{"id":"https://openalex.org/W4376657587","doi":"https://doi.org/10.1145/3588432.3591490","title":"PoseVocab: Learning Joint-structured Pose Embeddings for Human Avatar Modeling","display_name":"PoseVocab: Learning Joint-structured Pose Embeddings for Human Avatar Modeling","publication_year":2023,"publication_date":"2023-07-19","ids":{"openalex":"https://openalex.org/W4376657587","doi":"https://doi.org/10.1145/3588432.3591490"},"language":"en","primary_location":{"id":"doi:10.1145/3588432.3591490","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3588432.3591490","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3588432.3591490","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Proceedings","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3588432.3591490","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100671773","display_name":"Zhe Li","orcid":"https://orcid.org/0000-0003-4703-0875"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Li","raw_affiliation_strings":["Tsinghua University, China"],"raw_orcid":"https://orcid.org/0000-0003-4703-0875","affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074081252","display_name":"Zerong Zheng","orcid":"https://orcid.org/0000-0003-1339-2480"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zerong Zheng","raw_affiliation_strings":["Tsinghua University, China and NNKosmos Technology, China"],"raw_orcid":"https://orcid.org/0000-0003-1339-2480","affiliations":[{"raw_affiliation_string":"Tsinghua University, China and NNKosmos Technology, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085355221","display_name":"Yuxiao Liu","orcid":"https://orcid.org/0009-0002-0580-6647"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiao Liu","raw_affiliation_strings":["Tsinghua University, China"],"raw_orcid":"https://orcid.org/0009-0002-0580-6647","affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057994306","display_name":"Boyao Zhou","orcid":"https://orcid.org/0009-0004-4583-2676"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyao Zhou","raw_affiliation_strings":["Tsinghua University, China"],"raw_orcid":"https://orcid.org/0009-0004-4583-2676","affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032875389","display_name":"Yebin Liu","orcid":"https://orcid.org/0000-0003-3215-0225"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yebin Liu","raw_affiliation_strings":["Tsinghua University, China"],"raw_orcid":"https://orcid.org/0000-0003-3215-0225","affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9986000061035156,"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":0.8064660429954529},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.7249877452850342},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6928609609603882},{"id":"https://openalex.org/keywords/avatar","display_name":"Avatar","score":0.6366346478462219},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6323961019515991},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.615205705165863},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5803459882736206},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.532648503780365},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4833357036113739},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4793420732021332},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4462069571018219},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4193381667137146},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.4116232991218567},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40928351879119873},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.11175525188446045}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8064660429954529},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.7249877452850342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6928609609603882},{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.6366346478462219},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6323961019515991},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.615205705165863},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5803459882736206},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.532648503780365},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4833357036113739},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4793420732021332},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4462069571018219},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4193381667137146},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.4116232991218567},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40928351879119873},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.11175525188446045},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3588432.3591490","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3588432.3591490","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3588432.3591490","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Proceedings","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3588432.3591490","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3588432.3591490","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3588432.3591490","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Proceedings","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8989291188","display_name":null,"funder_award_id":"62125107","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4376657587.pdf","grobid_xml":"https://content.openalex.org/works/W4376657587.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W1967554269","https://openalex.org/W2016959837","https://openalex.org/W2133665775","https://openalex.org/W2793768642","https://openalex.org/W2942074357","https://openalex.org/W2949924544","https://openalex.org/W2962785568","https://openalex.org/W2971467054","https://openalex.org/W2978956737","https://openalex.org/W3036843665","https://openalex.org/W3107384982","https://openalex.org/W3109585842","https://openalex.org/W3157519194","https://openalex.org/W3161462225","https://openalex.org/W3165164793","https://openalex.org/W3166229844","https://openalex.org/W3168949721","https://openalex.org/W3176327543","https://openalex.org/W3182000110","https://openalex.org/W3201726595","https://openalex.org/W3202627061","https://openalex.org/W3202804820","https://openalex.org/W3203514471","https://openalex.org/W3210043805","https://openalex.org/W3212141385","https://openalex.org/W4221151978","https://openalex.org/W4226049640","https://openalex.org/W4283770636","https://openalex.org/W4286110585","https://openalex.org/W4287114999","https://openalex.org/W4288804810","https://openalex.org/W4306178025","https://openalex.org/W4310444161","https://openalex.org/W4312234520","https://openalex.org/W4312341890","https://openalex.org/W4312433790","https://openalex.org/W4312440792","https://openalex.org/W4312453532","https://openalex.org/W4312635677","https://openalex.org/W4312793185","https://openalex.org/W4312828520","https://openalex.org/W4312925709","https://openalex.org/W4312960807","https://openalex.org/W4313136947","https://openalex.org/W4313191666","https://openalex.org/W4385275452","https://openalex.org/W4386072032","https://openalex.org/W6600341180","https://openalex.org/W6600538214","https://openalex.org/W6798033281","https://openalex.org/W6948108987","https://openalex.org/W7074559608"],"related_works":["https://openalex.org/W4253893311","https://openalex.org/W3089306886","https://openalex.org/W2113785214","https://openalex.org/W2798721181","https://openalex.org/W3201205132","https://openalex.org/W4312694060","https://openalex.org/W4386075737","https://openalex.org/W4393563475","https://openalex.org/W4387967917","https://openalex.org/W4382141741"],"abstract_inverted_index":{"Creating":[0],"pose-driven":[1],"human":[2,17,29,34,62,181,210,220],"avatars":[3],"is":[4,31,196,250],"about":[5],"modeling":[6],"the":[7,10,50,54,60,80,101,122,132,142,147,154,158,204,216],"mapping":[8],"from":[9],"low-frequency":[11],"driving":[12],"pose":[13,22,45,56,85,103,108,117,134,159,187,200,206],"to":[14,33,52,110,139,146,175,198],"high-frequency":[15],"dynamic":[16,61,123,209,217],"appearances,":[18],"so":[19],"an":[20],"effective":[21,172],"encoding":[23,46],"method":[24,47,235],"that":[25,48,233],"can":[26],"encode":[27,121],"high-fidelity":[28],"details":[30,179,218],"essential":[32],"avatar":[35],"modeling.":[36],"To":[37,83,152],"this":[38],"end,":[39],"we":[40,90,165],"present":[41],"PoseVocab,":[42],"a":[43,69,107,169,185,189,192],"novel":[44,229],"encourages":[49],"network":[51],"discover":[53],"optimal":[55],"embeddings":[57,77,118,201],"for":[58,208],"learning":[59],"appearance.":[63],"Given":[64],"multi-view":[65],"RGB":[66],"videos":[67],"of":[68,96,149,157,180,219,246],"character,":[70],"PoseVocab":[71,213],"constructs":[72],"key":[73,92,113,127],"poses":[74],"and":[75,87,105,188,202,222,225,242],"latent":[76],"based":[78],"on":[79],"training":[81],"poses.":[82,230],"achieve":[84],"generalization":[86],"temporal":[88],"consistency,":[89],"sample":[91],"rotations":[93],"in":[94,244],"so(3)":[95],"each":[97,111,150],"joint":[98],"rather":[99],"than":[100],"global":[102,133],"vectors,":[104],"assign":[106],"embedding":[109,135,160],"sampled":[112],"rotation.":[114],"These":[115],"joint-structured":[116,137],"not":[119],"only":[120],"appearances":[124],"under":[125,228],"different":[126],"poses,":[128],"but":[129],"also":[130],"factorize":[131],"into":[136],"ones":[138],"better":[140],"learn":[141],"appearance":[143,221],"variation":[144],"related":[145],"motion":[148],"joint.":[151],"improve":[153],"representation":[155],"ability":[156],"while":[161],"maintaining":[162],"memory":[163],"efficiency,":[164],"introduce":[166],"feature":[167,207],"lines,":[168],"compact":[170],"yet":[171],"3D":[173],"representation,":[174],"model":[176],"more":[177],"fine-grained":[178],"appearances.":[182],"Furthermore,":[183],"given":[184],"query":[186,194],"spatial":[190],"position,":[191],"hierarchical":[193],"strategy":[195],"introduced":[197],"interpolate":[199],"acquire":[203],"conditional":[205],"synthesis.":[211],"Overall,":[212],"effectively":[214],"encodes":[215],"enables":[223],"realistic":[224],"generalized":[226],"animation":[227],"Experiments":[231],"show":[232],"our":[234],"outperforms":[236],"other":[237],"state-of-the-art":[238],"baselines":[239],"both":[240],"qualitatively":[241],"quantitatively":[243],"terms":[245],"synthesis":[247],"quality.":[248],"Code":[249],"available":[251],"at":[252],"https://github.com/lizhe00/PoseVocab.":[253]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2023-05-17T00:00:00"}