{"id":"https://openalex.org/W7139127545","doi":"https://doi.org/10.1109/tvcg.2026.3675725","title":"CoShMDM: Contact and Shape-Aware Latent Motion Diffusion Model for Human Interaction Generation","display_name":"CoShMDM: Contact and Shape-Aware Latent Motion Diffusion Model for Human Interaction Generation","publication_year":2026,"publication_date":"2026-03-19","ids":{"openalex":"https://openalex.org/W7139127545","doi":"https://doi.org/10.1109/tvcg.2026.3675725","pmid":"https://pubmed.ncbi.nlm.nih.gov/41855059"},"language":"en","primary_location":{"id":"doi:10.1109/tvcg.2026.3675725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2026.3675725","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/A5055938204","display_name":"Ali Asghar Manjotho","orcid":"https://orcid.org/0000-0003-1972-3746"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ali Asghar Manjotho","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1972-3746","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095369533","display_name":"Tekie Tsegay Tewolde","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tekie Tsegay Tewolde","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2128-4666","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075578637","display_name":"Ramadhani Ally Duma","orcid":"https://orcid.org/0000-0002-9195-4920"},"institutions":[{"id":"https://openalex.org/I28285804","display_name":"The University of Dodoma","ror":"https://ror.org/009n8zh45","country_code":"TZ","type":"education","lineage":["https://openalex.org/I28285804"]}],"countries":["TZ"],"is_corresponding":false,"raw_author_name":"Ramadhani Ally Duma","raw_affiliation_strings":["College of Informatics and Virtual Education, University of Dodoma, Dodoma, Tanzania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Informatics and Virtual Education, University of Dodoma, Dodoma, Tanzania","institution_ids":["https://openalex.org/I28285804"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130095388","display_name":"Zhendong Niu","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhendong Niu","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0576-7572","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.29095798,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"7","first_page":"5911","last_page":"5924"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.8409000039100647,"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":0.8409000039100647,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.05570000037550926,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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":0.0502999983727932,"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/polygon-mesh","display_name":"Polygon mesh","score":0.6967999935150146},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5996999740600586},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5297999978065491},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.44029998779296875},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.4163999855518341},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.39399999380111694},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.37790000438690186},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.3716000020503998}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7271999716758728},{"id":"https://openalex.org/C31487907","wikidata":"https://www.wikidata.org/wiki/Q1154597","display_name":"Polygon mesh","level":2,"score":0.6967999935150146},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5996999740600586},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5297999978065491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47440001368522644},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.44029998779296875},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.4163999855518341},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.39399999380111694},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.37790000438690186},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3716000020503998},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3637999892234802},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3637000024318695},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C181145010","wikidata":"https://www.wikidata.org/wiki/Q4418033","display_name":"Mesh generation","level":3,"score":0.325300008058548},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C145980571","wikidata":"https://www.wikidata.org/wiki/Q192788","display_name":"Rigid body","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C2777036941","wikidata":"https://www.wikidata.org/wiki/Q6917771","display_name":"Motion analysis","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C152086174","wikidata":"https://www.wikidata.org/wiki/Q3030571","display_name":"Haptic technology","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C81302111","wikidata":"https://www.wikidata.org/wiki/Q2916417","display_name":"Contact force","level":2,"score":0.2508000135421753}],"mesh":[{"descriptor_ui":"D000098408","descriptor_name":"Reinforcement Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098408","descriptor_name":"Reinforcement Machine Learning","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":"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":"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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D009038","descriptor_name":"Motion","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009038","descriptor_name":"Motion","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tvcg.2026.3675725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2026.3675725","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:41855059","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41855059","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":0.5883628726005554}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generating":[0],"realistic":[1,78],"two-person":[2,79],"interaction":[3,57],"motions":[4],"from":[5,81],"text":[6],"holds":[7],"immense":[8],"potential":[9],"in":[10,170,224,232],"computer":[11],"vision":[12],"and":[13,23,34,55,67,72,93,115,148,164,173,181,189,202,217,221,227,229],"animations.":[14],"While":[15],"existing":[16],"latent":[17,69,160],"motion":[18,49,70,89,163,190],"diffusion":[19,73,175,195],"models":[20],"offer":[21],"compact":[22],"efficient":[24],"representations,":[25],"they":[26],"often":[27],"fail":[28],"to":[29,38,100,140,157],"produce":[30],"physically":[31],"plausible":[32],"contacts":[33],"are":[35,167],"typically":[36],"constrained":[37],"a":[39,45,65,94,125,154,171,186],"single":[40],"canonical":[41],"body":[42,122],"shape.":[43],"As":[44],"result,":[46],"the":[47,194,200],"generated":[48],"sequences":[50],"exhibit":[51],"substantial":[52],"mesh":[53,97,128,142,225],"penetrations":[54,143],"lack":[56],"realism.":[58],"To":[59,105,177],"address":[60],"these":[61],"limitations,":[62],"we":[63,110,184],"propose":[64],"contact":[66,98,118,146,188,233],"shape-aware":[68,149],"representation":[71],"model":[74],"(CoShMDM)":[75],"for":[76,107,162],"generating":[77],"interactions":[80],"text.":[82],"Our":[83],"framework":[84],"begins":[85],"by":[86,134],"constructing":[87],"contact-compatible":[88],"using":[90],"SMPL-based":[91],"meshes":[92],"normal":[95],"alignment-based":[96],"matrix":[99],"capture":[101],"fine-grained":[102],"mesh-level":[103],"contacts.":[104],"account":[106],"shape":[108,113],"diversity,":[109],"incorporate":[111],"SMPL":[112],"parameters":[114],"iteratively":[116],"learn":[117,158],"dynamics":[119],"across":[120],"different":[121],"shapes.":[123],"Additionally,":[124],"reinforcement":[126],"learning-based":[127],"penetration":[129],"avoidance":[130],"policy":[131],"network,":[132],"guided":[133],"signed":[135],"distance":[136],"fields,":[137],"is":[138],"introduced":[139],"minimize":[141],"while":[144],"preserving":[145],"fidelity":[147],"motion.":[150],"We":[151],"further":[152],"employ":[153],"dual-encoder":[155],"VQ-VAE":[156],"disentangled":[159],"representations":[161],"contacts,":[165],"which":[166],"then":[168],"utilized":[169],"text-":[172],"body-shape-conditioned":[174],"model.":[176],"ensure":[178],"spatial,":[179],"temporal,":[180],"semantic":[182],"coherence,":[183],"integrate":[185],"novel":[187],"consistency":[191],"module":[192],"into":[193],"transformer.":[196],"Extensive":[197],"evaluations":[198],"on":[199],"InterHuman":[201],"InterX":[203],"datasets":[204],"demonstrate":[205],"that":[206],"our":[207],"method":[208],"outperforms":[209],"state-of-the-art":[210],"approaches":[211],"achieving":[212],"lowest":[213],"FID":[214],"scores":[215],"(4.801":[216],"0.013),":[218],"with":[219],"19%":[220],"17.3%":[222],"reductions":[223],"penetrations,":[226],"17.8%":[228],"33.2%":[230],"gains":[231],"similarity,":[234],"respectively.":[235]},"counts_by_year":[],"updated_date":"2026-06-24T06:17:17.354583","created_date":"2026-03-20T00:00:00"}
