{"id":"https://openalex.org/W7159819641","doi":"https://doi.org/10.1109/tvcg.2026.3689798","title":"HiTMM: Generative Temporal Masked Modeling of Human Interactive Motions","display_name":"HiTMM: Generative Temporal Masked Modeling of Human Interactive Motions","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7159819641","doi":"https://doi.org/10.1109/tvcg.2026.3689798","pmid":"https://pubmed.ncbi.nlm.nih.gov/42065975"},"language":"en","primary_location":{"id":"doi:10.1109/tvcg.2026.3689798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2026.3689798","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100585454","display_name":"Zicheng Jiao","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zicheng Jiao","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135038750","display_name":"Yunlian Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunlian Sun","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-4696-8848","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135039372","display_name":"Hongwen Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongwen Zhang","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Normal University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8633-4551","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Normal University, Beijing, China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135019123","display_name":"Jinhui Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I167027274","display_name":"Nanjing Forestry University","ror":"https://ror.org/03m96p165","country_code":"CN","type":"education","lineage":["https://openalex.org/I167027274"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhui Tang","raw_affiliation_strings":["School of Artificial Intelligence, Nanjing Forestry University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9008-222X","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Nanjing Forestry University, Nanjing, China","institution_ids":["https://openalex.org/I167027274"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064744996","display_name":"M\u00e1ssimo Tistarelli","orcid":"https://orcid.org/0000-0002-3406-3048"},"institutions":[{"id":"https://openalex.org/I159650629","display_name":"University of Sassari","ror":"https://ror.org/01bnjbv91","country_code":"IT","type":"education","lineage":["https://openalex.org/I159650629"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Massimo Tistarelli","raw_affiliation_strings":["Department of Engineering, University of Sassari, Sassari, Italy"],"raw_orcid":"https://orcid.org/0000-0002-3406-3048","affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Sassari, Sassari, Italy","institution_ids":["https://openalex.org/I159650629"]}]}],"institutions":[],"countries_distinct_count":2,"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":0.47910456,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"7","first_page":"6857","last_page":"6870"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.8342000246047974,"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":0.8342000246047974,"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":0.0575999990105629,"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":0.032099999487400055,"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/transformer","display_name":"Transformer","score":0.5501999855041504},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5209000110626221},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5145999789237976},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.508899986743927},{"id":"https://openalex.org/keywords/timeline","display_name":"Timeline","score":0.4417000114917755},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.3628999888896942},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.3474999964237213},{"id":"https://openalex.org/keywords/human-motion","display_name":"Human motion","score":0.34459999203681946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7565000057220459},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5501999855041504},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5209000110626221},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5145999789237976},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.508899986743927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4968000054359436},{"id":"https://openalex.org/C4438859","wikidata":"https://www.wikidata.org/wiki/Q186117","display_name":"Timeline","level":2,"score":0.4417000114917755},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3628999888896942},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C2986578859","wikidata":"https://www.wikidata.org/wiki/Q657632","display_name":"Human motion","level":3,"score":0.34459999203681946},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C2987082051","wikidata":"https://www.wikidata.org/wiki/Q223642","display_name":"Human interaction","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.30550000071525574},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C130187892","wikidata":"https://www.wikidata.org/wiki/Q133327","display_name":"Spacetime","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C2780806968","wikidata":"https://www.wikidata.org/wiki/Q6045196","display_name":"Interaction model","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C90738871","wikidata":"https://www.wikidata.org/wiki/Q41642869","display_name":"Configuration space","level":2,"score":0.25679999589920044}],"mesh":[{"descriptor_ui":"D000098842","descriptor_name":"Generative Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009068","descriptor_name":"Movement","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tvcg.2026.3689798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2026.3689798","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},{"id":"pmid:42065975","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42065975","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on visualization and computer graphics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5320035815238953}],"awards":[{"id":"https://openalex.org/G2693452441","display_name":null,"funder_award_id":"62476131","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4030041069","display_name":null,"funder_award_id":"62377004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,134],"have":[1],"recently":[2],"seen":[3],"some":[4],"progress":[5],"in":[6,71,192],"the":[7,45,58,66,97,108,112,140,160,167,180,185,193,196,201,238,242,256],"current":[8,243],"field":[9],"of":[10,60,139,215,235,253],"human-human":[11],"interaction":[12,87,99,109,224],"generation.":[13],"However,":[14],"directly":[15],"generating":[16,34],"complex":[17],"two-person":[18],"interactive":[19,37],"motions":[20,35,49,106],"remains":[21],"a":[22,82,121,126,145,151,155,176,208],"significant":[23],"challenge.":[24],"Meanwhile,":[25],"these":[26],"models":[27],"typically":[28],"employ":[29,150],"two":[30,40,101,141],"independent":[31],"timelines":[32],"when":[33],"for":[36,57,85,248,261],"scenarios":[38],"involving":[39],"individuals.":[41],"This":[42],"design":[43],"overlooks":[44],"temporal":[46,186,210,217],"dependencies":[47],"between":[48],"at":[50],"each":[51],"timestep":[52],"and":[53,62,73,154,162,169,188,250],"fails":[54],"to":[55,111,117,120,158,182],"account":[56],"roles":[59],"active":[61],"reactive":[63],"participants":[64],"during":[65],"generation":[67,88],"process,":[68],"often":[69],"resulting":[70],"unrealistic":[72],"unnatural":[74],"motions.":[75,104],"In":[76],"this":[77],"work,":[78],"we":[79,149],"propose":[80],"HiTMM,":[81],"novel":[83],"framework":[84],"Human":[86],"based":[89],"on":[90,219,237,255],"Temporal":[91],"Masked":[92],"Modeling.":[93],"HiTMM":[94],"first":[95,197],"decomposes":[96],"human":[98,223],"into":[100],"separate":[102],"single-person":[103],"Individual":[105],"within":[107,222],"belong":[110],"same":[113],"type,":[114],"enabling":[115],"them":[116],"be":[118],"mapped":[119],"shared":[122,146,209],"latent":[123],"space":[124],"through":[125],"coarse-to-fine":[127],"approach":[128],"that":[129,229],"produces":[130],"multi-layer":[131],"discrete":[132],"tokens.":[133,165],"then":[135],"arrange":[136],"all":[137],"tokens":[138,172],"interacting":[142],"individuals":[143],"along":[144,175],"timeline.":[147],"Subsequently,":[148],"masked":[152],"transformer":[153,157],"residual":[156],"model":[159,181,206,231,245],"base-layer":[161,168],"rest-layer":[163,170],"motion":[164,171,199],"Both":[166],"are":[173],"arranged":[174],"single":[177],"timeline,":[178],"allowing":[179],"explicitly":[183],"capture":[184],"order":[187],"initiating":[189],"role":[190],"embedded":[191],"sequence,":[194],"where":[195],"individual's":[198],"initiates":[200],"interaction.":[202],"Note":[203],"that,":[204],"our":[205,230],"utilizes":[207],"representation,":[211],"making":[212],"it":[213],"capable":[214],"performing":[216],"editing":[218],"specific":[220],"regions":[221],"sequences.":[225],"Experimental":[226],"results":[227],"show":[228],"achieves":[232],"an":[233,251],"FID":[234,252],"5.017":[236],"InterHuman":[239],"dataset,":[240],"surpassing":[241],"state-of-the-art":[244],"(vs":[246,259],"5.154":[247],"InterMask),":[249],"0.373":[254],"InterX":[257],"dataset":[258],"0.399":[260],"InterMask).":[262]},"counts_by_year":[],"updated_date":"2026-06-24T06:17:17.354583","created_date":"2026-05-03T00:00:00"}