{"id":"https://openalex.org/W7154692952","doi":"https://doi.org/10.48550/arxiv.2604.14933","title":"Generative Data Augmentation for Skeleton Action Recognition","display_name":"Generative Data Augmentation for Skeleton Action Recognition","publication_year":2026,"publication_date":"2026-04-16","ids":{"openalex":"https://openalex.org/W7154692952","doi":"https://doi.org/10.48550/arxiv.2604.14933"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.14933","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.14933","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.14933","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133859912","display_name":"Xu Dong","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dong, Xu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113307034","display_name":"W Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Wanqing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133916522","display_name":"Anthony Adeyemi-Ejeye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adeyemi-Ejeye, Anthony","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133891935","display_name":"Andrew Gilbert","orcid":"https://orcid.org/0000-0001-7560-5790"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gilbert, Andrew","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5133859912"],"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/T10812","display_name":"Human Pose and Action Recognition","score":0.855400025844574,"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"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.855400025844574,"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/T12290","display_name":"Human Motion and Animation","score":0.08669999986886978,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.007799999788403511,"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/skeleton","display_name":"Skeleton (computer programming)","score":0.6567000150680542},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6481000185012817},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5636000037193298},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5159000158309937},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.5094000101089478},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.5045999884605408},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4853000044822693},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.46059998869895935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7670000195503235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6718000173568726},{"id":"https://openalex.org/C18969341","wikidata":"https://www.wikidata.org/wiki/Q1169129","display_name":"Skeleton (computer programming)","level":2,"score":0.6567000150680542},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6481000185012817},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5636000037193298},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5159000158309937},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.5094000101089478},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.5045999884605408},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4853000044822693},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.46059998869895935},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4350000023841858},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.41670000553131104},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4147000014781952},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.41179999709129333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3953999876976013},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3343999981880188},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.2687999904155731},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C2777846634","wikidata":"https://www.wikidata.org/wiki/Q9621","display_name":"Human skeleton","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.14933","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.14933","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.14933","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.14933","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":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.7262791395187378}],"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],"human":[1,10],"action":[2,44,59,138],"recognition":[3,83,139],"is":[4,24],"a":[5,35,97,103,108],"powerful":[6],"approach":[7,130],"for":[8,39],"understanding":[9],"behaviour":[11],"from":[12],"pose":[13],"data,":[14],"but":[15],"collecting":[16],"large-scale,":[17],"diverse,":[18],"and":[19,27,66,80,107,114,121,147],"well-annotated":[20],"3D":[21],"skeleton":[22,43,53,78],"datasets":[23],"both":[25,145],"expensive":[26],"labor-intensive.":[28],"To":[29],"address":[30],"this":[31],"challenge,":[32],"we":[33,95],"propose":[34],"conditional":[36],"generative":[37,104],"pipeline":[38],"data":[40],"augmentation":[41],"in":[42,85,91,144],"recognition.":[45],"Our":[46],"method":[47],"learns":[48],"the":[49,56,62,122,133],"distribution":[50],"of":[51,58,64,135],"real":[52],"sequences":[54,79],"under":[55],"constraint":[57],"labels,":[60],"enabling":[61],"synthesis":[63],"diverse":[65],"high-fidelity":[67],"data.":[68],"Even":[69],"with":[70,102],"limited":[71],"training":[72],"samples,":[73],"it":[74],"can":[75,153],"effectively":[76],"generate":[77],"achieve":[81],"competitive":[82],"performance":[84],"low-data":[86],"scenarios,":[87],"demonstrating":[88],"strong":[89],"generalisation":[90],"downstream":[92],"tasks.":[93],"Specifically,":[94],"introduce":[96],"Transformer-based":[98],"encoder-decoder":[99],"architecture,":[100],"combined":[101],"refinement":[105],"module":[106],"dropout":[109],"mechanism,":[110],"to":[111],"balance":[112],"fidelity":[113],"diversity":[115],"during":[116],"sampling.":[117],"Experiments":[118],"on":[119],"HumanAct12":[120],"refined":[123],"NTU-RGBD":[124],"(NTU-VIBE)":[125],"dataset":[126],"show":[127],"that":[128],"our":[129],"consistently":[131],"improves":[132],"accuracy":[134],"multiple":[136],"skeleton-based":[137],"models,":[140],"validating":[141],"its":[142],"effectiveness":[143],"few-shot":[146],"full-data":[148],"settings.":[149],"The":[150],"source":[151],"code":[152],"be":[154],"found":[155],"at":[156],"here.":[157]},"counts_by_year":[],"updated_date":"2026-04-18T06:05:20.339008","created_date":"2026-04-18T00:00:00"}