{"id":"https://openalex.org/W7225658074","doi":"https://doi.org/10.5281/zenodo.24088418","title":"SignFlow: Real-Time Multi-Modal Sign Language Recognition via 12-Stream Hybrid Architecture on the Full-Vocabulary ASL Citizen Benchmark","display_name":"SignFlow: Real-Time Multi-Modal Sign Language Recognition via 12-Stream Hybrid Architecture on the Full-Vocabulary ASL Citizen Benchmark","publication_year":2026,"publication_date":"2026-11-09","ids":{"openalex":"https://openalex.org/W7225658074","doi":"https://doi.org/10.5281/zenodo.24088418"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24088418","doi":"https://doi.org/10.5281/zenodo.24088418","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24088418","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24088418","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161318187","display_name":"Nithin G","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"G, Nithin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5161318187"],"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":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/T10812","display_name":"Human Pose and Action Recognition","score":9.999999747378752e-05,"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/T11285","display_name":"Hearing Impairment and Communication","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/american-sign-language","display_name":"American Sign Language","score":0.8410000205039978},{"id":"https://openalex.org/keywords/sign-language-recognition","display_name":"sign language recognition","score":0.8299999833106995},{"id":"https://openalex.org/keywords/multimodal-fusion","display_name":"multimodal fusion","score":0.6240000128746033},{"id":"https://openalex.org/keywords/on-device-inference","display_name":"on-device inference","score":0.6790000200271606},{"id":"https://openalex.org/keywords/videomae","display_name":"VideoMAE","score":0.9679999947547913},{"id":"https://openalex.org/keywords/signer-independent-recognition","display_name":"signer-independent recognition","score":0.46399998664855957},{"id":"https://openalex.org/keywords/hybrid-architecture","display_name":"hybrid architecture","score":0.42399999499320984},{"id":"https://openalex.org/keywords/real-time-recognition","display_name":"real-time recognition","score":0.4779999852180481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7714999914169312},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.6086000204086304},{"id":"https://openalex.org/C2776737515","wikidata":"https://www.wikidata.org/wiki/Q14759","display_name":"American Sign Language","level":3,"score":0.5830000042915344},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5067999958992004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5038999915122986},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.48809999227523804},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43959999084472656},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.42570000886917114},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4018000066280365},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3853999972343445},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3515999913215637},{"id":"https://openalex.org/C2780008327","wikidata":"https://www.wikidata.org/wiki/Q3962","display_name":"Laptop","level":2,"score":0.34769999980926514},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26589998602867126},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.2630999982357025}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24088418","doi":"https://doi.org/10.5281/zenodo.24088418","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24088418","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.24088419","doi":"https://doi.org/10.5281/zenodo.24088419","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24088419","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.24088418","doi":"https://doi.org/10.5281/zenodo.24088418","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24088418","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416865598","https://openalex.org/W7203541744","https://openalex.org/W7214721103","https://openalex.org/W7116060075","https://openalex.org/W7223099906","https://openalex.org/W7163345842","https://openalex.org/W7127119875","https://openalex.org/W7131131947","https://openalex.org/W4415682825","https://openalex.org/W7162217209"],"abstract_inverted_index":{"Isolated":[0],"sign":[1,31],"language":[2,32],"recognition":[3,33],"(ISLR)":[4],"across":[5,49],"comprehensive":[6],"natural":[7],"vocabularies":[8],"is":[9],"constrained":[10],"by":[11],"signer":[12],"heterogeneity,":[13],"subtle":[14],"phonemic":[15],"contrasts,":[16],"and":[17,82,91,97,130],"high":[18],"computational":[19],"latency":[20,167],"on":[21,36,104,116,161,173],"edge":[22],"hardware.":[23],"We":[24],"present":[25],"SignFlow,":[26],"an":[27,55,165,174],"end-":[28],"to-end,":[29],"on-device":[30],"system":[34],"evaluated":[35,48],"the":[37,105,117],"complete":[38],"official":[39,106],"ASL":[40],"Citizen":[41],"benchmark":[42],"(2,731":[43],"glosses,":[44],"32,940":[45],"test":[46,120],"clips,":[47],"strictly":[50,103],"held-out":[51],"signers).":[52],"SignFlow":[53,122],"introduces":[54],"asymmetrical":[56],"12-":[57],"stream":[58],"hybrid":[59],"architecture":[60],"integrating:":[61],"(i)":[62],"four":[63],"Landmark":[64],"Transformers":[65],"initialized":[66],"via":[67,109],"self-supervised":[68],"masked-frame":[69],"pretraining;":[70],"(ii)":[71],"three":[72],"1D-CNN":[73,136],"temporal":[74],"convolutional":[75],"experts":[76],"with":[77,164],"dilated":[78],"multi-round":[79],"receptive":[80],"fields;":[81],"(iii)":[83],"five":[84],"VideoMAE":[85],"appearance":[86],"models":[87],"capturing":[88],"full-frame":[89],"dynamics":[90],"hand-":[92],"crop":[93],"details.":[94],"Fusion":[95],"weights":[96],"class-conditional":[98],"temperature":[99],"parameters":[100],"are":[101],"fit":[102],"validation":[107],"split":[108],"L-BFGS":[110],"log-linear":[111],"cross-":[112],"entropy":[113],"optimization.":[114],"Evaluated":[115],"32,940-clip":[118],"signer-independent":[119],"split,":[121],"achieves":[123],"87.04%":[124],"Top-1":[125],"(28,670/32,940":[126],"correct),":[127],"98.27%":[128],"Top-5,":[129],"98.89%":[131],"Top-10":[132],"accuracy.":[133],"A":[134],"single":[135],"expert":[137],"(conv3)":[138],"attains":[139],"85.16%":[140],"Top-":[141],"1":[142],"solo.":[143],"Signer-clustered":[144],"bootstrap":[145],"resampling":[146],"(B=2,000)":[147],"establishes":[148],"a":[149],"95%":[150],"confidence":[151],"interval":[152],"of":[153,168],"[85.61%,":[154],"88.35%].":[155],"The":[156],"entire":[157],"pipeline":[158],"operates":[159],"locally":[160],"consumer":[162],"hardware":[163],"inference":[166],"72":[169],"ms":[170],"per":[171],"clip":[172],"NVIDIA":[175],"RTX":[176],"3070":[177],"Ti":[178],"laptop":[179],"GPU.":[180]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}