{"id":"https://openalex.org/W4392909913","doi":"https://doi.org/10.1109/icassp48485.2024.10446237","title":"Text2Avatar: Text to 3d Human Avatar Generation with Codebook-Driven Body Controllable Attribute","display_name":"Text2Avatar: Text to 3d Human Avatar Generation with Codebook-Driven Body Controllable Attribute","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909913","doi":"https://doi.org/10.1109/icassp48485.2024.10446237"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5102563033","display_name":"Chaoqun Gong","orcid":"https://orcid.org/0009-0007-1790-0434"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Chaoqun Gong","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,China","Shenzhen International Graduate School, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102601222","display_name":"Yuqin Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqin Dai","raw_affiliation_strings":["Nanjing University of Science and Technology,School of Computer Science and Engineering,China","School of Computer Science and Engineering, Nanjing University of Science and Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology,School of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003335763","display_name":"Ronghui Li","orcid":"https://orcid.org/0000-0003-4850-0138"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Ronghui Li","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,China","Shenzhen International Graduate School, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018906868","display_name":"Achun Bao","orcid":"https://orcid.org/0009-0004-2844-9421"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Achun Bao","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,China","Shenzhen International Graduate School, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100691319","display_name":"Jun Li","orcid":"https://orcid.org/0000-0002-6239-2922"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Li","raw_affiliation_strings":["Nanjing University of Science and Technology,School of Computer Science and Engineering,China","School of Computer Science and Engineering, Nanjing University of Science and Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology,School of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100726984","display_name":"Jian Yang","orcid":"https://orcid.org/0000-0003-4800-832X"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["Nanjing University of Science and Technology,School of Computer Science and Engineering,China","School of Computer Science and Engineering, Nanjing University of Science and Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology,School of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100667179","display_name":"Yachao Zhang","orcid":"https://orcid.org/0000-0003-0118-6655"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Yachao Zhang","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,China","Shenzhen International Graduate School, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100754504","display_name":"Xiu Li","orcid":"https://orcid.org/0000-0003-0403-1923"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Xiu Li","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,China","Shenzhen International Graduate School, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4813,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.93980848,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"16","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9995999932289124,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9983999729156494,"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":0.9975000023841858,"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/avatar","display_name":"Avatar","score":0.9628788828849792},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.8190813064575195},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7853926420211792},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5326129198074341},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.47524333000183105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4240097105503082},{"id":"https://openalex.org/keywords/human-body-model","display_name":"Human-body model","score":0.4134896397590637}],"concepts":[{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.9628788828849792},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.8190813064575195},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7853926420211792},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5326129198074341},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.47524333000183105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4240097105503082},{"id":"https://openalex.org/C2781089380","wikidata":"https://www.wikidata.org/wiki/Q5936753","display_name":"Human-body model","level":2,"score":0.4134896397590637},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.5199999809265137}],"awards":[{"id":"https://openalex.org/G1940401171","display_name":null,"funder_award_id":"2023M731957","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G3549803541","display_name":null,"funder_award_id":"62306165","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7375162941","display_name":null,"funder_award_id":"62361166670","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7566429426","display_name":"\u5168\u53c2\u6570\u5316\u5b66\u4e60\u7684\u5b50\u7a7a\u95f4\u805a\u7c7b\u65b9\u6cd5\u53ca\u5e94\u7528\u7814\u7a76","funder_award_id":"62072242","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/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1967554269","https://openalex.org/W2471768434","https://openalex.org/W2981959899","https://openalex.org/W3034431451","https://openalex.org/W3047371217","https://openalex.org/W3109585842","https://openalex.org/W3115879670","https://openalex.org/W4286611269","https://openalex.org/W4286611314","https://openalex.org/W4294959213","https://openalex.org/W4298187450","https://openalex.org/W4312500989","https://openalex.org/W4312971576","https://openalex.org/W4327810111","https://openalex.org/W4390873382","https://openalex.org/W4393148505","https://openalex.org/W4399574593","https://openalex.org/W4402713106","https://openalex.org/W4403792521","https://openalex.org/W6791353385","https://openalex.org/W6843813467","https://openalex.org/W6845946351","https://openalex.org/W6851053448","https://openalex.org/W6851070570","https://openalex.org/W6857433768"],"related_works":["https://openalex.org/W2293149949","https://openalex.org/W2026099691","https://openalex.org/W4284672201","https://openalex.org/W2377486419","https://openalex.org/W2943202426","https://openalex.org/W2137816434","https://openalex.org/W2163679795","https://openalex.org/W3196465490","https://openalex.org/W2167654528","https://openalex.org/W4321231472"],"abstract_inverted_index":{"Generating":[0],"3D":[1,22,38,53,91,100,111,132],"human":[2,23,39,92,101],"models":[3],"directly":[4],"from":[5,134],"text":[6,59,75],"helps":[7],"reduce":[8],"the":[9,34,57,79,86],"cost":[10],"and":[11,20,33,76],"time":[12],"of":[13,36,81,88,110],"character":[14],"modeling.":[15],"However,":[16],"achieving":[17],"multi-attribute":[18],"controllable":[19],"realistic":[21,37,89,120,131],"avatar":[24,40,93,102,112],"generation":[25,103],"is":[26,139],"still":[27],"challenging":[28,140],"due":[29],"to":[30,70,84,105,118],"feature":[31,69],"coupling":[32],"scarcity":[35,87],"datasets.":[41],"To":[42],"address":[43],"these":[44],"issues,":[45],"we":[46,95],"propose":[47],"Text2Avatar,":[48],"which":[49,115,138],"can":[50,129],"generate":[51,130],"realistic-style":[52],"avatars":[54,133],"based":[55],"on":[56],"coupled":[58,135],"prompts.":[60],"Text2Avatar":[61,117],"leverages":[62],"a":[63,72,97,107],"discrete":[64],"codebook":[65],"as":[66],"an":[67],"intermediate":[68],"establish":[71],"connection":[73],"between":[74],"avatars,":[77],"enabling":[78],"disentanglement":[80],"features.":[82],"Furthermore,":[83],"alleviate":[85],"style":[90,121],"data,":[94,114,137],"utilize":[96],"pre-trained":[98],"unconditional":[99],"model":[104],"obtain":[106],"large":[108],"amount":[109],"pseudo":[113],"allows":[116],"achieve":[119],"generation.":[122],"Experimental":[123],"results":[124],"demonstrate":[125],"that":[126],"our":[127],"method":[128],"textual":[136],"for":[141],"other":[142],"existing":[143],"methods":[144],"in":[145],"this":[146],"field.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
