{"id":"https://openalex.org/W4415883031","doi":"https://doi.org/10.1109/tcsvt.2025.3628996","title":"Expressive Human Volumetric Video Generation With Rich Text","display_name":"Expressive Human Volumetric Video Generation With Rich Text","publication_year":2025,"publication_date":"2025-11-04","ids":{"openalex":"https://openalex.org/W4415883031","doi":"https://doi.org/10.1109/tcsvt.2025.3628996"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2025.3628996","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3628996","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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":null,"display_name":"Yi Yang","orcid":"https://orcid.org/0009-0009-4106-4581"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["School of Artificial Intelligence, Sun Yat-sen University, Zhuhai, China"],"raw_orcid":"https://orcid.org/0009-0009-4106-4581","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Sun Yat-sen University, Zhuhai, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030883042","display_name":"Guanghui Yue","orcid":"https://orcid.org/0000-0002-6761-8767"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanghui Yue","raw_affiliation_strings":["School of Biomedical Engineering, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-6761-8767","affiliations":[{"raw_affiliation_string":"School of Biomedical Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077250575","display_name":"Wei Zhou","orcid":"https://orcid.org/0000-0003-3641-1429"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wei Zhou","raw_affiliation_strings":["School of Computer Science and Informatics, Cardiff University, Cardiff, U.K","School of Computer Science and Informatics, Cardiff University, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-3641-1429","affiliations":[{"raw_affiliation_string":"School of Computer Science and Informatics, Cardiff University, Cardiff, U.K","institution_ids":["https://openalex.org/I79510175"]},{"raw_affiliation_string":"School of Computer Science and Informatics, Cardiff University, United Kingdom","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006837984","display_name":"Xudong Mao","orcid":"https://orcid.org/0000-0002-1952-4176"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xudong Mao","raw_affiliation_strings":["School of Artificial Intelligence, Sun Yat-sen University, Zhuhai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Sun Yat-sen University, Zhuhai, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000079751","display_name":"Ruomei Wang","orcid":"https://orcid.org/0000-0002-2712-4412"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruomei Wang","raw_affiliation_strings":["School of Software Engineering, Sun Yat-sen University, Zhuhai, China"],"raw_orcid":"https://orcid.org/0000-0002-2712-4412","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Sun Yat-sen University, Zhuhai, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102379113","display_name":"Baoquan Zhao","orcid":"https://orcid.org/0000-0002-0574-1663"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoquan Zhao","raw_affiliation_strings":["School of Artificial Intelligence, Sun Yat-sen University, Zhuhai, China"],"raw_orcid":"https://orcid.org/0000-0002-0574-1663","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Sun Yat-sen University, Zhuhai, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35337834,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"4","first_page":"5424","last_page":"5436"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.8549000024795532,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.8549000024795532,"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":0.08070000261068344,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.01940000057220459,"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/motion","display_name":"Motion (physics)","score":0.748199999332428},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6952000260353088},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.5313000082969666},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.4717999994754791},{"id":"https://openalex.org/keywords/stylized-fact","display_name":"Stylized fact","score":0.45879998803138733},{"id":"https://openalex.org/keywords/match-moving","display_name":"Match moving","score":0.4390999972820282},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.38839998841285706},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.36489999294281006},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.36250001192092896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8105000257492065},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.748199999332428},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6952000260353088},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6184999942779541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5778999924659729},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.5313000082969666},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.4717999994754791},{"id":"https://openalex.org/C38935604","wikidata":"https://www.wikidata.org/wiki/Q4330363","display_name":"Stylized fact","level":2,"score":0.45879998803138733},{"id":"https://openalex.org/C95020103","wikidata":"https://www.wikidata.org/wiki/Q1813492","display_name":"Match moving","level":3,"score":0.4390999972820282},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.38839998841285706},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.36489999294281006},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3515999913215637},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3285999894142151},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.32019999623298645},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.3151000142097473},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3093000054359436},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C174493125","wikidata":"https://www.wikidata.org/wiki/Q1073461","display_name":"Quarter-pixel motion","level":3,"score":0.26440000534057617},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C2777036941","wikidata":"https://www.wikidata.org/wiki/Q6917771","display_name":"Motion analysis","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C72560505","wikidata":"https://www.wikidata.org/wiki/Q204510","display_name":"Motion interpolation","level":5,"score":0.25600001215934753},{"id":"https://openalex.org/C46503548","wikidata":"https://www.wikidata.org/wiki/Q1145976","display_name":"Plain text","level":3,"score":0.2551000118255615}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2025.3628996","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3628996","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},{"id":"pmh:oai:https://orca.cardiff.ac.uk:182547","is_oa":false,"landing_page_url":"https://orca.cardiff.ac.uk/view/cardiffauthors/A2824239D.html>,","pdf_url":null,"source":{"id":"https://openalex.org/S4306401195","display_name":"ORCA Online Research @Cardiff (Cardiff University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79510175","host_organization_name":"Cardiff University","host_organization_lineage":["https://openalex.org/I79510175"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5369547173","display_name":null,"funder_award_id":"2023A1515011639","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G6519393976","display_name":null,"funder_award_id":"2023A1515011639","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G7022540869","display_name":null,"funder_award_id":"2024A1515030025","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G7779606772","display_name":null,"funder_award_id":"62176223","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8196606464","display_name":null,"funder_award_id":"62172452","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Plain":[0],"text":[1,30,70,189],"has":[2],"become":[3],"the":[4,128,144,151],"dominant":[5],"interactive":[6],"interface":[7],"for":[8,59,159],"text-driven":[9],"human":[10,208],"volumetric":[11,183,209],"video":[12,147,184],"generation.":[13],"However,":[14],"its":[15],"limited":[16],"customization":[17],"options":[18],"hinder":[19],"users":[20],"from":[21,94,186],"expressing":[22],"motion":[23,38,52,61,103,123,130,146,165,210],"effects":[24],"with":[25,44],"accuracy.":[26],"For":[27],"example,":[28],"plain":[29,191],"struggles":[31],"to":[32,49,141,150,171],"specify":[33],"continuous":[34],"variables":[35],"such":[36],"as":[37],"amplitude,":[39],"speed,":[40],"and":[41,46,87,108,121,161,190],"joint":[42,110],"trajectories":[43],"precision,":[45],"it":[47],"fails":[48],"convey":[50],"stylized":[51],"characteristics.":[53],"Additionally,":[54],"crafting":[55],"detailed":[56],"textual":[57],"prompts":[58,68],"complex":[60],"sequences":[62],"is":[63],"cumbersome,":[64],"while":[65],"excessively":[66],"long":[67],"strain":[69],"encoders.":[71],"To":[72],"address":[73],"these":[74],"limitations,":[75],"we":[76,134,155,196],"propose":[77],"a":[78,136,168],"rich":[79,95,188],"text-based":[80],"framework":[81],"that":[82,143,198],"supports":[83],"font":[84],"styles,":[85,104],"sizes,":[86],"trajectory":[88,111],"sketching.":[89],"By":[90],"extracting":[91],"motion-related":[92],"attributes":[93],"text,":[96],"our":[97,199],"method":[98,200],"enables":[99],"fine-grained":[100],"control":[101],"over":[102],"precise":[105],"speed":[106],"regulation,":[107],"accurate":[109],"manipulation.":[112],"These":[113],"capabilities":[114],"are":[115],"realized":[116],"through":[117],"gradient-guided":[118,138],"noise":[119],"editing":[120],"ControlNet-based":[122],"optimization,":[124],"which":[125],"operate":[126],"within":[127],"latent":[129],"diffusion":[131],"process.":[132],"Specifically,":[133],"design":[135],"unified":[137],"adaptation":[139],"mechanism":[140],"ensure":[142],"generated":[145],"adheres":[148],"strictly":[149],"specified":[152],"constraints.":[153],"Furthermore,":[154],"introduce":[156],"realism-oriented":[157],"optimization":[158],"stylistic":[160],"joint-level":[162],"control,":[163],"refining":[164],"synthesis":[166],"at":[167],"granular":[169],"level":[170],"produce":[172],"smoother,":[173],"more":[174],"natural":[175],"movements.":[176],"We":[177],"present":[178],"multiple":[179],"comparative":[180],"evaluations":[181],"showcasing":[182],"generation":[185],"both":[187],"text.":[192],"Through":[193],"quantitative":[194],"analysis,":[195],"demonstrate":[197],"surpasses":[201],"strong":[202],"plain-text":[203],"baselines,":[204],"producing":[205],"expressive,":[206],"customizable":[207],"videos.":[211]},"counts_by_year":[],"updated_date":"2026-04-07T06:01:17.266235","created_date":"2025-11-04T00:00:00"}
