{"id":"https://openalex.org/W4388623976","doi":"https://doi.org/10.1109/ro-man57019.2023.10309317","title":"Controllable Motion Synthesis and Reconstruction with Autoregressive Diffusion Models","display_name":"Controllable Motion Synthesis and Reconstruction with Autoregressive Diffusion Models","publication_year":2023,"publication_date":"2023-08-28","ids":{"openalex":"https://openalex.org/W4388623976","doi":"https://doi.org/10.1109/ro-man57019.2023.10309317"},"language":"en","primary_location":{"id":"doi:10.1109/ro-man57019.2023.10309317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man57019.2023.10309317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","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/A5101519083","display_name":"Wenjie Yin","orcid":"https://orcid.org/0000-0002-8115-1980"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Wenjie Yin","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Robotics, Perception and Learning,Sweden","Division of Robotics, Perception and Learning, KTH Royal Institute of Technology, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Robotics, Perception and Learning,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Robotics, Perception and Learning, KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053420346","display_name":"Ruibo Tu","orcid":"https://orcid.org/0000-0003-1356-9653"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Ruibo Tu","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Robotics, Perception and Learning,Sweden","Division of Robotics, Perception and Learning, KTH Royal Institute of Technology, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Robotics, Perception and Learning,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Robotics, Perception and Learning, KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067144254","display_name":"Hang Yin","orcid":"https://orcid.org/0000-0002-3599-440X"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Hang Yin","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Robotics, Perception and Learning,Sweden","Division of Robotics, Perception and Learning, KTH Royal Institute of Technology, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Robotics, Perception and Learning,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Robotics, Perception and Learning, KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023792180","display_name":"Danica Kragi\u0107","orcid":"https://orcid.org/0000-0003-2965-2953"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Danica Kragic","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Robotics, Perception and Learning,Sweden","Division of Robotics, Perception and Learning, KTH Royal Institute of Technology, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Robotics, Perception and Learning,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Robotics, Perception and Learning, KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021003965","display_name":"Hedvig Kjellstr\u00f6m","orcid":"https://orcid.org/0000-0002-5750-9655"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Hedvig Kjellstr\u00f6m","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Robotics, Perception and Learning,Sweden","Division of Robotics, Perception and Learning, KTH Royal Institute of Technology, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Robotics, Perception and Learning,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Robotics, Perception and Learning, KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082269387","display_name":"M\u00e5rten Bj\u00f6rkman","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"M\u00e5rten Bj\u00f6rkman","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Robotics, Perception and Learning,Sweden","Division of Robotics, Perception and Learning, KTH Royal Institute of Technology, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Robotics, Perception and Learning,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Robotics, Perception and Learning, KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":0.3641,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.67640924,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1102","last_page":"1108"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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/T12290","display_name":"Human Motion and Animation","score":0.9998999834060669,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9940999746322632,"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/computer-science","display_name":"Computer science","score":0.7115229368209839},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.6841418147087097},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5718919634819031},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.570041298866272},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.5215306282043457},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4955404996871948},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.43755242228507996},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.43560582399368286},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.43537983298301697},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4346696138381958},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.4228118360042572},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4218374490737915},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.41227179765701294},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.3812265396118164},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.360609769821167},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34694480895996094},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14688873291015625},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1305265724658966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7115229368209839},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6841418147087097},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5718919634819031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.570041298866272},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.5215306282043457},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4955404996871948},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.43755242228507996},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.43560582399368286},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.43537983298301697},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4346696138381958},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.4228118360042572},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4218374490737915},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.41227179765701294},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3812265396118164},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.360609769821167},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34694480895996094},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14688873291015625},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1305265724658966},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ro-man57019.2023.10309317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man57019.2023.10309317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320337495","display_name":"Technology Development","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1735317348","https://openalex.org/W2004167999","https://openalex.org/W2594167370","https://openalex.org/W2747308422","https://openalex.org/W2759921250","https://openalex.org/W2801493797","https://openalex.org/W2802441648","https://openalex.org/W2945629925","https://openalex.org/W2959300817","https://openalex.org/W2963223306","https://openalex.org/W2963389355","https://openalex.org/W2964203186","https://openalex.org/W2971625077","https://openalex.org/W3036167779","https://openalex.org/W3107914916","https://openalex.org/W3196079725","https://openalex.org/W3204221554","https://openalex.org/W4200526174","https://openalex.org/W4283372749","https://openalex.org/W4294621855","https://openalex.org/W4298186886","https://openalex.org/W4312305613","https://openalex.org/W4319301023","https://openalex.org/W4377010269","https://openalex.org/W4386065807","https://openalex.org/W4390873610","https://openalex.org/W4391305822","https://openalex.org/W6688384872","https://openalex.org/W6713700718","https://openalex.org/W6748307345","https://openalex.org/W6765775151","https://openalex.org/W6779823529","https://openalex.org/W6788328477","https://openalex.org/W6791353385","https://openalex.org/W6841752625","https://openalex.org/W6844223692"],"related_works":["https://openalex.org/W3082178636","https://openalex.org/W2374250903","https://openalex.org/W1521968289","https://openalex.org/W2782041652","https://openalex.org/W2952088488","https://openalex.org/W2612657834","https://openalex.org/W3109499659","https://openalex.org/W4382315317","https://openalex.org/W2966641257","https://openalex.org/W3186268266"],"abstract_inverted_index":{"Data-driven":[0],"and":[1,6,18,33,64,78,100,121,132],"controllable":[2,111],"human":[3],"motion":[4,48,77,112,136],"synthesis":[5,113,131],"prediction":[7],"are":[8,69],"active":[9],"research":[10],"areas":[11],"with":[12,35,116],"various":[13],"applications":[14],"in":[15,23,72,76,110],"interactive":[16],"media":[17],"social":[19],"robotics.":[20],"Challenges":[21],"remain":[22],"these":[24],"fields":[25],"for":[26,114,129],"generating":[27],"diverse":[28],"motions":[29],"given":[30],"past":[31],"observations":[32],"dealing":[34],"imperfect":[36],"poses.":[37],"This":[38],"paper":[39],"introduces":[40],"MoDiff,":[41],"an":[42],"autoregressive":[43],"probabilistic":[44],"diffusion":[45,92,126],"model":[46,58],"over":[47],"sequences":[49],"conditioned":[50],"on":[51,90],"control":[52,79],"contexts":[53],"of":[54,108,125,134],"other":[55],"modalities.":[56,80],"Our":[57],"integrates":[59],"a":[60,65,84],"cross-modal":[61],"Transformer":[62],"encoder":[63],"Transformer-based":[66],"decoder,":[67],"which":[68],"found":[70],"effective":[71],"capturing":[73],"temporal":[74],"correlations":[75],"We":[81,103],"also":[82],"introduce":[83],"new":[85],"data":[86,98,127],"dropout":[87,128],"method":[88],"based":[89],"the":[91,105,123],"forward":[93],"process":[94],"to":[95,118,138],"provide":[96],"richer":[97],"representations":[99],"robust":[101,130],"generation.":[102],"demonstrate":[104],"superior":[106],"performance":[107],"MoDiff":[109],"locomotion":[115],"respect":[117],"two":[119],"baselines":[120],"show":[122],"benefits":[124],"reconstruction":[133],"high-fidelity":[135],"close":[137],"recorded":[139],"data.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}