{"id":"https://openalex.org/W4417124633","doi":"https://doi.org/10.1145/3757377.3763861","title":"HOMA: Towards Generic Human-Object Interaction in Multimodal Driven Human Animation with Weak Conditions","display_name":"HOMA: Towards Generic Human-Object Interaction in Multimodal Driven Human Animation with Weak Conditions","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W4417124633","doi":"https://doi.org/10.1145/3757377.3763861"},"language":null,"primary_location":{"id":"doi:10.1145/3757377.3763861","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3757377.3763861","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3757377.3763861","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102570203","display_name":"Ziyao Huang","orcid":"https://orcid.org/0009-0004-3141-9979"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyao Huang","raw_affiliation_strings":["University of Chinese Academy of Sciences, beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-3141-9979","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zixiang Zhou","orcid":"https://orcid.org/0009-0007-0443-389X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixiang Zhou","raw_affiliation_strings":["Tencent, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-0443-389X","affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056924576","display_name":"Juan Cao","orcid":"https://orcid.org/0000-0002-7857-1546"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juan Cao","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7857-1546","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035573840","display_name":"Yifeng Ma","orcid":"https://orcid.org/0009-0002-4123-0091"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifeng Ma","raw_affiliation_strings":["Tencent, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-4123-0091","affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102156610","display_name":"Yi Chen","orcid":"https://orcid.org/0009-0002-2831-8232"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Chen","raw_affiliation_strings":["Tencent, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-2831-8232","affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113882091","display_name":"Z. Rao","orcid":"https://orcid.org/0009-0006-2888-185X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zejing Rao","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-2888-185X","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049513422","display_name":"Zhiyong Xu","orcid":"https://orcid.org/0009-0007-6908-1709"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Xu","raw_affiliation_strings":["Tencent, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-6908-1709","affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongmei Wang","orcid":"https://orcid.org/0000-0002-4538-906X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongmei Wang","raw_affiliation_strings":["Tencent, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4538-906X","affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102310454","display_name":"Qin Lin","orcid":"https://orcid.org/0009-0008-3462-9735"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Lin","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0008-3462-9735","affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuan Zhou","orcid":"https://orcid.org/0000-0001-6430-2137"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Zhou","raw_affiliation_strings":["Tencent, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6430-2137","affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011375148","display_name":"Qinglin Lu","orcid":"https://orcid.org/0000-0002-4584-0826"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinglin Lu","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-4584-0826","affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112699696","display_name":"Fan Tang","orcid":"https://orcid.org/0000-0002-3975-2483"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Tang","raw_affiliation_strings":["University of Chinese Academy of Sciences, beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3975-2483","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.546999990940094,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.546999990940094,"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/T11448","display_name":"Face recognition and analysis","score":0.22920000553131104,"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":0.1014999970793724,"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/animation","display_name":"Animation","score":0.5631999969482422},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.5612000226974487},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.5178999900817871},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4846999943256378},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.46860000491142273},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4162999987602234},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.35199999809265137},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.3513000011444092},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.3228999972343445}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8008000254631042},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5631999969482422},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.5612000226974487},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.5178999900817871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5069000124931335},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4846999943256378},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.46860000491142273},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43220001459121704},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4162999987602234},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3659000098705292},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3181000053882599},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C2776977519","wikidata":"https://www.wikidata.org/wiki/Q4636326","display_name":"3D interaction","level":3,"score":0.29840001463890076},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.2865000069141388},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.2806999981403351},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2752000093460083},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2587999999523163},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3757377.3763861","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3757377.3763861","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3757377.3763861","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3757377.3763861","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8887096489","display_name":null,"funder_award_id":"62572458","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":18,"referenced_works":["https://openalex.org/W2191779130","https://openalex.org/W2604379605","https://openalex.org/W3159481202","https://openalex.org/W4378084859","https://openalex.org/W4386072021","https://openalex.org/W4388979610","https://openalex.org/W4389339329","https://openalex.org/W4390190334","https://openalex.org/W4390872031","https://openalex.org/W4402704510","https://openalex.org/W4402727180","https://openalex.org/W4402754063","https://openalex.org/W4402772461","https://openalex.org/W4404526836","https://openalex.org/W4404966227","https://openalex.org/W4409369524","https://openalex.org/W4413145441","https://openalex.org/W4415798746"],"related_works":[],"abstract_inverted_index":{"While":[0],"recent":[1],"advances":[2],"in":[3,165],"human-object":[4,15],"interaction":[5,46,166],"(HOI)":[6],"video":[7,62],"generation":[8,63,189],"showcase":[9],"promising":[10],"capabilities":[11],"for":[12,148],"synthesizing":[13],"coordinated":[14],"dynamics,":[16],"existing":[17,174],"methods":[18,175],"remain":[19],"constrained":[20],"by":[21,176,195],"their":[22],"reliance":[23],"on":[24,77],"meticulously":[25],"curated":[26],"motion":[27,69,86],"sequences":[28],"and":[29,36,45,74,85,110,118,168,190],"actor-specific":[30],"data,":[31],"thereby":[32],"limiting":[33],"practical":[34],"scalability":[35],"user":[37],"accessibility.":[38],"Furthermore,":[39],"generalization":[40,169],"to":[41,71,106,133],"novel":[42],"object":[43,192],"appearances":[44],"scenarios":[47],"remains":[48],"understudied.":[49],"To":[50,114],"address":[51],"these":[52],"limitations,":[53],"we":[54,122,142],"propose":[55],"HOMA,":[56],"a":[57,94,102,124,144,196],"weakly":[58],"conditioned":[59],"multimodal-driven":[60],"HOI":[61,126],"framework":[64],"that":[65,160],"introduces":[66],"sparse,":[67],"decoupled":[68],"guidance":[70],"enhance":[72],"controllability":[73],"reduce":[75],"dependency":[76],"stringent":[78],"input":[79,91],"conditions.":[80],"Our":[81],"approach":[82],"encodes":[83],"appearance":[84],"signals":[87],"into":[88],"the":[89],"dual":[90],"space":[92,105],"of":[93],"multimodal":[95],"diffusion":[96],"transformer":[97],"(MMDiT),":[98],"fusing":[99],"them":[100],"within":[101],"shared":[103],"context":[104],"enable":[107],"temporally":[108],"consistent":[109],"physically":[111],"plausible":[112],"interactions.":[113],"optimize":[115],"learning":[116],"efficiency":[117],"feature":[119],"injection":[120],"accuracy,":[121],"introduce":[123],"parameter-space":[125],"adapter":[127,147],"initialized":[128],"with":[129],"pretrained":[130],"MMDiT":[131],"weights":[132],"preserve":[134],"prior":[135],"knowledge":[136],"while":[137],"enabling":[138],"efficient":[139],"adaptation.":[140],"Additionally,":[141],"design":[143],"facial":[145],"cross-attention":[146],"audio-driven":[149],"lip":[150],"synchronization,":[151],"ensuring":[152],"anatomically":[153],"accurate":[154],"speech":[155],"animation.":[156],"Extensive":[157],"experiments":[158],"demonstrate":[159],"HOMA":[161],"achieves":[162],"state-of-the-art":[163],"performance":[164],"naturalness":[167],"under":[170],"weak":[171],"supervision,":[172],"outperforming":[173],"significant":[177],"margins.":[178],"We":[179],"further":[180],"illustrate":[181],"HOMA\u2019s":[182],"versatility":[183],"through":[184],"diverse":[185],"applications,":[186],"including":[187],"text-conditioned":[188],"interactive":[191],"manipulation,":[193],"facilitated":[194],"user-friendly":[197],"demo":[198],"interface.":[199],"The":[200],"project":[201],"page":[202],"is":[203],"https://bone-11.github.io/homa-page/.":[204]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-08T00:00:00"}