{"id":"https://openalex.org/W4415707943","doi":"https://doi.org/10.1109/icme59968.2025.11209361","title":"Efficient Text-to-Motion via Multi-Head Generative Masked Modeling","display_name":"Efficient Text-to-Motion via Multi-Head Generative Masked Modeling","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707943","doi":"https://doi.org/10.1109/icme59968.2025.11209361"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209361","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5100338797","display_name":"Heng Li","orcid":"https://orcid.org/0000-0002-2196-6520"},"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":"Heng Li","raw_affiliation_strings":["Sun Yat-Sen University,School of Computer Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University,School of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120192671","display_name":"Xing Liufu","orcid":null},"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":"Xing Liufu","raw_affiliation_strings":["Sun Yat-Sen University,School of Computer Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University,School of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaotong Lin","orcid":null},"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":"Xiaotong Lin","raw_affiliation_strings":["Sun Yat-Sen University,School of Computer Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University,School of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088444199","display_name":"Jian Zhu","orcid":"https://orcid.org/0000-0002-2551-2024"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Zhu","raw_affiliation_strings":["Guangdong University of Technology,School of Computer Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,School of Computer Science and Technology,China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102648233","display_name":"Jian-Fang Hu","orcid":"https://orcid.org/0009-0003-4799-8525"},"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":"Jian-Fang Hu","raw_affiliation_strings":["Sun Yat-Sen University,School of Computer Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University,School of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I157773358"]}]}],"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":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.6761000156402588,"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":0.6761000156402588,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.13689999282360077,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.05550000071525574,"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/autoencoder","display_name":"Autoencoder","score":0.7246000170707703},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.6366999745368958},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6366999745368958},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.619700014591217},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.6173999905586243},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5049999952316284},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4316999912261963}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7246000170707703},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6751999855041504},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6366999745368958},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6366999745368958},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.619700014591217},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6173999905586243},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5073999762535095},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5049999952316284},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4316999912261963},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3887999951839447},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3817000091075897},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C13336665","wikidata":"https://www.wikidata.org/wiki/Q125977","display_name":"Vector space","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C2779020251","wikidata":"https://www.wikidata.org/wiki/Q3555171","display_name":"Motion vector","level":3,"score":0.29989999532699585},{"id":"https://openalex.org/C2988416141","wikidata":"https://www.wikidata.org/wiki/Q6031139","display_name":"Information loss","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209361","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/W2982625143","https://openalex.org/W3144253442","https://openalex.org/W3215615641","https://openalex.org/W4205260486","https://openalex.org/W4297981470","https://openalex.org/W4312635677","https://openalex.org/W4312936899","https://openalex.org/W4312974539","https://openalex.org/W4312995056","https://openalex.org/W4313021454","https://openalex.org/W4386065848","https://openalex.org/W4386071584","https://openalex.org/W4386076288","https://openalex.org/W4386253639","https://openalex.org/W4390871712","https://openalex.org/W4390872247","https://openalex.org/W4390873580","https://openalex.org/W4390874627","https://openalex.org/W4391305822","https://openalex.org/W4402754111","https://openalex.org/W4402754184","https://openalex.org/W4404600557","https://openalex.org/W4413147141"],"related_works":[],"abstract_inverted_index":{"Text-to-motion":[0],"generation":[1],"has":[2],"attracted":[3],"increasing":[4],"attention":[5],"in":[6],"recent":[7],"years.":[8],"Existing":[9],"methods":[10],"primarily":[11],"employ":[12],"Vector":[13],"Quantized":[14],"Variational":[15],"AutoEncoder":[16],"(VQ-VAE)":[17],"as":[18],"the":[19,29,56,65,107,116],"tokenizer":[20],"for":[21,87],"motion":[22,60,90,108],"representation.":[23],"However,":[24],"such":[25],"vector":[26],"quantization":[27,86],"maps":[28],"continuous":[30],"space":[31,110],"into":[32,85],"limited":[33],"discrete":[34,59],"tokens,":[35],"which":[36,80],"inevitably":[37],"leads":[38],"to":[39,54],"significant":[40],"information":[41,66],"loss.":[42],"To":[43],"address":[44],"this":[45,105],"limitation,":[46],"we":[47,73],"propose":[48],"a":[49,75,88,101],"simple":[50],"yet":[51],"effective":[52],"approach":[53],"expand":[55],"capacity":[57],"of":[58,118],"representation":[61,109],"space,":[62],"effectively":[63],"reducing":[64],"loss":[67],"without":[68],"incurring":[69],"additional":[70],"overhead.":[71,123],"Specifically,":[72],"present":[74],"Multi-Head":[76],"Generative":[77],"Masked":[78],"model":[79],"a)":[81],"exploits":[82],"multi-head":[83],"mechanism":[84],"high-fidelity":[89],"tokenizer,":[91],"and":[92,121,136],"b)":[93],"simultaneously":[94],"generates":[95],"tokens":[96],"across":[97],"different":[98],"heads":[99],"using":[100],"bi-directional":[102],"transformer.":[103],"In":[104],"way,":[106],"can":[111],"be":[112],"expanded":[113],"exponentially":[114],"at":[115],"cost":[117],"negligible":[119],"time":[120],"parameter":[122],"Extensive":[124],"experiments":[125],"demonstrate":[126],"that":[127],"our":[128],"method":[129],"achieves":[130],"state-of-the-art":[131],"performance":[132],"on":[133],"both":[134],"HumanML3D":[135],"KIT-ML":[137],"datasets.":[138]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}