{"id":"https://openalex.org/W7147469741","doi":"https://doi.org/10.48550/arxiv.2603.29057","title":"LA-Sign: Looped Transformers with Geometry-aware Alignment for Skeleton-based Sign Language Recognition","display_name":"LA-Sign: Looped Transformers with Geometry-aware Alignment for Skeleton-based Sign Language Recognition","publication_year":2026,"publication_date":"2026-03-30","ids":{"openalex":"https://openalex.org/W7147469741","doi":"https://doi.org/10.48550/arxiv.2603.29057"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.29057","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29057","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.29057","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132543712","display_name":"Muxin Pu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pu, Muxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046137969","display_name":"Mei Kuan Lim","orcid":"https://orcid.org/0000-0001-8834-9933"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lim, Mei Kuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024635381","display_name":"Chun Yong Chong","orcid":"https://orcid.org/0000-0003-1164-0049"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chong, Chun Yong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132583603","display_name":"Chen Change Loy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Loy, Chen Change","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9868999719619751,"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":0.9868999719619751,"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":0.004399999976158142,"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":0.0012000000569969416,"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/sign-language","display_name":"Sign language","score":0.7017999887466431},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6172000169754028},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4426000118255615},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.37279999256134033},{"id":"https://openalex.org/keywords/sign","display_name":"Sign (mathematics)","score":0.35510000586509705},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.3411000072956085},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.33970001339912415},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32739999890327454}],"concepts":[{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.7017999887466431},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6759999990463257},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6172000169754028},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5710999965667725},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4426000118255615},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.37279999256134033},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3411000072956085},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.33970001339912415},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33160001039505005},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.32420000433921814},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3197000026702881},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3167000114917755},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2849000096321106},{"id":"https://openalex.org/C33347731","wikidata":"https://www.wikidata.org/wiki/Q285210","display_name":"Stacking","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.29057","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29057","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.29057","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29057","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6446904540061951,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Skeleton-based":[0],"isolated":[1],"sign":[2,159],"language":[3,160],"recognition":[4],"(ISLR)":[5],"demands":[6],"fine-grained":[7],"understanding":[8,76],"of":[9,58,150],"articulated":[10],"motion":[11,75],"across":[12],"multiple":[13,113],"spatial":[14],"scales,":[15],"from":[16,66],"subtle":[17],"finger":[18],"movements":[19],"to":[20,72],"global":[21],"body":[22],"dynamics.":[23],"Existing":[24],"approaches":[25],"typically":[26],"rely":[27],"on":[28,131],"deep":[29],"feed-forward":[30],"architectures,":[31],"which":[32],"increase":[33],"model":[34],"capacity":[35],"but":[36],"lack":[37],"mechanisms":[38],"for":[39,55,158],"recurrent":[40,151],"refinement":[41,84,153],"and":[42,95,112,133,154],"structured":[43],"representation.":[44],"We":[45,107],"propose":[46],"LA-Sign,":[47],"a":[48,88],"looped":[49],"transformer":[50],"framework":[51],"with":[52,121],"geometry-aware":[53,89,155],"alignment":[54,124],"ISLR.":[56],"Instead":[57],"stacking":[59],"deeper":[60],"layers,":[61,146],"LA-Sign":[62,138],"derives":[63],"its":[64],"depth":[65],"recurrence,":[67],"repeatedly":[68],"revisiting":[69],"latent":[70,152],"representations":[71],"progressively":[73],"refine":[74],"under":[77],"shared":[78],"parameters.":[79],"To":[80],"further":[81],"regularise":[82],"this":[83],"process,":[85],"we":[86],"present":[87],"contrastive":[90],"objective":[91],"that":[92,117,137],"projects":[93],"skeletal":[94],"textual":[96],"features":[97],"into":[98],"an":[99],"adaptive":[100,122],"hyperbolic":[101],"space,":[102],"encouraging":[103],"multi-scale":[104],"semantic":[105],"organisation.":[106],"study":[108],"three":[109],"looping":[110,119],"designs":[111],"geometric":[114],"manifolds,":[115],"demonstrating":[116],"encoder-decoder":[118],"combined":[120],"Poincare":[123],"yields":[125],"the":[126,148],"strongest":[127],"performance.":[128],"Extensive":[129],"experiments":[130],"WLASL":[132],"MSASL":[134],"benchmarks":[135],"show":[136],"achieves":[139],"state-of-the-art":[140],"results":[141],"while":[142],"using":[143],"fewer":[144],"unique":[145],"highlighting":[147],"effectiveness":[149],"representation":[156],"learning":[157],"recognition.":[161]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-02T00:00:00"}