{"id":"https://openalex.org/W4312417903","doi":"https://doi.org/10.1109/cvpr52688.2022.01288","title":"MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video","display_name":"MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video","publication_year":2022,"publication_date":"2022-06-01","ids":{"openalex":"https://openalex.org/W4312417903","doi":"https://doi.org/10.1109/cvpr52688.2022.01288"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52688.2022.01288","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52688.2022.01288","pdf_url":null,"source":{"id":"https://openalex.org/S4363607701","display_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5041539748","display_name":"Jinlu Zhang","orcid":"https://orcid.org/0000-0002-8731-7099"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinlu Zhang","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074405661","display_name":"Zhigang Tu","orcid":"https://orcid.org/0000-0001-5003-2260"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhigang Tu","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007776175","display_name":"Jianyu Yang","orcid":"https://orcid.org/0000-0002-0208-221X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianyu Yang","raw_affiliation_strings":["Soochow University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101416291","display_name":"Yujin Chen","orcid":"https://orcid.org/0000-0003-3709-6125"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yujin Chen","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085245110","display_name":"Junsong Yuan","orcid":"https://orcid.org/0000-0002-7324-7034"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junsong Yuan","raw_affiliation_strings":["State University of New York at Buffalo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State University of New York at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":30.2214,"has_fulltext":false,"cited_by_count":412,"citation_normalized_percentile":{"value":0.9969516,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"13222","last_page":"13232"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"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":1.0,"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":0.9968000054359436,"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":0.9955999851226807,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.786889910697937},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7766611576080322},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6492893695831299},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5849025249481201},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5389019250869751},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4957467019557953},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47984951734542847},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.4787006676197052},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4786035716533661},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4350910186767578},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.4155592918395996},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4144099950790405},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4114062190055847},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11372658610343933}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.786889910697937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7766611576080322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6492893695831299},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5849025249481201},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5389019250869751},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4957467019557953},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47984951734542847},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.4787006676197052},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4786035716533661},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4350910186767578},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.4155592918395996},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4144099950790405},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4114062190055847},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11372658610343933},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52688.2022.01288","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52688.2022.01288","pdf_url":null,"source":{"id":"https://openalex.org/S4363607701","display_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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":70,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2052747804","https://openalex.org/W2064675550","https://openalex.org/W2099333815","https://openalex.org/W2101032778","https://openalex.org/W2118931255","https://openalex.org/W2133832403","https://openalex.org/W2155196764","https://openalex.org/W2307770531","https://openalex.org/W2554247908","https://openalex.org/W2611932403","https://openalex.org/W2612706635","https://openalex.org/W2756050327","https://openalex.org/W2797184202","https://openalex.org/W2798646183","https://openalex.org/W2916798096","https://openalex.org/W2962896489","https://openalex.org/W2963150697","https://openalex.org/W2963383668","https://openalex.org/W2963592930","https://openalex.org/W2963598138","https://openalex.org/W2964015378","https://openalex.org/W2964221239","https://openalex.org/W2964318832","https://openalex.org/W2966735886","https://openalex.org/W2972662547","https://openalex.org/W2985923700","https://openalex.org/W2987087879","https://openalex.org/W3022928074","https://openalex.org/W3034217102","https://openalex.org/W3034448411","https://openalex.org/W3034971010","https://openalex.org/W3035416506","https://openalex.org/W3037859578","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3097623574","https://openalex.org/W3098473649","https://openalex.org/W3098612954","https://openalex.org/W3106838237","https://openalex.org/W3112574648","https://openalex.org/W3126473426","https://openalex.org/W3126541466","https://openalex.org/W3136525061","https://openalex.org/W3137592945","https://openalex.org/W3169891778","https://openalex.org/W3173283771","https://openalex.org/W3173811519","https://openalex.org/W3174541392","https://openalex.org/W3175199633","https://openalex.org/W3178872387","https://openalex.org/W3195639294","https://openalex.org/W3203617912","https://openalex.org/W4200316912","https://openalex.org/W4225557002","https://openalex.org/W4283817055","https://openalex.org/W4312275869","https://openalex.org/W4312982586","https://openalex.org/W4385245566","https://openalex.org/W6697925102","https://openalex.org/W6726873649","https://openalex.org/W6745881451","https://openalex.org/W6766771472","https://openalex.org/W6767176642","https://openalex.org/W6777015449","https://openalex.org/W6778485988","https://openalex.org/W6784333009","https://openalex.org/W6785687725","https://openalex.org/W6789699889","https://openalex.org/W6792506852"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W4205302943","https://openalex.org/W2119949815","https://openalex.org/W4283822356","https://openalex.org/W1950940422","https://openalex.org/W2129146436","https://openalex.org/W2032507829","https://openalex.org/W2147282173"],"abstract_inverted_index":{"Recent":[0],"transformer-based":[1],"solutions":[2],"have":[3],"been":[4],"introduced":[5],"to":[6,23,52,70,84,95,112],"estimate":[7],"3D":[8],"human":[9],"pose":[10],"from":[11,108],"2D":[12],"keypoint":[13],"sequence":[14],"by":[15,151],"considering":[16],"body":[17],"joints":[18,34],"among":[19],"all":[20],"frames":[21,114],"globally":[22],"learn":[24,85],"spatio-temporal":[25,98],"correlation.":[26,57,88],"We":[27,58],"observe":[28],"that":[29,144],"the":[30,38,44,73,103,109,116,121,124,148],"motions":[31],"of":[32,48,55,76,115],"different":[33],"differ":[35],"significantly.":[36],"However,":[37],"previous":[39],"methods":[40],"cannot":[41],"efficiently":[42],"model":[43,72,146],"solid":[45],"inter-frame":[46],"correspondence":[47],"each":[49,77],"joint,":[50],"leading":[51],"insufficient":[53],"learning":[54],"spatial-temporal":[56],"propose":[59],"MixSTE":[60],"(Mixed":[61],"Spatio-Temporal":[62],"Encoder),":[63],"which":[64],"has":[65],"a":[66,80],"temporal":[67,74],"transformer":[68,82],"block":[69,83],"separately":[71],"motion":[75],"joint":[78],"and":[79,126,139,154],"spatial":[81,87],"inter-joint":[86],"These":[89],"two":[90],"blocks":[91],"are":[92,131],"utilized":[93],"alternately":[94],"obtain":[96],"better":[97],"feature":[99],"encoding.":[100],"In":[101],"addition,":[102],"network":[104],"output":[105,127],"is":[106,159],"extended":[107],"central":[110],"frame":[111],"entire":[113],"input":[117,125],"video,":[118],"thereby":[119],"improving":[120],"coherence":[122],"between":[123],"sequences.":[128],"Extensive":[129],"experiments":[130],"conducted":[132],"on":[133],"three":[134],"benchmarks":[135],"(i.e.":[136],"Human3.6M,":[137],"MPI-INF-3DHP,":[138],"HumanEva).":[140],"The":[141,157],"results":[142],"show":[143],"our":[145],"outperforms":[147],"state-of-the-art":[149],"approach":[150],"10.9%":[152],"P-MPJPE":[153],"7.6%":[155],"MPJPE.":[156],"code":[158],"available":[160],"at":[161],"https://github.com/JinluZhang1126/MixSTE.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":83},{"year":2025,"cited_by_count":135},{"year":2024,"cited_by_count":122},{"year":2023,"cited_by_count":67},{"year":2022,"cited_by_count":5}],"updated_date":"2026-09-06T09:10:53.072986","created_date":"2025-10-10T00:00:00"}