{"id":"https://openalex.org/W4391307065","doi":"https://doi.org/10.1109/smc53992.2023.10394361","title":"STMotionFormer: Language Guided 3D Human Motion Synthesis with Spatial Temporal Transformer","display_name":"STMotionFormer: Language Guided 3D Human Motion Synthesis with Spatial Temporal Transformer","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4391307065","doi":"https://doi.org/10.1109/smc53992.2023.10394361"},"language":"en","primary_location":{"id":"doi:10.1109/smc53992.2023.10394361","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/smc53992.2023.10394361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5010342402","display_name":"Yifan Lv","orcid":"https://orcid.org/0000-0003-2690-799X"},"institutions":[{"id":"https://openalex.org/I4210119942","display_name":"Wuhan Textile University","ror":"https://ror.org/02jgsf398","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210119942"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Lv","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Wuhan Textile University,Wuhan,China","School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Wuhan Textile University,Wuhan,China","institution_ids":["https://openalex.org/I4210119942"]},{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, China","institution_ids":["https://openalex.org/I4210119942"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109678223","display_name":"Xiaoqin Du","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119942","display_name":"Wuhan Textile University","ror":"https://ror.org/02jgsf398","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210119942"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqin Du","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Wuhan Textile University, Hubei Provincial Engineering Research Center for Intelligent Textile and Fashion,Wuhan,China","School of Computer Science and Artificial Intelligence, Wuhan Textile University, Hubei Provincial Engineering Research Center for Intelligent Textile and Fashion, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Wuhan Textile University, Hubei Provincial Engineering Research Center for Intelligent Textile and Fashion,Wuhan,China","institution_ids":["https://openalex.org/I4210119942"]},{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Wuhan Textile University, Hubei Provincial Engineering Research Center for Intelligent Textile and Fashion, Wuhan, China","institution_ids":["https://openalex.org/I4210119942"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101578107","display_name":"Jiashuang Zhou","orcid":"https://orcid.org/0009-0007-3675-1630"},"institutions":[{"id":"https://openalex.org/I4210119942","display_name":"Wuhan Textile University","ror":"https://ror.org/02jgsf398","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210119942"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiashuang Zhou","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Wuhan Textile University,Wuhan,China","School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Wuhan Textile University,Wuhan,China","institution_ids":["https://openalex.org/I4210119942"]},{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, China","institution_ids":["https://openalex.org/I4210119942"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102956462","display_name":"Yongqi Liu","orcid":"https://orcid.org/0009-0001-8453-8224"},"institutions":[{"id":"https://openalex.org/I4210119942","display_name":"Wuhan Textile University","ror":"https://ror.org/02jgsf398","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210119942"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongqi Liu","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Wuhan Textile University,Wuhan,China","School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Wuhan Textile University,Wuhan,China","institution_ids":["https://openalex.org/I4210119942"]},{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, China","institution_ids":["https://openalex.org/I4210119942"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067406265","display_name":"Xu Han","orcid":"https://orcid.org/0000-0001-9861-4868"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Xu","raw_affiliation_strings":["School of Journalism and Information Communication, Huazhong University of Science and Technology,Wuhan,China","School of Journalism and Information Communication, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Journalism and Information Communication, Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"School of Journalism and Information Communication, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4470","last_page":"4475"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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/T12290","display_name":"Human Motion and Animation","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9912999868392944,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7684763669967651},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7068269848823547},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5865647196769714},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5169355273246765},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4757547080516815},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.45824477076530457},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.45670080184936523},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36432358622550964},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3578992784023285},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3218322992324829},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2420056164264679}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7684763669967651},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7068269848823547},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5865647196769714},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5169355273246765},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4757547080516815},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.45824477076530457},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.45670080184936523},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36432358622550964},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3578992784023285},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3218322992324829},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2420056164264679},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc53992.2023.10394361","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/smc53992.2023.10394361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W613224938","https://openalex.org/W1517964818","https://openalex.org/W2101032778","https://openalex.org/W2425121537","https://openalex.org/W2614519765","https://openalex.org/W2798670545","https://openalex.org/W2862846329","https://openalex.org/W2894497779","https://openalex.org/W2896457183","https://openalex.org/W2963076818","https://openalex.org/W2982625143","https://openalex.org/W3068510429","https://openalex.org/W3115266783","https://openalex.org/W3125772723","https://openalex.org/W3134060426","https://openalex.org/W3144253442","https://openalex.org/W3153832461","https://openalex.org/W4297981470","https://openalex.org/W4313145975","https://openalex.org/W4385245566","https://openalex.org/W4390873117"],"related_works":["https://openalex.org/W2068608913","https://openalex.org/W3124914020","https://openalex.org/W2141033859","https://openalex.org/W2077542787","https://openalex.org/W2156434174","https://openalex.org/W2071701083","https://openalex.org/W2383687187","https://openalex.org/W2070401501","https://openalex.org/W2121496884","https://openalex.org/W2387910809"],"abstract_inverted_index":{"Inspired":[0],"by":[1,16,68],"the":[2,85,90,103,158,178,207],"Transformer's":[3],"adaptive":[4],"capability":[5],"in":[6,102,180],"natural":[7,65],"language":[8,162],"processing":[9],"and":[10,14,35,93,108,121,184],"computer":[11],"vision":[12],"domains,":[13],"supported":[15],"CLIP's":[17],"strong":[18],"semantic":[19,141,203],"prior":[20,142],"knowledge,":[21],"we":[22],"propose":[23,76,94],"a":[24,48,64],"novel":[25],"generative":[26],"model":[27,176,193],"named":[28],"STMotionFormer":[29],"based":[30],"on":[31,74,157],"improved":[32],"Transformer":[33,78,96],"block":[34,79,97],"CLIP":[36,145],"for":[37],"language-guided":[38],"3D":[39,168],"skeleton-based":[40],"human":[41,196],"motion":[42,161],"synthesis.":[43],"The":[44],"skeleton":[45,127],"sequence,":[46],"as":[47,133,135],"kind":[49],"of":[50,63,144,182],"spatial":[51,95,104,111,120],"temporal":[52,58,86,122],"dynamic":[53],"data,":[54],"not":[55],"only":[56],"contains":[57,165],"information":[59,204],"but":[60],"also":[61],"consists":[62],"graph":[66,131],"structure":[67,132],"different":[69],"body":[70],"parts.":[71],"We":[72,153],"focus":[73],"this,":[75],"Temporal":[77],"(T-Former)":[80],"applies":[81,99],"attention":[82,100],"mechanism":[83,101],"along":[84],"dimension":[87,105],"to":[88,106],"capture":[89],"long-term":[91],"relationship,":[92],"(S-Former)":[98],"aggregate":[107],"update":[109],"joints'":[110],"features.":[112],"Therefore,":[113],"our":[114,149,155,175,192],"approach":[115],"can":[116,125,194],"automatically":[117],"explore":[118],"both":[119],"information,":[123],"which":[124],"generate":[126,195],"sequence":[128],"with":[129,202],"reasonable":[130],"well":[134],"global":[136],"time":[137],"relationship.":[138],"Moreover,":[139],"powerful":[140],"knowledge":[143],"are":[146,199],"injected":[147],"into":[148],"motion-language":[150],"joint":[151],"manifold.":[152],"evaluate":[154],"method":[156],"public":[159],"KIT":[160],"dataset":[163],"that":[164,174,191,198],"manually":[166],"annotated":[167],"pose":[169],"sequences.":[170],"Experimental":[171],"results":[172,189],"show":[173],"outperforms":[177],"state-of-the-art":[179],"terms":[181],"APE":[183],"AVE":[185],"respectively.":[186],"Qualitative":[187],"visualization":[188],"indicate":[190],"motions":[197],"more":[200],"compatible":[201],"even":[205],"than":[206],"GroundTruth.":[208]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}