{"id":"https://openalex.org/W4415160805","doi":"https://doi.org/10.1109/iccv51701.2025.01013","title":"Humoto: A 4D Dataset of Mocap Human Object Interactions","display_name":"Humoto: A 4D Dataset of Mocap Human Object Interactions","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415160805","doi":"https://doi.org/10.1109/iccv51701.2025.01013"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01013","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/2504.10414","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103923205","display_name":"Jiaxin Lu","orcid":"https://orcid.org/0009-0004-4485-9615"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiaxin Lu","raw_affiliation_strings":["University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059883840","display_name":"Chun-Hao P. Huang","orcid":"https://orcid.org/0000-0002-1268-6527"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chun-Hao Paul Huang","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042584669","display_name":"Uttaran Bhattacharya","orcid":"https://orcid.org/0000-0003-2141-9276"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Uttaran Bhattacharya","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056540212","display_name":"Qixing Huang","orcid":"https://orcid.org/0000-0001-6365-8051"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qixing Huang","raw_affiliation_strings":["University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089348821","display_name":"Yixuan Zhou","orcid":"https://orcid.org/0000-0003-4984-2252"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Zhou","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103923205"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25791923,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10886","last_page":"10897"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9979000091552734,"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":0.9979000091552734,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.9828000068664551,"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/scripting-language","display_name":"Scripting language","score":0.6985999941825867},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6694999933242798},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6675000190734863},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6161999702453613},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5952000021934509},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5419999957084656},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5273000001907349},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.511900007724762}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7360000014305115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7103000283241272},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6985999941825867},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6694999933242798},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6675000190734863},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6161999702453613},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5952000021934509},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5881999731063843},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5419999957084656},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5273000001907349},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.511900007724762},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.5066999793052673},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45419999957084656},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.39169999957084656},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.3050999939441681},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.2994000017642975},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29260000586509705},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2831000089645386},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C17511633","wikidata":"https://www.wikidata.org/wiki/Q830694","display_name":"SMT placement equipment","level":3,"score":0.25049999356269836}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01013","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:2504.10414","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.10414","pdf_url":"https://arxiv.org/pdf/2504.10414","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.2504.10414","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.10414","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.10414","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.10414","pdf_url":"https://arxiv.org/pdf/2504.10414","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":[{"id":"https://openalex.org/G1721723565","display_name":"CAREER: Modeling Uncertainties for Geometry Processing","funder_award_id":"2047677","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2355686941","display_name":"HCC:Small: Neural Shape Generators under Geometric, Physical, and Topological Priors","funder_award_id":"2413161","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8669240848","display_name":null,"funder_award_id":"IIS-2047677","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415160805.pdf","grobid_xml":"https://content.openalex.org/works/W4415160805.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,96],"present":[1],"Human":[2],"Motions":[3],"with":[4,32,53,128],"Objects":[5],"(HUMOTO),":[6],"a":[7,44,57],"high-fidelity":[8],"dataset":[9],"of":[10],"human-object":[11,122],"interactions":[12,31,111],"for":[13],"motion":[14,107],"generation,":[15],"computer":[16],"vision,":[17],"and":[18,37,56,78,86,93,108,116,134],"robotics":[19],"applications.":[20],"Featuring":[21],"735":[22],"sequences":[23],"(7,875":[24],"seconds":[25],"at":[26],"30":[27],"fps),":[28],"HUMOTO":[29,73],"captures":[30],"63":[33],"precisely":[34],"modeled":[35],"objects":[36],"72":[38],"articulated":[39],"parts.":[40],"Our":[41],"innovations":[42],"include":[43],"scene-driven":[45],"LLM":[46],"scripting":[47],"pipeline":[48],"creating":[49],"complete,":[50],"purposeful":[51],"tasks":[52],"natural":[54],"progression,":[55],"mocap-and-camera":[58],"recording":[59],"setup":[60],"to":[61,70,101,119],"effectively":[62],"handle":[63],"occlusions.":[64],"Spanning":[65],"diverse":[66],"activities":[67],"from":[68],"cooking":[69],"outdoor":[71],"picnics,":[72],"preserves":[74],"both":[75],"physical":[76],"accuracy":[77],"logical":[79],"task":[80],"flow.":[81],"Professional":[82],"artists":[83],"rigorously":[84],"clean":[85],"verify":[87],"each":[88],"sequence,":[89],"minimizing":[90],"foot":[91],"sliding":[92],"object":[94],"penetrations.":[95],"also":[97],"provide":[98,117],"benchmarks":[99],"compared":[100],"other":[102],"datasets.":[103],"HUMOTO's":[104],"comprehensive":[105],"full-body":[106],"simultaneous":[109],"multi-object":[110],"address":[112],"key":[113],"data-capturing":[114],"challenges":[115],"opportunities":[118],"advance":[120],"realistic":[121],"interaction":[123],"modeling":[124],"across":[125],"research":[126],"domains":[127],"practical":[129],"applications":[130],"in":[131],"animation,":[132],"robotics,":[133],"embodied":[135],"AI":[136],"systems.":[137],"Project:":[138],"https://jiaxin-lu.github.io/humoto/":[139],".":[140]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-14T00:00:00"}