{"id":"https://openalex.org/W4417160817","doi":"https://doi.org/10.1109/iccv51701.2025.01182","title":"Primal: Physically Reactive and Interactive Motor Model for Avatar Learning","display_name":"Primal: Physically Reactive and Interactive Motor Model for Avatar Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417160817","doi":"https://doi.org/10.1109/iccv51701.2025.01182"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01182","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.17544","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100456311","display_name":"Yan Zhang","orcid":"https://orcid.org/0000-0002-7904-0982"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yan Zhang","raw_affiliation_strings":["Meshcapade"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meshcapade","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102813327","display_name":"Yao Feng","orcid":"https://orcid.org/0000-0002-9481-9783"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao Feng","raw_affiliation_strings":["Meshcapade"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meshcapade","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053473303","display_name":"Alp\u00e1r Cseke","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alpar Cseke","raw_affiliation_strings":["Meshcapade"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meshcapade","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055739174","display_name":"Nitin Saini","orcid":"https://orcid.org/0000-0001-6434-8899"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nitin Saini","raw_affiliation_strings":["Meshcapade"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meshcapade","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120732396","display_name":"Nathan Bajandas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nathan Bajandas","raw_affiliation_strings":["Meshcapade"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meshcapade","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120732397","display_name":"Nicolas Heron","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicolas Heron","raw_affiliation_strings":["Meshcapade"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meshcapade","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065396778","display_name":"Michael J. Black","orcid":"https://orcid.org/0000-0001-6077-4540"},"institutions":[{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael J. Black","raw_affiliation_strings":["Max Planck Institute for Intelligent Systems,Tübingen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Intelligent Systems,Tübingen","institution_ids":["https://openalex.org/I4210135521"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100456311"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45185395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12725","last_page":"12736"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.8740000128746033,"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":0.8740000128746033,"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":0.0738999992609024,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.01769999973475933,"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/avatar","display_name":"Avatar","score":0.6797999739646912},{"id":"https://openalex.org/keywords/character-animation","display_name":"Character animation","score":0.6326000094413757},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.6212000250816345},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5794000029563904},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.487199991941452},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.44510000944137573},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4332999885082245},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4219000041484833},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4075999855995178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7454000115394592},{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.6797999739646912},{"id":"https://openalex.org/C90697248","wikidata":"https://www.wikidata.org/wiki/Q1062896","display_name":"Character animation","level":4,"score":0.6326000094413757},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.6212000250816345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5857999920845032},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5794000029563904},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.487199991941452},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4772000014781952},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.44510000944137573},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4332999885082245},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4219000041484833},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4075999855995178},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4065999984741211},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.3472000062465668},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C2986578859","wikidata":"https://www.wikidata.org/wiki/Q657632","display_name":"Human motion","level":3,"score":0.3034999966621399},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.30070000886917114},{"id":"https://openalex.org/C150303390","wikidata":"https://www.wikidata.org/wiki/Q1983852","display_name":"Virtual actor","level":3,"score":0.3003000020980835},{"id":"https://openalex.org/C111151474","wikidata":"https://www.wikidata.org/wiki/Q1653368","display_name":"iCub","level":4,"score":0.2939999997615814},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C2776716048","wikidata":"https://www.wikidata.org/wiki/Q6045290","display_name":"Interactive Learning","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27889999747276306},{"id":"https://openalex.org/C107524782","wikidata":"https://www.wikidata.org/wiki/Q40164","display_name":"Lever","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C2780575108","wikidata":"https://www.wikidata.org/wiki/Q7316652","display_name":"Retargeting","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C189645446","wikidata":"https://www.wikidata.org/wiki/Q350865","display_name":"Mirroring","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.26030001044273376},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.250900000333786}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01182","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.17544","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.17544","pdf_url":"https://arxiv.org/pdf/2503.17544","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},{"id":"doi:10.48550/arxiv.2503.17544","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.17544","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.17544","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.17544","pdf_url":"https://arxiv.org/pdf/2503.17544","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,176],"formulate":[1],"the":[2,17,44,70,73,111,125,137,148,178],"motor":[3],"system":[4,186],"of":[5,48,82],"an":[6],"interactive":[7],"avatar":[8,126],"as":[9,158],"a":[10,25,66,79,87,105,142,182],"generative":[11,88],"motion":[12,34,84],"model":[13,74,113,150,179],"that":[14,169,190],"can":[15],"drive":[16],"body":[18,76],"to":[19,127,130,146,154,180],"move":[20],"through":[21],"3D":[22],"space":[23],"in":[24,56,133,187],"perpetual,":[26],"realistic,":[27,118],"controllable,":[28],"and":[29,46,119,163,194,198],"responsive":[30,129,193],"manner.":[31],"Although":[32],"human":[33,50],"generation":[35,162],"has":[36],"been":[37],"extensively":[38],"studied,":[39],"many":[40],"existing":[41],"methods":[42],"lack":[43],"responsiveness":[45],"realism":[47],"real":[49,134],"movements.":[51],"Inspired":[52],"by":[53],"recent":[54],"advances":[55],"foundation":[57,89],"models,":[58,197],"we":[59,140],"propose":[60],"PRIMAL,":[61],"which":[62,91],"is":[63,99],"learned":[64],"with":[65],"two-stage":[67],"paradigm.":[68],"In":[69,136],"pretraining":[71],"stage,":[72],"learns":[75],"movements":[77],"from":[78,90],"large":[80],"number":[81],"sub-second":[83],"segments,":[85],"providing":[86],"more":[92,199],"complex":[93],"motions":[94],"are":[95,201],"built.":[96],"This":[97],"training":[98],"fully":[100],"unsupervised":[101],"without":[102],"annotations.":[103],"Given":[104],"single-frame":[106],"initial":[107],"state":[108],"during":[109],"inference,":[110],"pretrained":[112],"not":[114],"only":[115],"generates":[116],"unbounded,":[117],"controllable":[120],"motion,":[121],"but":[122],"also":[123],"enables":[124],"be":[128],"induced":[131],"impulses":[132],"time.":[135],"adaptation":[138],"phase,":[139],"employ":[141],"novel":[143],"ControlNet-like":[144],"adaptor":[145],"fine-tune":[147],"base":[149],"efficiently,":[151],"adapting":[152],"it":[153],"new":[155],"tasks":[156],"such":[157],"few-shot":[159],"personalized":[160],"action":[161],"spatial":[164],"target":[165],"reaching.":[166],"Evaluations":[167],"show":[168],"our":[170],"proposed":[171],"method":[172],"outperforms":[173],"state-of-the-art":[174],"baselines.":[175],"leverage":[177],"create":[181],"real-time":[183],"character":[184],"animation":[185],"Unreal":[188],"Engine":[189],"feels":[191],"highly":[192],"natural.":[195],"Code,":[196],"results":[200],"available":[202],"at:":[203],"https://yz-cnsdqz.github.io/eigenmotion/PRIMAL":[204]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}