{"id":"https://openalex.org/W4415541064","doi":"https://doi.org/10.1145/3746027.3754748","title":"Towards Robust and Controllable Text-to-Motion via Masked Autoregressive Diffusion","display_name":"Towards Robust and Controllable Text-to-Motion via Masked Autoregressive Diffusion","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415541064","doi":"https://doi.org/10.1145/3746027.3754748"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3754748","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754748","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.11013","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zongye Zhang","orcid":"https://orcid.org/0009-0002-8149-0533"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongye Zhang","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-8149-0533","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bohan Kong","orcid":"https://orcid.org/0009-0006-3813-0427"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bohan Kong","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-3813-0427","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056847110","display_name":"Qingjie Liu","orcid":"https://orcid.org/0000-0002-5181-6451"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingjie Liu","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China and Hangzhou Innovation Institute, Beihang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-5181-6451","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China and Hangzhou Innovation Institute, Beihang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100398953","display_name":"Yunhong Wang","orcid":"https://orcid.org/0000-0001-8001-2703"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhong Wang","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China and Hangzhou Innovation Institute, Beihang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0001-8001-2703","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China and Hangzhou Innovation Institute, Beihang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.3441744,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9326","last_page":"9335"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9994999766349792,"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":0.9994999766349792,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9957000017166138,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.7085000276565552},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6891999840736389},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.545199990272522},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5199999809265137},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.421099990606308},{"id":"https://openalex.org/keywords/human-motion","display_name":"Human motion","score":0.41679999232292175},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.3743000030517578},{"id":"https://openalex.org/keywords/motion-control","display_name":"Motion control","score":0.3716000020503998}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7602999806404114},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.7085000276565552},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6891999840736389},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.545199990272522},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5199999809265137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5138000249862671},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.421099990606308},{"id":"https://openalex.org/C2986578859","wikidata":"https://www.wikidata.org/wiki/Q657632","display_name":"Human motion","level":3,"score":0.41679999232292175},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.3743000030517578},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.3716000020503998},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37040001153945923},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3538999855518341},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3319999873638153},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32519999146461487},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.3021000027656555},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.25200000405311584},{"id":"https://openalex.org/C2780624872","wikidata":"https://www.wikidata.org/wiki/Q852453","display_name":"Motion detection","level":3,"score":0.2513999938964844},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3754748","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754748","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.11013","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.11013","pdf_url":"https://arxiv.org/pdf/2505.11013","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.11013","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.11013","pdf_url":"https://arxiv.org/pdf/2505.11013","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2474702929","https://openalex.org/W4386076288","https://openalex.org/W4387969168","https://openalex.org/W4403791248"],"related_works":[],"abstract_inverted_index":{"Generating":[0],"3D":[1],"human":[2,17],"motion":[3,83,96,118,133,154],"from":[4],"text":[5],"descriptions":[6],"remains":[7],"challenging":[8],"due":[9],"to":[10,44,56,94],"the":[11,24],"diverse":[12],"and":[13,114,141,158],"complex":[14],"nature":[15],"of":[16,117],"motion.":[18],"While":[19],"existing":[20],"methods":[21,41,63],"excel":[22],"within":[23],"training":[25],"distribution,":[26],"they":[27],"often":[28,42,68],"struggle":[29],"with":[30,91,129],"out-of-distribution":[31],"motions,":[32],"limiting":[33],"their":[34,54],"applicability":[35],"in":[36,153],"real-world":[37],"scenarios.":[38],"Existing":[39],"VQVAE-based":[40],"fail":[43],"represent":[45],"novel":[46,126],"motions":[47],"faithfully":[48],"using":[49,97],"discrete":[50],"tokens,":[51],"which":[52,87],"hampers":[53],"ability":[55],"generalize":[57],"beyond":[58],"seen":[59],"data.":[60],"Meanwhile,":[61],"diffusion-based":[62],"operating":[64],"on":[65,125,137],"continuous":[66,99],"representations":[67],"lack":[69],"fine-grained":[70],"control":[71,110],"over":[72,111],"individual":[73],"frames.":[74],"To":[75],"address":[76],"these":[77],"challenges,":[78],"we":[79],"propose":[80],"a":[81],"robust":[82],"generation":[84],"framework":[85],"MoMADiff,":[86],"combines":[88],"masked":[89],"modeling":[90],"diffusion":[92],"processes":[93],"generate":[95],"frame-level":[98],"representations.":[100],"Our":[101],"model":[102],"supports":[103],"flexible":[104],"user-provided":[105],"keyframe":[106,159],"specification,":[107],"enabling":[108],"precise":[109],"both":[112],"spatial":[113],"temporal":[115],"aspects":[116],"synthesis.":[119],"MoMADiff":[120],"demonstrates":[121],"strong":[122],"generalization":[123],"capability":[124],"text-to-motion":[127],"datasets":[128,140],"sparse":[130],"keyframes":[131],"as":[132],"prompts.":[134],"Extensive":[135],"experiments":[136],"two":[138,142],"held-out":[139],"standard":[143],"benchmarks":[144],"show":[145],"that":[146],"our":[147],"method":[148],"consistently":[149],"outperforms":[150],"state-of-the-art":[151],"models":[152],"quality,":[155],"instruction":[156],"fidelity,":[157],"adherence.":[160],"The":[161],"code":[162],"is":[163],"available":[164],"at:":[165],"https://github.com/zzysteve/MoMADiff":[166]},"counts_by_year":[],"updated_date":"2026-06-14T07:44:22.658603","created_date":"2025-10-10T00:00:00"}