{"id":"https://openalex.org/W4413359679","doi":"https://doi.org/10.1109/tpami.2025.3600658","title":"Foundation Model for Skeleton-Based Human Action Understanding","display_name":"Foundation Model for Skeleton-Based Human Action Understanding","publication_year":2025,"publication_date":"2025-08-20","ids":{"openalex":"https://openalex.org/W4413359679","doi":"https://doi.org/10.1109/tpami.2025.3600658","pmid":"https://pubmed.ncbi.nlm.nih.gov/40833899"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3600658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3600658","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014269015","display_name":"Hongsong Wang","orcid":"https://orcid.org/0000-0002-9464-1778"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongsong Wang","raw_affiliation_strings":["School of Computer Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-9464-1778","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wanjiang Weng","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanjiang Weng","raw_affiliation_strings":["School of Computer Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112578806","display_name":"Junbo Wang","orcid":"https://orcid.org/0009-0006-9955-7838"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junbo Wang","raw_affiliation_strings":["School of Software, Northwestern Polytechnical University, Xi’an, China","School of Software, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0006-9955-7838","affiliations":[{"raw_affiliation_string":"School of Software, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Software, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329780","display_name":"Fang Zhao","orcid":"https://orcid.org/0000-0002-6772-8042"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Zhao","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, School of Intelligence Science and Technology, Nanjing University, Nanjing, China","State Key Laboratory for Novel Software Technology and School of Intelligence Science and Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-6772-8042","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, School of Intelligence Science and Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology and School of Intelligence Science and Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084688255","display_name":"Guo-Sen Xie","orcid":"https://orcid.org/0000-0002-5487-9845"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo-Sen Xie","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-5487-9845","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xin Geng","orcid":"https://orcid.org/0000-0001-7729-0622"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Geng","raw_affiliation_strings":["School of Computer Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-7729-0622","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115602506","display_name":"Liang Wang","orcid":"https://orcid.org/0000-0001-5224-8647"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Wang","raw_affiliation_strings":["New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), China"],"raw_orcid":"https://orcid.org/0000-0001-5224-8647","affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9349,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78070669,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"48","issue":"1","first_page":"47","last_page":"61"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.7052000164985657,"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":0.7052000164985657,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.6518999934196472,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/skeleton","display_name":"Skeleton (computer programming)","score":0.5858420133590698},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5748187899589539},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5564522743225098},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.532607913017273},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.48774105310440063},{"id":"https://openalex.org/keywords/human-skeleton","display_name":"Human skeleton","score":0.41590046882629395}],"concepts":[{"id":"https://openalex.org/C18969341","wikidata":"https://www.wikidata.org/wiki/Q1169129","display_name":"Skeleton (computer programming)","level":2,"score":0.5858420133590698},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5748187899589539},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5564522743225098},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.532607913017273},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.48774105310440063},{"id":"https://openalex.org/C2777846634","wikidata":"https://www.wikidata.org/wiki/Q9621","display_name":"Human skeleton","level":2,"score":0.41590046882629395},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006802","descriptor_name":"Human Activities","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D006802","descriptor_name":"Human Activities","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D012863","descriptor_name":"Skeleton","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012863","descriptor_name":"Skeleton","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3600658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3600658","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40833899","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40833899","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":77,"referenced_works":["https://openalex.org/W1950788856","https://openalex.org/W2313903725","https://openalex.org/W2510185399","https://openalex.org/W2605300166","https://openalex.org/W2606294640","https://openalex.org/W2739251211","https://openalex.org/W2788787949","https://openalex.org/W2798795235","https://openalex.org/W2803158089","https://openalex.org/W2885940446","https://openalex.org/W2944006115","https://openalex.org/W2948058585","https://openalex.org/W2960406243","https://openalex.org/W2963076818","https://openalex.org/W2963853051","https://openalex.org/W2964134613","https://openalex.org/W3033793613","https://openalex.org/W3035050855","https://openalex.org/W3035225512","https://openalex.org/W3092424783","https://openalex.org/W3109306201","https://openalex.org/W3113067059","https://openalex.org/W3157403981","https://openalex.org/W3169413442","https://openalex.org/W3174053790","https://openalex.org/W3185273257","https://openalex.org/W3203227473","https://openalex.org/W3203711169","https://openalex.org/W3205106480","https://openalex.org/W3216270236","https://openalex.org/W4200634815","https://openalex.org/W4226027695","https://openalex.org/W4226289673","https://openalex.org/W4312387119","https://openalex.org/W4312675926","https://openalex.org/W4312841534","https://openalex.org/W4313185874","https://openalex.org/W4313186260","https://openalex.org/W4366503267","https://openalex.org/W4379984420","https://openalex.org/W4380303514","https://openalex.org/W4382240124","https://openalex.org/W4382240189","https://openalex.org/W4382459184","https://openalex.org/W4385768200","https://openalex.org/W4386057769","https://openalex.org/W4386065445","https://openalex.org/W4386076095","https://openalex.org/W4386076499","https://openalex.org/W4386108371","https://openalex.org/W4386215080","https://openalex.org/W4387789756","https://openalex.org/W4387968040","https://openalex.org/W4387968449","https://openalex.org/W4389459415","https://openalex.org/W4390871931","https://openalex.org/W4390872019","https://openalex.org/W4390872069","https://openalex.org/W4390873156","https://openalex.org/W4390874423","https://openalex.org/W4390906058","https://openalex.org/W4391693788","https://openalex.org/W4393148248","https://openalex.org/W4399039553","https://openalex.org/W4399404947","https://openalex.org/W4399800460","https://openalex.org/W4401416983","https://openalex.org/W4402194884","https://openalex.org/W4402660150","https://openalex.org/W4402727464","https://openalex.org/W4403770628","https://openalex.org/W4403842392","https://openalex.org/W4403842411","https://openalex.org/W4403887661","https://openalex.org/W4406208390","https://openalex.org/W4409366445","https://openalex.org/W7084098655"],"related_works":["https://openalex.org/W2953562271","https://openalex.org/W1979723775","https://openalex.org/W2126881935","https://openalex.org/W4312993112","https://openalex.org/W3209135759","https://openalex.org/W2347221702","https://openalex.org/W2523395320","https://openalex.org/W41889997","https://openalex.org/W2784535632","https://openalex.org/W2348425426"],"abstract_inverted_index":{"Human":[0],"action":[1,27,51,69,92,196,228],"understanding":[2,28,52,70,197,229],"serves":[3,84],"as":[4,16,85],"a":[5,17,65,75,86,97],"foundational":[6,87],"pillar":[7],"in":[8,32,226],"the":[9,43,162,169,175,179,211,222],"field":[10],"of":[11,68,96,164,171,181,224],"intelligent":[12],"motion":[13],"perception.Skeletons":[14],"serve":[15],"modality-":[18],"and":[19,25,36,45,107,123,137,144,154,167,204,230],"device-agnostic":[20],"representation":[21],"for":[22,89],"human":[23,91],"modeling,":[24],"skeleton-based":[26,90,195,227],"has":[29],"potential":[30],"applications":[31],"humanoid":[33],"robot":[34],"control":[35],"interaction.":[37],"However,":[38],"existing":[39],"works":[40],"often":[41],"lack":[42],"scalability":[44],"generalization":[46],"required":[47],"to":[48,64,119,140,234],"handle":[49],"diverse":[50],"tasks.":[53,71,237],"There":[54],"is":[55],"no":[56],"skeleton":[57],"foundation":[58],"model":[59,88],"that":[60,217],"can":[61],"be":[62],"adapted":[63],"wide":[66],"range":[67],"This":[72],"paper":[73],"presents":[74],"Unified":[76],"Skeleton-based":[77],"Dense":[78,99],"Representation":[79],"Learning":[80],"(USDRL)":[81],"framework,":[82],"which":[83],"understanding.":[93],"USDRL":[94],"consists":[95],"Transformer-based":[98],"Spatio-Temporal":[100],"Encoder":[101],"(DSTE),":[102],"Multi-Grained":[103],"Feature":[104],"Decorrelation":[105],"(MG-FD),":[106],"Multi-Perspective":[108],"Consistency":[109],"Training":[110],"(MPCT).":[111],"The":[112,127,148,159],"DSTE":[113],"module":[114,129,150],"adopts":[115],"two":[116],"parallel":[117],"streams":[118],"learn":[120],"temporal":[121],"dynamic":[122],"spatial":[124],"structure":[125],"features.":[126,184],"MG-FD":[128],"collaboratively":[130],"performs":[131],"feature":[132],"decorrelation":[133],"across":[134,192,193],"temporal,":[135],"spatial,":[136],"instance":[138],"domains":[139],"reduce":[141],"dimensional":[142],"redundancy":[143],"enhance":[145],"information":[146],"extraction.":[147],"MPCT":[149],"employs":[151],"both":[152],"multi-view":[153],"multi-modal":[155],"self-supervised":[156],"consistency":[157],"training.":[158],"former":[160],"enhances":[161],"learning":[163,180],"high-level":[165],"semantics":[166],"mitigates":[168],"impact":[170],"low-level":[172],"discrepancies,":[173],"while":[174],"latter":[176],"effectively":[177],"facilitates":[178],"informative":[182],"multimodal":[183],"We":[185,215],"perform":[186],"extensive":[187],"experiments":[188],"on":[189],"25":[190],"benchmarks":[191],"9":[194],"tasks,":[198],"covering":[199],"coarse":[200],"prediction,":[201,203],"dense":[202,235],"transferred":[205],"prediction.":[206],"Our":[207],"approach":[208],"significantly":[209],"outperforms":[210],"current":[212],"state-of-the-art":[213],"methods.":[214],"hope":[216],"this":[218],"work":[219],"would":[220],"broaden":[221],"scope":[223],"research":[225],"encourage":[231],"more":[232],"attention":[233],"prediction":[236]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}