{"id":"https://openalex.org/W7225003368","doi":"https://doi.org/10.5281/zenodo.23813421","title":"HiSTAG: Hierarchical Spatio-Temporal Attention over Part Groupings for Isolated Sign Language Recognition","display_name":"HiSTAG: Hierarchical Spatio-Temporal Attention over Part Groupings for Isolated Sign Language Recognition","publication_year":2026,"publication_date":"2026-10-30","ids":{"openalex":"https://openalex.org/W7225003368","doi":"https://doi.org/10.5281/zenodo.23813421"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23813421","doi":"https://doi.org/10.5281/zenodo.23813421","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23813421","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","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23813421","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160248442","display_name":"Ahan Sparsh","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sparsh, Ahan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5160248442"],"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":0.9731000065803528,"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":0.9731000065803528,"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":0.026200000196695328,"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/isolated-sign-language-recognition","display_name":"isolated sign language recognition","score":0.9919999837875366},{"id":"https://openalex.org/keywords/skeleton-based-action-recognition","display_name":"skeleton-based action recognition","score":0.7879999876022339},{"id":"https://openalex.org/keywords/spatiotemporal-attention","display_name":"spatio-temporal attention","score":0.8130000233650208},{"id":"https://openalex.org/keywords/graph-attention-networks","display_name":"graph attention networks","score":0.671999990940094},{"id":"https://openalex.org/keywords/self-supervised-pretraining","display_name":"self-supervised pre-training","score":0.7269999980926514},{"id":"https://openalex.org/keywords/part-grouping","display_name":"part grouping","score":0.5239999890327454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8162999749183655},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6176999807357788},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.5891000032424927},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5450000166893005},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.5163000226020813},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5130000114440918},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4966000020503998},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.47269999980926514},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4657000005245209},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4361000061035156},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.41920000314712524},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.39879998564720154},{"id":"https://openalex.org/C2776737515","wikidata":"https://www.wikidata.org/wiki/Q14759","display_name":"American Sign Language","level":3,"score":0.3968000113964081},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C162372511","wikidata":"https://www.wikidata.org/wiki/Q218341","display_name":"Checksum","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3118000030517578},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C113324615","wikidata":"https://www.wikidata.org/wiki/Q472302","display_name":"Login","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C2779696439","wikidata":"https://www.wikidata.org/wiki/Q7512811","display_name":"Signature (topology)","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C46503548","wikidata":"https://www.wikidata.org/wiki/Q1145976","display_name":"Plain text","level":3,"score":0.2732999920845032},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C2779151265","wikidata":"https://www.wikidata.org/wiki/Q1156791","display_name":"Copying","level":2,"score":0.26330000162124634}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23813421","doi":"https://doi.org/10.5281/zenodo.23813421","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23813421","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.23813422","doi":"https://doi.org/10.5281/zenodo.23813422","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23813422","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.23813421","doi":"https://doi.org/10.5281/zenodo.23813421","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23813421","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/W4402856323","https://openalex.org/W4312206539","https://openalex.org/W4412738871","https://openalex.org/W4385800861","https://openalex.org/W7214804516","https://openalex.org/W6921527910","https://openalex.org/W7131782561","https://openalex.org/W4392826867","https://openalex.org/W7211925054","https://openalex.org/W4393855519"],"abstract_inverted_index":{"Isolated":[0],"sign":[1,10],"language":[2],"recognition":[3],"maps":[4],"a":[5,8,40,53,82,87,91,145,151,207],"video":[6],"of":[7,25,81,104,147,153,167,210],"single":[9,88],"to":[11,22,159],"its":[12],"label;":[13],"skeleton-based":[14],"models":[15],"reduce":[16],"input":[17],"videos":[18],"from":[19],"pixel":[20],"data":[21],"temporal":[23,92],"sequences":[24],"body":[26,50],"and":[27,78,128,187,201,214,226],"hand":[28],"keypoints.":[29],"This":[30],"work":[31],"presents":[32],"HiSTAG":[33,98],"(Hierarchical":[34],"Spatio-Temporal":[35],"Attention":[36],"over":[37],"Part":[38],"Groupings),":[39],"three-stage":[41],"skeleton":[42],"encoder":[43,122],"built":[44],"on":[45,107,126,130],"slots,":[46],"each":[47,69,75],"holding":[48],"one":[49],"part":[51],"within":[52],"short":[54],"time":[55],"window.":[56],"Windowed":[57],"graph":[58],"attention,":[59],"pretrained":[60,121],"without":[61],"labels":[62],"by":[63],"reconstructing":[64],"masked":[65],"keypoints,":[66],"first":[67],"encodes":[68],"slot;":[70],"pooling":[71,93],"attention":[72],"then":[73],"condenses":[74],"slot":[76],"separately,":[77],"the":[79,96,108,119,136,148,171,174,178,188,196,218,231],"slots":[80],"window":[83],"are":[84,223],"merged":[85],"into":[86],"token":[89],"before":[90],"cascade":[94],"relates":[95],"windows.":[97],"reaches":[99,124],"94.62%":[100],"top-1":[101],"accuracy":[102,155],"(mean":[103],"two":[105],"seeds)":[106],"2,002-gloss":[109],"signer-independent":[110],"FDMSE-ISL":[111,179,198],"benchmark":[112],"at":[113,150],"9.44":[114],"GFLOPs":[115],"per":[116],"clip.":[117],"With":[118],"same":[120],"it":[123],"98.96%":[125],"INCLUDE":[127,200],"98.75%":[129],"LSA64":[131,202],"(HWGAT":[132],"subject":[133],"split),":[134],"matching":[135],"best":[137],"published":[138],"result":[139],"there.":[140],"Post-training":[141],"low-rank":[142],"truncation":[143],"removes":[144],"quarter":[146],"parameters":[149],"cost":[152],"0.05":[154],"points.":[156],"Status:":[157],"submitted":[158],"IEEE":[160],"FG":[161],"2027,":[162],"under":[163],"review.":[164],"Version":[165],"1.0":[166],"this":[168,211,221],"record":[169],"contains":[170],"preprint":[172],"(HiSTAG_preprint.pdf),":[173],"source":[175],"code":[176,232],"(histag-code-v1.0.zip),":[177],"checkpoint":[180],"for":[181,195,217,234],"seed":[182],"0":[183],"(histag_fdmse2002_seed0.pt,":[184],"94.592%":[185],"top-1)":[186],"self-supervised":[189],"Stage-1":[190],"weights":[191],"(histag_stage1_ssl.pt).":[192],"The":[193],"checkpoints":[194],"second":[197],"seed,":[199],"will":[203],"be":[204],"added":[205],"in":[206,220,224],"later":[208],"version":[209,222],"record.":[212],"Scores":[213],"SHA-256":[215],"checksums":[216],"files":[219],"MODEL_CARD.md":[225],"SHA256SUMS.txt.":[227],"See":[228],"README.md":[229],"inside":[230],"archive":[233],"reproduction":[235],"steps.":[236]},"counts_by_year":[],"updated_date":"2026-11-02T09:45:03.842371","created_date":"2026-11-01T00:00:00"}