{"id":"https://openalex.org/W4366966749","doi":"https://doi.org/10.1109/tcsvt.2023.3269666","title":"Spatiotemporal Learning Transformer for Video-Based Human Pose Estimation","display_name":"Spatiotemporal Learning Transformer for Video-Based Human Pose Estimation","publication_year":2023,"publication_date":"2023-04-24","ids":{"openalex":"https://openalex.org/W4366966749","doi":"https://doi.org/10.1109/tcsvt.2023.3269666"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3269666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3269666","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.bournemouth.ac.uk/38864/1/Spatiotemporal_Learning_Transformer_for_Video-Based_Human_Pose_Estimation.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041243051","display_name":"Di Gai","orcid":null},"institutions":[{"id":"https://openalex.org/I141649914","display_name":"Nanchang University","ror":"https://ror.org/042v6xz23","country_code":"CN","type":"education","lineage":["https://openalex.org/I141649914"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Di Gai","raw_affiliation_strings":["School of Mathematics and Computer Sciences, the Jiangxi Key Laboratory of Smart City, and the Institute of Metaverse, Nanchang University, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"School of Mathematics and Computer Sciences, the Jiangxi Key Laboratory of Smart City, and the Institute of Metaverse, Nanchang University, Nanchang, China","institution_ids":["https://openalex.org/I141649914"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083780769","display_name":"Runyang Feng","orcid":"https://orcid.org/0000-0002-4912-6646"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runyang Feng","raw_affiliation_strings":["School of Artificial Intelligence, Jilin University, Changchun, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046155722","display_name":"Weidong Min","orcid":"https://orcid.org/0000-0003-2526-2181"},"institutions":[{"id":"https://openalex.org/I141649914","display_name":"Nanchang University","ror":"https://ror.org/042v6xz23","country_code":"CN","type":"education","lineage":["https://openalex.org/I141649914"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidong Min","raw_affiliation_strings":["School of Mathematics and Computer Sciences, the Jiangxi Key Laboratory of Smart City, and the Institute of Metaverse, Nanchang University, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"School of Mathematics and Computer Sciences, the Jiangxi Key Laboratory of Smart City, and the Institute of Metaverse, Nanchang University, Nanchang, China","institution_ids":["https://openalex.org/I141649914"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022654705","display_name":"Xiaosong Yang","orcid":"https://orcid.org/0000-0003-3815-0584"},"institutions":[{"id":"https://openalex.org/I9300472","display_name":"Bournemouth University","ror":"https://ror.org/05wwcw481","country_code":"GB","type":"education","lineage":["https://openalex.org/I9300472"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiaosong Yang","raw_affiliation_strings":["National Centre for Computer Animation, Bournemouth University, Poole, U.K"],"affiliations":[{"raw_affiliation_string":"National Centre for Computer Animation, Bournemouth University, Poole, U.K","institution_ids":["https://openalex.org/I9300472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072158202","display_name":"Pengxiang Su","orcid":null},"institutions":[{"id":"https://openalex.org/I141649914","display_name":"Nanchang University","ror":"https://ror.org/042v6xz23","country_code":"CN","type":"education","lineage":["https://openalex.org/I141649914"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengxiang Su","raw_affiliation_strings":["School of Software, Nanchang University, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Nanchang University, Nanchang, China","institution_ids":["https://openalex.org/I141649914"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341321","display_name":"Qi Wang","orcid":"https://orcid.org/0000-0002-7028-4956"},"institutions":[{"id":"https://openalex.org/I141649914","display_name":"Nanchang University","ror":"https://ror.org/042v6xz23","country_code":"CN","type":"education","lineage":["https://openalex.org/I141649914"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Wang","raw_affiliation_strings":["School of Mathematics and Computer Sciences, the Jiangxi Key Laboratory of Smart City, and the Institute of Metaverse, Nanchang University, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"School of Mathematics and Computer Sciences, the Jiangxi Key Laboratory of Smart City, and the Institute of Metaverse, Nanchang University, Nanchang, China","institution_ids":["https://openalex.org/I141649914"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029896144","display_name":"Qing Han","orcid":null},"institutions":[{"id":"https://openalex.org/I141649914","display_name":"Nanchang University","ror":"https://ror.org/042v6xz23","country_code":"CN","type":"education","lineage":["https://openalex.org/I141649914"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Han","raw_affiliation_strings":["School of Mathematics and Computer Sciences, the Jiangxi Key Laboratory of Smart City, and the Institute of Metaverse, Nanchang University, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"School of Mathematics and Computer Sciences, the Jiangxi Key Laboratory of Smart City, and the Institute of Metaverse, Nanchang University, Nanchang, China","institution_ids":["https://openalex.org/I141649914"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5041243051"],"corresponding_institution_ids":["https://openalex.org/I141649914"],"apc_list":null,"apc_paid":null,"fwci":3.5975,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":{"value":0.94465185,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"33","issue":"9","first_page":"4564","last_page":"4576"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998000264167786,"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":0.9998000264167786,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.995199978351593,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9922000169754028,"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/computer-science","display_name":"Computer science","score":0.8131714463233948},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.789306640625},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6737775802612305},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5562781095504761},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5462907552719116},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5293107032775879},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5290486216545105},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5160007476806641},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4908083379268646},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.431941956281662},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4145689904689789}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8131714463233948},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.789306640625},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6737775802612305},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5562781095504761},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5462907552719116},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5293107032775879},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5290486216545105},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5160007476806641},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4908083379268646},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.431941956281662},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4145689904689789},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2023.3269666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3269666","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Circuits and Systems for Video Technology","raw_type":"journal-article"},{"id":"pmh:oai:eprints.bournemouth.ac.uk:38864","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.bournemouth.ac.uk/38864/1/Spatiotemporal_Learning_Transformer_for_Video-Based_Human_Pose_Estimation.pdf","source":{"id":"https://openalex.org/S4306400187","display_name":"Bournemouth University Research Online (Bournemouth University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9300472","host_organization_name":"Bournemouth University","host_organization_lineage":["https://openalex.org/I9300472"],"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":"PeerReviewed"}],"best_oa_location":{"id":"pmh:oai:eprints.bournemouth.ac.uk:38864","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.bournemouth.ac.uk/38864/1/Spatiotemporal_Learning_Transformer_for_Video-Based_Human_Pose_Estimation.pdf","source":{"id":"https://openalex.org/S4306400187","display_name":"Bournemouth University Research Online (Bournemouth University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9300472","host_organization_name":"Bournemouth University","host_organization_lineage":["https://openalex.org/I9300472"],"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":"PeerReviewed"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G1191276245","display_name":null,"funder_award_id":"62076117","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4486925438","display_name":null,"funder_award_id":"62166026","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5931362567","display_name":null,"funder_award_id":"20224BAB212011","funder_id":"https://openalex.org/F4320322665","funder_display_name":"Natural Science Foundation of Jiangxi Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322665","display_name":"Natural Science Foundation of Jiangxi Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4366966749.pdf","grobid_xml":"https://content.openalex.org/works/W4366966749.grobid-xml"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W1540144755","https://openalex.org/W1912967058","https://openalex.org/W2057204268","https://openalex.org/W2099305880","https://openalex.org/W2113325037","https://openalex.org/W2143478373","https://openalex.org/W2194775991","https://openalex.org/W2307770531","https://openalex.org/W2554082199","https://openalex.org/W2559085405","https://openalex.org/W2604346130","https://openalex.org/W2716916105","https://openalex.org/W2907137919","https://openalex.org/W2916798096","https://openalex.org/W2956532199","https://openalex.org/W2959975024","https://openalex.org/W2962773068","https://openalex.org/W2962849564","https://openalex.org/W2963402313","https://openalex.org/W2963708869","https://openalex.org/W2963759896","https://openalex.org/W2963781481","https://openalex.org/W2964084369","https://openalex.org/W2964185410","https://openalex.org/W2964221239","https://openalex.org/W2964304707","https://openalex.org/W2967298375","https://openalex.org/W2977426443","https://openalex.org/W2991833656","https://openalex.org/W2994857106","https://openalex.org/W3011208089","https://openalex.org/W3034399482","https://openalex.org/W3035435924","https://openalex.org/W3072456739","https://openalex.org/W3103089151","https://openalex.org/W3109653595","https://openalex.org/W3110103163","https://openalex.org/W3173415456","https://openalex.org/W3175123126","https://openalex.org/W3193694068","https://openalex.org/W4205572757","https://openalex.org/W4214508443","https://openalex.org/W4214545909","https://openalex.org/W4214657742","https://openalex.org/W4221025196","https://openalex.org/W4225557002","https://openalex.org/W4283825932","https://openalex.org/W4288335118","https://openalex.org/W4295295532","https://openalex.org/W4312305353","https://openalex.org/W4312967365","https://openalex.org/W6748370023","https://openalex.org/W6750378959","https://openalex.org/W6750584947","https://openalex.org/W6757658208","https://openalex.org/W6763478003","https://openalex.org/W6766781929","https://openalex.org/W6771382925","https://openalex.org/W6785685617"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W1974414866","https://openalex.org/W2057568687","https://openalex.org/W2063982682","https://openalex.org/W2338543196","https://openalex.org/W4309346246"],"abstract_inverted_index":{"Multi-frame":[0],"human":[1,98,144,237],"pose":[2,22,99],"estimation":[3,100],"has":[4],"long":[5],"been":[6],"an":[7,89],"appealing":[8],"and":[9,21,120,133,146,203,212,229,244,260,277],"fundamental":[10],"issue":[11],"in":[12,24,44,70,76,235,271],"visual":[13,279],"perception.":[14],"Owing":[15],"to":[16,35,139,141,150,159,169,179,187,195,221,242],"the":[17,45,50,66,71,77,84,135,142,152,166,171,182,188,192,197,200,204,209,213,223,231,236,240,247],"frequent":[18],"rapid":[19],"motion":[20,255],"occlusion":[23],"videos,":[25],"this":[26],"task":[27],"is":[28,177],"extremely":[29],"challenging.":[30],"Current":[31],"state-of-the-art":[32,269],"methods":[33],"seek":[34],"model":[36,241],"spatiotemporal":[37,93,153,193],"features":[38,63,138,149,194],"by":[39],"equally":[40],"fusing":[41],"each":[42,227],"frame":[43,52,137,168,190,202],"local":[46,205],"sequence,":[47,206],"which":[48,102,131],"weakens":[49],"target":[51,167,189,201],"information.":[53],"In":[54],"addition,":[55],"existing":[56],"approaches":[57,270],"usually":[58],"emphasize":[59],"more":[60],"on":[61,165,252],"deep":[62,214],"while":[64],"ignoring":[65],"detailed":[67,211],"information":[68,183],"implied":[69],"shallow":[72,210],"feature":[73],"maps,":[74],"resulting":[75],"dropping":[78],"of":[79,104,226,273],"crucial":[80],"features.":[81,154],"To":[82,125],"address":[83],"above":[85],"problems,":[86],"we":[87,128,218],"propose":[88,129],"effective":[90],"framework,":[91],"namely":[92],"learning":[94],"transformer":[95],"for":[96,181],"video-based":[97],"(SLT-Pose),":[101],"consists":[103],"a":[105,175],"Personalized":[106],"Feature":[107],"Extraction":[108],"Module":[109,113,118],"(PFEM),":[110],"Self-feature":[111],"Refinement":[112],"(SRM),":[114],"Cross-frame":[115],"Temporal":[116],"Learning":[117],"(CTLM)":[119],"Disentangled":[121],"Keypoint":[122],"Detector":[123],"(DKD).":[124],"be":[126],"specific,":[127],"PFEM":[130],"extracts":[132],"modulates":[134],"individual":[136],"adapt":[140],"varying":[143],"shape,":[145],"integrates":[147],"single-frame":[148],"obtain":[151],"We":[155],"further":[156],"present":[157],"SRM":[158],"establish":[160],"global":[161],"correlation":[162],"spatial":[163],"cues":[164],"attain":[170],"refinement":[172],"feature.":[173],"Then,":[174],"CTLM":[176],"designed":[178],"search":[180],"most":[184],"closely":[185],"related":[186],"from":[191],"intensify":[196],"interaction":[198],"between":[199],"using":[207],"both":[208,274],"semantic":[215],"representations.":[216],"Finally,":[217],"employ":[219],"DKD":[220],"extract":[222],"disentangled":[224],"characteristics":[225],"joint":[228,233],"encode":[230],"articulated":[232],"pairs":[234],"body,":[238],"promoting":[239],"reasonably":[243],"accurately":[245],"predict":[246],"keypoint":[248],"heatmaps.":[249],"Extensive":[250],"experiments":[251],"three":[253],"huamn":[254],"benchmarks,":[256],"including":[257],"PoseTrack2017,":[258],"PoseTrack2018,":[259],"Sub-JHMDB":[261],"dataset,":[262],"demonstrate":[263],"that":[264],"SLT-Pose":[265],"plays":[266],"favorably":[267],"against":[268],"terms":[272],"objective":[275],"evaluation":[276],"subjective":[278],"performance.":[280]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}