{"id":"https://openalex.org/W4416399818","doi":"https://doi.org/10.1109/wacv61042.2026.00153","title":"MMHOI: Modeling Complex 3D Multi-Human Multi-Object Interactions","display_name":"MMHOI: Modeling Complex 3D Multi-Human Multi-Object Interactions","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4416399818","doi":"https://doi.org/10.1109/wacv61042.2026.00153"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00153","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.07828","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047279383","display_name":"Kaen Kogashi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kaen Kogashi","raw_affiliation_strings":["Mitsubishi Electric,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric,Japan","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024613828","display_name":"Anoop Cherian","orcid":"https://orcid.org/0000-0002-5566-0351"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anoop Cherian","raw_affiliation_strings":["Mitsubishi Electric Research Labs,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Labs,United States","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120366046","display_name":"Meng-Yu Jennifer Kuo","orcid":null},"institutions":[{"id":"https://openalex.org/I98885092","display_name":"Nara Women's University","ror":"https://ror.org/05kzadn81","country_code":"JP","type":"education","lineage":["https://openalex.org/I98885092"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Meng-Yu Jennifer Kuo","raw_affiliation_strings":["Nara Women’s University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Women’s University,Japan","institution_ids":["https://openalex.org/I98885092"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1512","last_page":"1521"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.8758999705314636,"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":0.8758999705314636,"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":0.06870000064373016,"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":0.011599999852478504,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.6794999837875366},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6685000061988831},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5823000073432922},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5806999802589417},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.5382999777793884},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5029000043869019},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41100001335144043},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.3612000048160553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7506999969482422},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.6794999837875366},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6685000061988831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.635699987411499},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5823000073432922},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5806999802589417},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.5382999777793884},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5029000043869019},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41100001335144043},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4009999930858612},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3612000048160553},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29420000314712524},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26980000734329224},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00153","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.07828","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.07828","pdf_url":"https://arxiv.org/pdf/2510.07828","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"},{"id":"doi:10.48550/arxiv.2510.07828","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.07828","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.07828","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.07828","pdf_url":"https://arxiv.org/pdf/2510.07828","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":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4416399818.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Real-world":[0],"scenes":[1],"often":[2],"feature":[3],"multiple":[4,8],"humans":[5],"interacting":[6],"with":[7,68,127],"objects":[9,122],"in":[10,112,151,155],"ways":[11],"that":[12,145],"are":[13],"causal,":[14],"goal-oriented,":[15],"or":[16],"cooperative.":[17],"Yet":[18],"existing":[19],"3D":[20,57,102],"human-object":[21,101],"interaction":[22,133],"(HOI)":[23],"benchmarks":[24],"consider":[25],"only":[26],"a":[27,41,80,116],"fraction":[28],"of":[29,48],"these":[30],"complex":[31],"interactions.":[32],"To":[33],"close":[34],"this":[35],"gap,":[36],"we":[37,90],"present":[38,91],"MMHOI":[39,54,137,162],"--":[40],"large-scale,":[42],"Multi-human":[43],"Multi-object":[44],"Interaction":[45],"dataset":[46,163],"consisting":[47],"images":[49],"from":[50],"12":[51],"everyday":[52],"scenarios.":[53],"offers":[55],"complete":[56],"shape":[58],"and":[59,65,74,106,123,138,158],"pose":[60],"annotations":[61],"for":[62,70,83,98,120],"every":[63],"person":[64],"object,":[66],"along":[67],"labels":[69],"78":[71],"action":[72,128],"categories":[73],"14":[75],"interaction-specific":[76],"body":[77],"parts,":[78],"providing":[79],"comprehensive":[81],"testbed":[82],"next-generation":[84],"HOI":[85],"research.":[86],"Building":[87],"on":[88,136],"MMHOI,":[89],"MMHOI-Net,":[92],"an":[93],"end-to-end":[94],"transformer-based":[95],"neural":[96],"network":[97],"jointly":[99],"estimating":[100],"geometries,":[103],"their":[104,124],"interactions,":[105,125],"associated":[107],"actions.":[108],"A":[109],"key":[110],"innovation":[111],"our":[113,146],"framework":[114],"is":[115,164],"structured":[117],"dual-patch":[118],"representation":[119],"modeling":[121],"combined":[126],"recognition":[129],"to":[130],"enhance":[131],"the":[132,139],"prediction.":[134],"Experiments":[135],"recently":[140],"proposed":[141],"CORE4D":[142],"datasets":[143],"demonstrate":[144],"approach":[147],"achieves":[148],"state-of-the-art":[149],"performance":[150],"multi-HOI":[152],"modeling,":[153],"excelling":[154],"both":[156],"accuracy":[157],"reconstruction":[159],"quality.":[160],"The":[161],"publicly":[165],"available":[166],"at":[167],"https://zenodo.org/records/17711786.":[168]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-11T00:00:00"}