{"id":"https://openalex.org/W4408352276","doi":"https://doi.org/10.1109/icassp49660.2025.10890079","title":"PASTD: Progressive Augmentation and Spatiotemporal Decoupling Contrastive Learning for Skeleton-Based Action Recognition","display_name":"PASTD: Progressive Augmentation and Spatiotemporal Decoupling Contrastive Learning for Skeleton-Based Action Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352276","doi":"https://doi.org/10.1109/icassp49660.2025.10890079"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890079","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5060769276","display_name":"Qian Huang","orcid":"https://orcid.org/0000-0002-2862-8065"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qian Huang","raw_affiliation_strings":["Hohai University,College of Computer Science and Software Engineering,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Hohai University,College of Computer Science and Software Engineering,Nanjing,China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091894519","display_name":"Weiwen Qian","orcid":"https://orcid.org/0000-0003-2523-8173"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiwen Qian","raw_affiliation_strings":["Hohai University,College of Computer Science and Software Engineering,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Hohai University,College of Computer Science and Software Engineering,Nanjing,China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100429517","display_name":"Chang Li","orcid":"https://orcid.org/0000-0002-1705-0149"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Li","raw_affiliation_strings":["Hohai University,College of Computer Science and Software Engineering,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Hohai University,College of Computer Science and Software Engineering,Nanjing,China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110866322","display_name":"Gongquan Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I12615008","display_name":"Beijing Normal University - Hong Kong Baptist University United International College","ror":"https://ror.org/04snvc712","country_code":"CN","type":"education","lineage":["https://openalex.org/I12615008"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gongyou Xu","raw_affiliation_strings":["United International College, BNU-HKBU,Faculty of Science and Technology,Zhuhai,China"],"affiliations":[{"raw_affiliation_string":"United International College, BNU-HKBU,Faculty of Science and Technology,Zhuhai,China","institution_ids":["https://openalex.org/I12615008"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045760779","display_name":"Zhaoxi Chen","orcid":"https://orcid.org/0000-0001-5290-5977"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongqi Chen","raw_affiliation_strings":["Hohai University,College of Computer Science and Software Engineering,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Hohai University,College of Computer Science and Software Engineering,Nanjing,China","institution_ids":["https://openalex.org/I163340411"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5060769276"],"corresponding_institution_ids":["https://openalex.org/I163340411"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04022989,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9973000288009644,"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":0.9973000288009644,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9700000286102295,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7168713808059692},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.6752831935882568},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.5818848609924316},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5498325228691101},{"id":"https://openalex.org/keywords/skeleton","display_name":"Skeleton (computer programming)","score":0.5012991428375244},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36005714535713196},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34142935276031494},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3341193199157715},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1507367491722107},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.055681049823760986}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7168713808059692},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.6752831935882568},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.5818848609924316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5498325228691101},{"id":"https://openalex.org/C18969341","wikidata":"https://www.wikidata.org/wiki/Q1169129","display_name":"Skeleton (computer programming)","level":2,"score":0.5012991428375244},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36005714535713196},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34142935276031494},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3341193199157715},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1507367491722107},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.055681049823760986},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890079","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1744759976","https://openalex.org/W1950788856","https://openalex.org/W2604321021","https://openalex.org/W2787919227","https://openalex.org/W2868755588","https://openalex.org/W2944006115","https://openalex.org/W2948058585","https://openalex.org/W2963076818","https://openalex.org/W2964134613","https://openalex.org/W3033793613","https://openalex.org/W3034548564","https://openalex.org/W3035524453","https://openalex.org/W3092424783","https://openalex.org/W3169413442","https://openalex.org/W3194512065","https://openalex.org/W3203227473","https://openalex.org/W3203634062","https://openalex.org/W3205106480","https://openalex.org/W3212618454","https://openalex.org/W3216909972","https://openalex.org/W4200634815","https://openalex.org/W4286983754","https://openalex.org/W4294068600","https://openalex.org/W4313185874","https://openalex.org/W4382240124","https://openalex.org/W4382459184","https://openalex.org/W4385768200","https://openalex.org/W4386065445","https://openalex.org/W4386159986","https://openalex.org/W4388819754","https://openalex.org/W4389459415","https://openalex.org/W6720006811","https://openalex.org/W6774314701","https://openalex.org/W6840857800","https://openalex.org/W6850445340"],"related_works":["https://openalex.org/W4313561376","https://openalex.org/W3103825105","https://openalex.org/W3027880158","https://openalex.org/W3207533102","https://openalex.org/W1617565119","https://openalex.org/W160381218","https://openalex.org/W2512958550","https://openalex.org/W2004102934","https://openalex.org/W4399611050","https://openalex.org/W3170431411"],"abstract_inverted_index":{"Contrastive":[0],"learning":[1,71,128],"has":[2],"achieved":[3],"significant":[4],"progress":[5],"in":[6],"the":[7,31,34,81,112,139,149],"field":[8],"of":[9,33,151],"self-supervised":[10],"skeleton-based":[11],"action":[12],"recognition.":[13],"However,":[14],"existing":[15],"methods":[16,38,158],"often":[17],"apply":[18],"strong":[19],"augmentations":[20],"directly":[21],"to":[22,48,79,99,110,130],"skeleton":[23],"data,":[24],"which":[25,85],"can":[26],"distort":[27],"or":[28],"even":[29],"lose":[30],"semantic":[32],"skeletons.":[35],"Additionally,":[36],"most":[37],"focus":[39],"on":[40,138],"unified":[41],"feature":[42],"extraction":[43],"through":[44,92],"spatiotemporal":[45,49,107],"modeling,":[46],"leading":[47],"entanglement":[50],"that":[51],"hinders":[52],"model\u2019s":[53,82],"interpretability":[54],"and":[55,67,95,115,145],"degrades":[56],"performance.":[57],"To":[58],"address":[59],"these":[60,152],"issues,":[61],"we":[62,75,105],"propose":[63,76,106],"a":[64,119],"Progressive":[65],"Augmentation":[66],"SpatioTemporal":[68],"Decoupling":[69],"contrastive":[70],"model":[72],"(PASTD).":[73],"Specifically,":[74],"progressive":[77],"augmentation":[78],"enhance":[80],"generalization":[83],"capability,":[84],"generates":[86],"multiple":[87,93],"distinct":[88],"positive":[89],"sample":[90],"pairs":[91],"branches":[94],"uses":[96],"inter-branch":[97],"constraints":[98],"maintain":[100],"consistent":[101],"motion":[102],"patterns.":[103],"Moreover,":[104,154],"decoupling":[108],"module":[109,122],"separate":[111],"feature\u2019s":[113],"spatial":[114],"temporal":[116],"information,":[117],"using":[118],"dual-path":[120],"self-attention":[121],"combined":[123],"with":[124],"an":[125],"intra-branch":[126],"cross-domain":[127],"strategy":[129],"facilitate":[131],"information":[132],"exchange":[133],"between":[134],"domains.":[135],"Extensive":[136],"experiments":[137],"four":[140],"public":[141],"datasets":[142],"NTU-RGB+D":[143],"(60&120)":[144],"PKU-MMD":[146],"(I&II)":[147],"demonstrate":[148],"effectiveness":[150],"components.":[153],"PASTD":[155],"outperforms":[156],"state-of-the-art":[157],"across":[159],"various":[160],"evaluation":[161],"metrics.":[162]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}