{"id":"https://openalex.org/W4416249737","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229178","title":"AG-Mask: Augmented 3D Generative Masked Motion Model for Text-to-Motion","display_name":"AG-Mask: Augmented 3D Generative Masked Motion Model for Text-to-Motion","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416249737","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229178"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5053607992","display_name":"Zhiqiang Su","orcid":"https://orcid.org/0009-0008-2373-1961"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zixin Su","raw_affiliation_strings":["Guangxi University,School of Computer and Electronic Information,Nanning,China"],"affiliations":[{"raw_affiliation_string":"Guangxi University,School of Computer and Electronic Information,Nanning,China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104039802","display_name":"Mengxiao Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengxiao Yin","raw_affiliation_strings":["Guangxi University,School of Computer and Electronic Information,Nanning,China"],"affiliations":[{"raw_affiliation_string":"Guangxi University,School of Computer and Electronic Information,Nanning,China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038788038","display_name":"Fei Xie","orcid":"https://orcid.org/0000-0002-0105-5826"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fancui Xie","raw_affiliation_strings":["Guangxi University,School of Computer and Electronic Information,Nanning,China"],"affiliations":[{"raw_affiliation_string":"Guangxi University,School of Computer and Electronic Information,Nanning,China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077844760","display_name":"Peihong Wu","orcid":"https://orcid.org/0000-0001-8008-1872"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peihong Wu","raw_affiliation_strings":["Guangxi University,School of Computer and Electronic Information,Nanning,China"],"affiliations":[{"raw_affiliation_string":"Guangxi University,School of Computer and Electronic Information,Nanning,China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101732526","display_name":"Bei Hua","orcid":"https://orcid.org/0000-0001-7281-8977"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bei Hua","raw_affiliation_strings":["Guangxi University,School of Computer and Electronic Information,Nanning,China"],"affiliations":[{"raw_affiliation_string":"Guangxi University,School of Computer and Electronic Information,Nanning,China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"last","author":{"id":null,"display_name":"Feng Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Zhan","raw_affiliation_strings":["Guangxi University,School of Computer and Electronic Information,Nanning,China"],"affiliations":[{"raw_affiliation_string":"Guangxi University,School of Computer and Electronic Information,Nanning,China","institution_ids":["https://openalex.org/I150807315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5053607992"],"corresponding_institution_ids":["https://openalex.org/I150807315"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41741085,"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9635999798774719,"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":0.9635999798774719,"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":0.008999999612569809,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.004999999888241291,"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":0.6146000027656555},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5916000008583069},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4982999861240387},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4927000105381012},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4706000089645386},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.47049999237060547},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4318999946117401},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.4090999960899353},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3806000053882599}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7817000150680542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7092000246047974},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6146000027656555},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5916000008583069},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5239999890327454},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4982999861240387},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4927000105381012},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.47049999237060547},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4318999946117401},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.4090999960899353},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C2986578859","wikidata":"https://www.wikidata.org/wiki/Q657632","display_name":"Human motion","level":3,"score":0.32899999618530273},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C146159030","wikidata":"https://www.wikidata.org/wiki/Q7625099","display_name":"Structure from motion","level":3,"score":0.2809000015258789},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.26030001044273376},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2474702929","https://openalex.org/W2971856312","https://openalex.org/W2982625143","https://openalex.org/W3215615641","https://openalex.org/W4288079574","https://openalex.org/W4289752563","https://openalex.org/W4297981470","https://openalex.org/W4312635677","https://openalex.org/W4312849707","https://openalex.org/W4312936899","https://openalex.org/W4313145975","https://openalex.org/W4375958382","https://openalex.org/W4382457661","https://openalex.org/W4386065848","https://openalex.org/W4386076288","https://openalex.org/W4387963302","https://openalex.org/W4390872247","https://openalex.org/W4390874125","https://openalex.org/W4402754111","https://openalex.org/W4402754184","https://openalex.org/W4404600557","https://openalex.org/W4404914313","https://openalex.org/W4405852735","https://openalex.org/W4408353766"],"related_works":[],"abstract_inverted_index":{"Generating":[0],"natural":[1],"3D":[2,43,109],"human":[3,44],"motions":[4,135,163,189],"that":[5,222],"are":[6,153],"consistent":[7,136],"with":[8,137],"textual":[9],"descriptions":[10],"is":[11],"a":[12],"key":[13],"task":[14],"in":[15,38,147,175,227],"text-to-motion":[16],"generation.":[17],"The":[18],"Transformer-based":[19],"text-conditional":[20],"mask":[21,32],"motion":[22,69,112,129,177,202,236],"generation":[23,200],"model":[24,113,174,184],"relies":[25],"on":[26,215],"the":[27,51,57,63,73,76,81,90,97,118,157,168,173,176,185,199,209,216,235],"multi-head":[28,52,82],"attention":[29,53,83],"mechanism":[30,54,84],"and":[31,41,99,125,131,150,159,179,190,218],"training":[33],"strategy,":[34],"making":[35,239],"significant":[36],"progress":[37],"generating":[39,228],"high-quality":[40,134,229],"high-fidelity":[42],"motions.":[45,103,213,230],"However,":[46],"these":[47],"models":[48],"only":[49],"use":[50],"to":[55,88,121,155,206],"capture":[56,89,122],"long-distance":[58],"dependence":[59],"of":[60,65,68,75,93,101,128,162,172,188,201,211],"features,":[61],"lacking":[62],"modeling":[64],"spatio-temporal":[66,186],"relationship":[67,187],"sequence,":[70,130],"which":[71,95,115,152],"affects":[72,96],"coherence":[74],"generated":[77,102,212],"motion.":[78],"In":[79,231],"addition,":[80,232],"has":[85],"limited":[86],"ability":[87,120,171],"detailed":[91,126,160],"information":[92,161,169],"motions,":[94],"authenticity":[98],"accuracy":[100],"Therefore,":[104],"we":[105,141],"propose":[106],"an":[107],"augmented":[108,144],"generative":[110],"masked":[111],"(AG-Mask),":[114],"significantly":[116],"enhances":[117],"model\u2019s":[119],"spatiotemporal":[123],"feature":[124,127],"effectively":[132],"generates":[133],"text":[138],"descriptions.":[139],"Specifically,":[140],"design":[142],"two":[143],"bidirectional":[145],"transformer":[146],"AG-Mask:":[148],"STM-Transformer":[149,165],"MDR-Transformer,":[151],"used":[154],"process":[156],"basic":[158],"respectively.":[164],"can":[166,183],"boost":[167],"extraction":[170],"channel":[178],"spatial":[180],"dimension.":[181],"MDR-Transformer":[182],"extract":[191],"rich":[192],"multidimensional":[193],"features.":[194],"Their":[195],"combined":[196],"processing":[197],"promotes":[198],"sequence":[203],"from":[204],"coarse":[205],"fine,":[207],"optimizing":[208],"quality":[210],"Experiments":[214],"HumanML3D":[217],"KIT-ML":[219],"datasets":[220],"show":[221],"AG-Mask":[223,233],"achieves":[224],"state-of-the-art":[225],"performance":[226],"refines":[234],"editing":[237],"function,":[238],"it":[240],"more":[241],"flexible":[242],"for":[243],"practical":[244],"applications.":[245]},"counts_by_year":[],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-11-14T00:00:00"}