{"id":"https://openalex.org/W4415708286","doi":"https://doi.org/10.1109/icme59968.2025.11209879","title":"THOR: Text to Human-Object Interaction Diffusion via Relation Intervention","display_name":"THOR: Text to Human-Object Interaction Diffusion via Relation Intervention","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708286","doi":"https://doi.org/10.1109/icme59968.2025.11209879"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209879","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209879","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5035783011","display_name":"Qianyang Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianyang Wu","raw_affiliation_strings":["ShanghaiTech University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017327360","display_name":"Shi Ye","orcid":"https://orcid.org/0000-0001-9625-8222"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Shi","raw_affiliation_strings":["ShanghaiTech University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043863561","display_name":"Xiaoshui Huang","orcid":"https://orcid.org/0000-0002-3579-538X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshui Huang","raw_affiliation_strings":["Shanghai Jiao Tong University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101320366","display_name":"Lan Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lan Xu","raw_affiliation_strings":["ShanghaiTech University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100564692","display_name":"Jingyi Yu","orcid":"https://orcid.org/0009-0001-7113-3893"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyi Yu","raw_affiliation_strings":["ShanghaiTech University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100639520","display_name":"Jingya Wang","orcid":"https://orcid.org/0000-0002-5618-7498"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingya Wang","raw_affiliation_strings":["ShanghaiTech University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,China","institution_ids":["https://openalex.org/I30809798"]}]}],"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.366100013256073,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.366100013256073,"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":0.31700000166893005,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.07980000227689743,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6284999847412109},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6191999912261963},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5929999947547913},{"id":"https://openalex.org/keywords/vagueness","display_name":"Vagueness","score":0.4902999997138977},{"id":"https://openalex.org/keywords/intervention","display_name":"Intervention (counseling)","score":0.4805000126361847},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.47999998927116394}],"concepts":[{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6284999847412109},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6191999912261963},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5929999947547913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5424000024795532},{"id":"https://openalex.org/C2776825360","wikidata":"https://www.wikidata.org/wiki/Q1411921","display_name":"Vagueness","level":3,"score":0.4902999997138977},{"id":"https://openalex.org/C2780665704","wikidata":"https://www.wikidata.org/wiki/Q959298","display_name":"Intervention (counseling)","level":2,"score":0.4805000126361847},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.47999998927116394},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4652000069618225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.462799996137619},{"id":"https://openalex.org/C156103551","wikidata":"https://www.wikidata.org/wiki/Q130998","display_name":"Equivalence relation","level":2,"score":0.34619998931884766},{"id":"https://openalex.org/C207451115","wikidata":"https://www.wikidata.org/wiki/Q12898216","display_name":"Throwing","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3000999987125397},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2973000109195709},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209879","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209879","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2811441028","https://openalex.org/W2986708244","https://openalex.org/W4297981470","https://openalex.org/W4312457231","https://openalex.org/W4312635677","https://openalex.org/W4312783246","https://openalex.org/W4313182738","https://openalex.org/W4378084859","https://openalex.org/W4382457661","https://openalex.org/W4386065366","https://openalex.org/W4386065848","https://openalex.org/W4386075980","https://openalex.org/W4386075982","https://openalex.org/W4386136919","https://openalex.org/W4389339329","https://openalex.org/W4390190183","https://openalex.org/W4390871704","https://openalex.org/W4390871885","https://openalex.org/W4390872031","https://openalex.org/W4390872247","https://openalex.org/W4390872353","https://openalex.org/W4390872595","https://openalex.org/W4393196385","https://openalex.org/W4402754156","https://openalex.org/W4402772414","https://openalex.org/W4404439868","https://openalex.org/W4414197407"],"related_works":[],"abstract_inverted_index":{"This":[0,100],"paper":[1],"addresses":[2],"the":[3,33,38,44,103],"challenging":[4],"task":[5,30],"of":[6,40,47,137],"generating":[7],"dynamic":[8],"Human-Object":[9,59],"Interactions":[10],"from":[11,120],"textual":[12],"descriptions,":[13],"named":[14],"Text2HOI.":[15],"While":[16],"most":[17],"existing":[18],"works":[19],"assume":[20],"interactions":[21],"with":[22,63,74,110],"limited":[23],"body":[24],"parts":[25],"or":[26],"static":[27],"objects,":[28,109],"our":[29],"involves":[31],"addressing":[32],"variation":[34],"in":[35,97],"human":[36,86],"motion,":[37],"diversity":[39],"object":[41,48,88,98],"shapes,":[42],"and":[43,87,90,108,126],"semantic":[45],"vagueness":[46],"motion":[49,89,112,119,138],"simultaneously.":[50],"To":[51,122],"tackle":[52],"this,":[53],"we":[54,83],"propose":[55],"a":[56,69,75],"novel":[57],"Text-guided":[58],"Interaction":[60],"diffusion":[61,71,81],"model":[62,72],"Relation":[64],"Intervention":[65],"(THOR).":[66],"THOR":[67],"is":[68,132],"cohesive":[70],"equipped":[73],"relation":[76,129],"intervention":[77,101,130],"mechanism.":[78],"In":[79],"each":[80],"step,":[82],"initiate":[84],"text-guided":[85],"then":[91],"leverage":[92],"human-object":[93],"relations":[94,105],"to":[95],"intervene":[96],"motion.":[99],"enhances":[102],"spatial-temporal":[104],"between":[106],"humans":[107],"human-centric":[111],"providing":[113],"additional":[114],"guidance":[115],"for":[116],"synthesizing":[117],"consistent":[118],"text.":[121],"achieve":[123],"more":[124],"reasonable":[125],"realistic":[127],"results,":[128],"loss":[131],"introduced":[133],"at":[134],"different":[135],"levels":[136],"granularity.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}
