{"id":"https://openalex.org/W7204158374","doi":"https://doi.org/10.48550/arxiv.2608.22760","title":"ByteAction: Byte-space Action Recognition Foundation Model","display_name":"ByteAction: Byte-space Action Recognition Foundation Model","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204158374","doi":"https://doi.org/10.48550/arxiv.2608.22760"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.22760","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22760","pdf_url":"https://arxiv.org/pdf/2608.22760","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.22760","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147382793","display_name":"Fangcheng Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Fangcheng","raw_affiliation_strings":["School of Electronic Information and Communications , Huazhong University of Science and Technology , Wuhan , 430074 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications , Huazhong University of Science and Technology , Wuhan , 430074 , China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147979196","display_name":"Zhen Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu, Zhen","raw_affiliation_strings":["School of Electronic Information and Communications , Huazhong University of Science and Technology , Wuhan , 430074 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications , Huazhong University of Science and Technology , Wuhan , 430074 , China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148130606","display_name":"Kejun Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu, Kejun","raw_affiliation_strings":["School of Electronic Information and Communications , Huazhong University of Science and Technology , Wuhan , 430074 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications , Huazhong University of Science and Technology , Wuhan , 430074 , China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100336301","display_name":"Qiong Liu","orcid":"https://orcid.org/0000-0002-2407-806X","observed_orcids":["https://orcid.org/0000-0002-2407-806X","https://orcid.org/0009-0005-7612-555X"]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Qiong","raw_affiliation_strings":["School of Electronic Information and Communications , Huazhong University of Science and Technology , Wuhan , 430074 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications , Huazhong University of Science and Technology , Wuhan , 430074 , China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132792812","display_name":"You Yang","orcid":"https://orcid.org/0000-0002-5695-1046","observed_orcids":["https://orcid.org/0000-0002-5695-1046"]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, You","raw_affiliation_strings":["School of Electronic Information and Communications , Huazhong University of Science and Technology , Wuhan , 430074 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications , Huazhong University of Science and Technology , Wuhan , 430074 , China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.8687000274658203,"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":0.8687000274658203,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.04019999876618385,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.01140000019222498,"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":[],"concepts":[{"id":"https://openalex.org/C136695289","wikidata":"https://www.wikidata.org/wiki/Q415568","display_name":"Bitstream","level":3,"score":0.890500009059906},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7756999731063843},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.6360999941825867},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5540000200271606},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5343000292778015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5138999819755554},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4345000088214874},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34369999170303345},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.32120001316070557},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2948000133037567},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C148730421","wikidata":"https://www.wikidata.org/wiki/Q141090","display_name":"Encryption","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.263700008392334}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.22760","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22760","pdf_url":"https://arxiv.org/pdf/2608.22760","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.22760","doi":"https://doi.org/10.48550/arxiv.2608.22760","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.22760","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.22760","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22760","pdf_url":"https://arxiv.org/pdf/2608.22760","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4765690980","display_name":null,"funder_award_id":"62501246","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204158374.pdf","grobid_xml":"https://content.openalex.org/works/W7204158374.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2069867586","https://openalex.org/W3206354200","https://openalex.org/W4379255802","https://openalex.org/W4391244998","https://openalex.org/W4401058225","https://openalex.org/W4407806935","https://openalex.org/W7203672434"],"related_works":["https://openalex.org/W7223090838","https://openalex.org/W7203672434","https://openalex.org/W3121352235","https://openalex.org/W4402980278","https://openalex.org/W4394596448","https://openalex.org/W4206095319","https://openalex.org/W4415540152","https://openalex.org/W4403992130","https://openalex.org/W7172102318","https://openalex.org/W7214984192"],"abstract_inverted_index":{"Byte-space":[0],"Action":[1,172],"Recognition":[2],"(BAR)":[3],"aims":[4],"to":[5,38,126,130,148],"recognize":[6],"human":[7],"actions":[8],"directly":[9],"from":[10,165],"compressed":[11],"image":[12,63,163],"bitstreams":[13],"without":[14],"any":[15],"pixel":[16],"decoding.":[17],"By":[18],"operating":[19],"entirely":[20],"in":[21],"byte":[22,116,120,134],"space,":[23],"BAR":[24,53],"is":[25,97],"inherently":[26],"independent":[27],"of":[28],"file":[29],"integrity":[30],"and":[31,41,75,88,102,122,168],"pixel-level":[32],"reconstruction,":[33],"making":[34],"it":[35],"naturally":[36],"applicable":[37],"privacy-sensitive":[39],"scenarios":[40,182],"robust":[42,132],"against":[43],"bitstream":[44,78,164,187],"corruption.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49,107],"propose":[50,108,138],"ByteAction,":[51],"a":[52,67,91,139],"foundation":[54],"model":[55,96,129,147],"that":[56,144,174],"achieves":[57,176],"accurate":[58],"action":[59],"recognition":[60,70],"on":[61,161],"corrupted":[62,77],"bitstreams.":[64],"ByteAction":[65,175],"follows":[66],"dual-view":[68],"byte-level":[69],"framework.":[71],"It":[72],"constructs":[73],"weakly":[74],"strongly":[76],"views,":[79],"which":[80,113],"are":[81],"augmented":[82],"by":[83],"Bitstream":[84,109],"Pattern":[85,110],"Augmentation":[86,111],"(BPA)":[87],"encoded":[89],"with":[90,99],"shared":[92],"ByteFormer":[93],"backbone.":[94],"The":[95],"optimized":[98],"both":[100],"classification":[101],"corruption":[103,154,178],"consistency":[104],"objectives.":[105],"Specifically,":[106],"(BPA),":[112],"reshapes":[114],"one-dimensional":[115],"sequences":[117],"into":[118],"two-dimensional":[119],"matrix":[121],"applies":[123],"region-level":[124],"erasure":[125],"encourage":[127],"the":[128,146,162],"learn":[131],"cross-region":[133],"dependencies.":[135],"We":[136],"further":[137],"Corruption":[140],"Consistency":[141],"Training":[142],"strategy":[143],"constrains":[145],"maintain":[149],"stable":[150],"predictions":[151],"across":[152,180],"different":[153],"severities":[155],"through":[156],"bidirectional":[157],"KL":[158],"divergence.":[159],"Experiments":[160],"Stanford40,":[166],"PPMI,":[167],"PASCAL":[169],"VOC":[170],"2012":[171],"demonstrate":[173],"state-of-the-art":[177],"robustness":[179],"all":[181],"while":[183],"maintaining":[184],"competitive":[185],"intact":[186],"performance.":[188]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-26T00:00:00"}
