 28/10/24. https://doi.org/10.1145/3664647.3681578","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:monash.edu:publications/e6049e1a-547d-475b-9f5b-e12772ab12d2","is_oa":true,"landing_page_url":"https://research.monash.edu/en/publications/e6049e1a-547d-475b-9f5b-e12772ab12d2","pdf_url":"https://researchmgt.monash.edu/ws/files/668651513/635449284-oa.pdf","source":{"id":"https://openalex.org/S4306402625","display_name":"Monash University Research Portal (Monash University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I56590836","host_organization_name":"Monash University","host_organization_lineage":["https://openalex.org/I56590836"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Pu, M, Lim, M K & Chong, C Y 2024, Siformer : Feature-isolated Transformer for Efficient Skeleton-based Sign Language Recognition. in Y Luo, T Do & Y Yan (eds), Proceedings of the 32nd ACM International Conference on Multimedia. Association for Computing Machinery (ACM), New York NY USA, pp. 9387-9396, ACM International Conference on Multimedia 2024, Melbourne, Victoria, Australia, 28/10/24. https://doi.org/10.1145/3664647.3681578","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403791003.pdf","grobid_xml":"https://content.openalex.org/works/W4403791003.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W135171945","https://openalex.org/W1497212834","https://openalex.org/W1972034101","https://openalex.org/W1989794498","https://openalex.org/W2075156252","https://openalex.org/W2305729929","https://openalex.org/W2515700416","https://openalex.org/W2563154851","https://openalex.org/W2891726870","https://openalex.org/W2895040984","https://openalex.org/W2904518066","https://openalex.org/W2928376668","https://openalex.org/W2940457086","https://openalex.org/W2950568498","https://openalex.org/W2963393494","https://openalex.org/W2963613787","https://openalex.org/W2964208152","https://openalex.org/W2964347220","https://openalex.org/W2970454332","https://openalex.org/W3009828227","https://openalex.org/W3033737024","https://openalex.org/W3034765865","https://openalex.org/W3101163004","https://openalex.org/W3118253896","https://openalex.org/W3120017044","https://openalex.org/W3135189994","https://openalex.org/W3177318507","https://openalex.org/W4212926968","https://openalex.org/W4242177601","https://openalex.org/W4367047590","https://openalex.org/W4382460739","https://openalex.org/W4385301148"],"related_works":["https://openalex.org/W2953562271","https://openalex.org/W2334655667","https://openalex.org/W2464530384","https://openalex.org/W2105938841","https://openalex.org/W4253358700","https://openalex.org/W4379621602","https://openalex.org/W3139863978","https://openalex.org/W2014897006","https://openalex.org/W4294690766","https://openalex.org/W1756135943"],"abstract_inverted_index":{"Sign":[0],"language":[1,8],"recognition":[2,48],"(SLR)":[3],"refers":[4],"to":[5,54,57,96,125,165,192,194,207,267],"interpreting":[6],"sign":[7,33,121,199],"glosses":[9,122],"from":[10,180],"given":[11],"videos":[12],"automatically.":[13],"This":[14,172],"research":[15],"area":[16],"presents":[17],"a":[18,145,162,225,238,244,257],"complex":[19],"challenge":[20],"in":[21,32,60,101,129],"computer":[22],"vision":[23],"because":[24],"of":[25,79,139,157,187,198,218,241,247,260],"the":[26,77,137,155,175,185,188,216,250],"rapid":[27],"and":[28,41,62,107,178,211,232,264],"intricate":[29,109],"movements":[30],"inherent":[31],"languages,":[34],"which":[35],"encompass":[36],"hand":[37,81,140,147],"gestures,":[38],"body":[39,113],"postures,":[40],"even":[42],"facial":[43],"expressions.":[44],"Recently,":[45],"skeleton-based":[46,67],"action":[47],"has":[49],"attracted":[50],"increasing":[51],"attention":[52],"due":[53],"its":[55],"ability":[56],"handle":[58],"variations":[59],"subjects":[61],"backgrounds":[63],"independently.":[64],"However,":[65],"current":[66],"SLR":[68,87,189],"methods":[69,118],"exhibit":[70],"three":[71],"limitations:":[72],"1)":[73],"they":[74,94],"often":[75],"neglect":[76],"importance":[78],"realistic":[80],"poses,":[82],"where":[83],"most":[84],"studies":[85],"train":[86],"models":[88],"on":[89,167,230],"non-realistic":[90],"skeletal":[91,133,141],"representations;":[92],"2)":[93],"tend":[95],"assume":[97],"complete":[98],"data":[99],"availability":[100],"both":[102],"training":[103],"or":[104],"inference":[105,205],"phases,":[106],"capture":[108],"relationships":[110],"among":[111],"different":[112],"parts":[114],"collectively;":[115],"3)":[116],"these":[117],"treat":[119],"all":[120],"uniformly,":[123],"failing":[124],"account":[126],"for":[127,151],"differences":[128],"complexity":[130,196],"levels":[131,197],"regarding":[132],"representations.":[134],"To":[135],"enhance":[136],"realism":[138],"representations,":[142],"we":[143,160,201,236,255],"present":[144],"kinematic":[146],"pose":[148],"rectification":[149],"method":[150,173],"enforcing":[152],"constraints.":[153],"Mitigating":[154],"impact":[156],"missing":[158],"data,":[159],"propose":[161],"feature-isolated":[163],"mechanism":[164],"focus":[166],"capturing":[168],"local":[169],"spatial-temporal":[170],"context.":[171],"captures":[174],"context":[176],"concurrently":[177],"independently":[179],"individual":[181],"features,":[182],"thus":[183],"enhancing":[184],"robustness":[186],"model.":[190],"Additionally,":[191],"adapt":[193],"varying":[195],"glosses,":[200],"develop":[202],"an":[203],"input-adaptive":[204],"approach":[206],"optimise":[208],"computational":[209],"efficiency":[210],"accuracy.":[212],"Experimental":[213],"results":[214],"demonstrate":[215],"effectiveness":[217],"our":[219],"approach,":[220],"as":[221],"evidenced":[222],"by":[223],"achieving":[224],"new":[226],"state-of-the-art":[227],"(SOTA)":[228],"performance":[229],"WLASL100":[231],"LSA64.":[233],"For":[234,253],"WLASL100,":[235],"achieve":[237,256],"top-1":[239,258],"accuracy":[240,259],"86.50%,":[242],"marking":[243],"relative":[245],"improvement":[246],"2.39%":[248],"over":[249],"previous":[251],"SOTA.":[252],"LSA64,":[254],"99.84%.":[261],"The":[262],"artefacts":[263],"code":[265],"related":[266],"this":[268],"study":[269],"are":[270],"made":[271],"publicly":[272],"online":[273],"(https://github.com/mpuu00001/Siformer.git).":[274]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}