{"id":"https://openalex.org/W7138041856","doi":"https://doi.org/10.1609/aaai.v40i14.38148","title":"UniHOI: Unified Human-Object Interaction Understanding via Unified Token Space","display_name":"UniHOI: Unified Human-Object Interaction Understanding via Unified Token Space","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138041856","doi":"https://doi.org/10.1609/aaai.v40i14.38148"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i14.38148","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38148","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i14.38148","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113196447","display_name":"Panqi Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Panqi Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129659824","display_name":"Haodong Jing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haodong Jing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129689115","display_name":"Nanning Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nanning Zheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129734979","display_name":"Yongqiang Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongqiang Ma","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5113196447"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33258762,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"14","first_page":"11640","last_page":"11648"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.964900016784668,"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":0.964900016784668,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.00419999985024333,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.003800000064074993,"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/semantics","display_name":"Semantics (computer science)","score":0.5260000228881836},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5042999982833862},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4544999897480011},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.45080000162124634},{"id":"https://openalex.org/keywords/unified-model","display_name":"Unified Model","score":0.4496000111103058},{"id":"https://openalex.org/keywords/development","display_name":"Development (topology)","score":0.3711000084877014}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7541000247001648},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5260000228881836},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5042999982833862},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4560000002384186},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4544999897480011},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.45080000162124634},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.4496000111103058},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43709999322891235},{"id":"https://openalex.org/C2776542497","wikidata":"https://www.wikidata.org/wiki/Q5266672","display_name":"Development (topology)","level":2,"score":0.3711000084877014},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C46451288","wikidata":"https://www.wikidata.org/wiki/Q1080745","display_name":"Unified field theory","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27239999175071716}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i14.38148","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38148","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i14.38148","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38148","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6917653679847717,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"the":[1,21],"field":[2],"of":[3,23],"human-object":[4],"interaction":[5,25,74,106],"(HOI),":[6],"detection":[7,37,91,103],"and":[8,38,50,61,73,92,104],"generation":[9,39,112],"are":[10],"two":[11],"dual":[12],"tasks":[13],"that":[14,83],"have":[15],"traditionally":[16],"been":[17],"addressed":[18],"separately,":[19],"hindering":[20],"development":[22],"comprehensive":[24],"understanding.":[26],"To":[27],"address":[28],"this,":[29],"we":[30,54],"propose":[31],"UniHOI,":[32],"which":[33],"jointly":[34],"models":[35],"HOI":[36,90,102],"via":[40],"a":[41,56,62],"unified":[42,63],"token":[43],"space,":[44],"thereby":[45],"effectively":[46],"promoting":[47],"knowledge":[48],"sharing":[49],"enhancing":[51],"generalization.":[52],"Specifically,":[53,94],"introduce":[55],"symmetric":[57],"interaction-aware":[58],"attention":[59],"module":[60],"semi-supervised":[64],"learning":[65],"paradigm,":[66],"enabling":[67],"effective":[68],"bidirectional":[69],"mapping":[70],"between":[71],"images":[72],"semantics":[75],"even":[76],"under":[77],"limited":[78],"annotations.":[79],"Extensive":[80],"experiments":[81],"demonstrate":[82],"UniHOI":[84,95],"achieves":[85],"state-of-the-art":[86],"performance":[87],"in":[88],"both":[89],"generation.":[93],"improves":[96],"accuracy":[97],"by":[98,108],"4.9%":[99],"on":[100,110],"long-tailed":[101],"boosts":[105],"metrics":[107],"42.0%":[109],"open-vocabulary":[111],"tasks.":[113]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}