{"id":"https://openalex.org/W4415708113","doi":"https://doi.org/10.1109/icme59968.2025.11209135","title":"SwinCAE: Capsule Autoencoder using Shifted Windows for 3D Human Pose Estimation","display_name":"SwinCAE: Capsule Autoencoder using Shifted Windows for 3D Human Pose Estimation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708113","doi":"https://doi.org/10.1109/icme59968.2025.11209135"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5100735904","display_name":"Xiufeng Liu","orcid":"https://orcid.org/0000-0002-3315-8571"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiufeng Liu","raw_affiliation_strings":["Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102019923","display_name":"Zhongqiu Zhao","orcid":"https://orcid.org/0000-0003-3940-3256"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongqiu Zhao","raw_affiliation_strings":["Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115591010","display_name":"Yi Yang","orcid":"https://orcid.org/0009-0009-7760-333X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010997479","display_name":"Donghui Hu","orcid":"https://orcid.org/0000-0001-9517-9688"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Donghui Hu","raw_affiliation_strings":["Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101828632","display_name":"Zhao Zhang","orcid":"https://orcid.org/0000-0002-3271-7482"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Zhang","raw_affiliation_strings":["Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26433043,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9832000136375427,"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":0.9832000136375427,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.00419999985024333,"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"}},{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.0027000000700354576,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/autoencoder","display_name":"Autoencoder","score":0.8959000110626221},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.7281000018119812},{"id":"https://openalex.org/keywords/viewpoints","display_name":"Viewpoints","score":0.636900007724762},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.566100001335144},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5638999938964844},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5314000248908997},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.46959999203681946},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4528999924659729}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8959000110626221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7998999953269958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7710000276565552},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.7281000018119812},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.636900007724762},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6116999983787537},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.566100001335144},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5638999938964844},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5314000248908997},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.46959999203681946},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4528999924659729},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4458000063896179},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.40529999136924744},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.3294999897480011},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2824999988079071},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C2777897806","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3D modeling","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2101032778","https://openalex.org/W2593146028","https://openalex.org/W2611932403","https://openalex.org/W2799211965","https://openalex.org/W2895689136","https://openalex.org/W2962896489","https://openalex.org/W2964221239","https://openalex.org/W3014641072","https://openalex.org/W3106838237","https://openalex.org/W3106882556","https://openalex.org/W3126541466","https://openalex.org/W3136525061","https://openalex.org/W3138516171","https://openalex.org/W3202716970","https://openalex.org/W4213019189","https://openalex.org/W4252298411","https://openalex.org/W4312249545","https://openalex.org/W4312417903","https://openalex.org/W4312797994","https://openalex.org/W4385780399","https://openalex.org/W4386075813","https://openalex.org/W4386076485","https://openalex.org/W4390874574","https://openalex.org/W4402715909","https://openalex.org/W4402980496"],"related_works":[],"abstract_inverted_index":{"Estimating":[0],"3D":[1,143],"human":[2,144],"poses":[3],"from":[4],"monocular":[5],"videos":[6],"is":[7,119],"a":[8,45,49,78,96,124],"challenging":[9],"task,":[10],"primarily":[11],"due":[12],"to":[13,86,100,139],"self-occlusion.":[14],"Many":[15],"existing":[16],"methods":[17],"struggle":[18],"with":[19,53,82],"unseen":[20],"viewpoints":[21],"as":[22],"they":[23],"rely":[24],"on":[25],"large":[26],"amounts":[27],"of":[28,113],"data":[29],"rather":[30],"than":[31],"enhancing":[32],"their":[33],"generalization":[34],"ability":[35],"across":[36],"different":[37],"viewpoints.":[38],"To":[39],"overcome":[40],"this":[41],"limitation,":[42],"we":[43,76,94],"propose":[44],"novel":[46],"approach":[47],"using":[48],"capsule":[50],"autoencoder":[51],"integrated":[52],"the":[54,66,71,111,116],"shifted-windows":[55],"model":[56,117],"(SwinCAE),":[57],"which":[58],"can":[59],"enhance":[60,87],"prediction":[61],"accuracy":[62],"by":[63],"effectively":[64],"capturing":[65],"spatial":[67],"hierarchical":[68],"relationship":[69],"between":[70],"parts":[72],"and":[73,90,107],"objects.":[74],"Furthermore,":[75],"build":[77],"Parallel":[79],"Double":[80],"Attention":[81],"Shifted":[83],"Windows":[84],"module":[85,99],"computational":[88],"efficiency":[89],"modeling":[91],"capacity.":[92],"Additionally,":[93],"construct":[95],"Multi-Attention":[97],"Collaborative":[98],"capture":[101],"diverse":[102],"information,":[103],"including":[104],"both":[105],"coarse":[106],"fine":[108],"details.":[109],"Through":[110],"collaboration":[112],"these":[114],"modules,":[115],"representation":[118],"significantly":[120],"improved,":[121],"resulting":[122],"in":[123],"more":[125],"accurate":[126],"generated":[127],"pose.":[128],"Extensive":[129],"experiments":[130],"demonstrate":[131],"that":[132],"SwinCAE":[133],"achieves":[134],"better":[135],"or":[136],"comparable":[137],"results":[138],"state-of-the-art":[140],"models":[141],"about":[142],"pose":[145],"estimation":[146],"task.":[147]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-30T00:00:00"}