{"id":"https://openalex.org/W7126028946","doi":"https://doi.org/10.1109/access.2026.3659132","title":"Bridging Detection Architectures With Foundation Models: A Unified Framework for Human\u2013Object Interaction Detection","display_name":"Bridging Detection Architectures With Foundation Models: A Unified Framework for Human\u2013Object Interaction Detection","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7126028946","doi":"https://doi.org/10.1109/access.2026.3659132"},"language":null,"primary_location":{"id":"doi:10.1109/access.2026.3659132","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3659132","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3659132","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124241751","display_name":"Junwen Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Junwen Chen","raw_affiliation_strings":["Department of Informatics, The University of Electro-Communications, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, The University of Electro-Communications, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112212819","display_name":"Keiji Yanai","orcid":null},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiji Yanai","raw_affiliation_strings":["Department of Informatics, The University of Electro-Communications, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, The University of Electro-Communications, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5124241751"],"corresponding_institution_ids":["https://openalex.org/I20529979"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20652751,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"23299","last_page":"23310"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9922000169754028,"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":0.9922000169754028,"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":0.0010999999940395355,"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/T10028","display_name":"Topic Modeling","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/bridging","display_name":"Bridging (networking)","score":0.7768999934196472},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.527899980545044},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.5187000036239624},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4684999883174896},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4361000061035156},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.37860000133514404},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.3614000082015991}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8155999779701233},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.7768999934196472},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.527899980545044},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.5187000036239624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.474700003862381},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4684999883174896},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4361000061035156},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3693999946117401},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.33250001072883606},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33079999685287476},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C152745839","wikidata":"https://www.wikidata.org/wiki/Q5438153","display_name":"Fault detection and isolation","level":3,"score":0.2703000009059906},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/access.2026.3659132","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3659132","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3659132","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3659132","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5299659967422485,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G7301858264","display_name":null,"funder_award_id":"22H00548","funder_id":"https://openalex.org/F4320320212","funder_display_name":"Japan Society for the Promotion of Science London"}],"funders":[{"id":"https://openalex.org/F4320320212","display_name":"Japan Society for the Promotion of Science London","ror":"https://ror.org/02m7axw05"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W2194775991","https://openalex.org/W2888096830","https://openalex.org/W2962844592","https://openalex.org/W2963097937","https://openalex.org/W2964225075","https://openalex.org/W2990599624","https://openalex.org/W3034427487","https://openalex.org/W3035598501","https://openalex.org/W3095753865","https://openalex.org/W3096609285","https://openalex.org/W3109754877","https://openalex.org/W3138516171","https://openalex.org/W3159481202","https://openalex.org/W3171169846","https://openalex.org/W3174164794","https://openalex.org/W3181762391","https://openalex.org/W4292692470","https://openalex.org/W4312443924","https://openalex.org/W4312538795","https://openalex.org/W4312848112","https://openalex.org/W4312960102","https://openalex.org/W4313169234","https://openalex.org/W4367300822","https://openalex.org/W4385245566","https://openalex.org/W4386057783","https://openalex.org/W4386071869","https://openalex.org/W4386072519","https://openalex.org/W4387961281","https://openalex.org/W4388579521","https://openalex.org/W4389179984","https://openalex.org/W4390873645","https://openalex.org/W4390874582","https://openalex.org/W4402753532","https://openalex.org/W4402753722","https://openalex.org/W4402754006","https://openalex.org/W4409263010"],"related_works":[],"abstract_inverted_index":{"Human\u2013Object":[0],"Interaction":[1],"Detection":[2],"(HOID)":[3],"has":[4],"benefited":[5],"greatly":[6],"from":[7,72,110],"advances":[8],"in":[9],"modern":[10],"detection":[11,158],"architectures":[12,159],"and":[13,27,35,49,80,101,116,139],"vision-language":[14,161],"foundation":[15,125,162],"models.":[16,163],"In":[17],"this":[18],"paper,":[19],"we":[20],"present":[21],"two":[22],"progressively":[23],"improved":[24],"HOID":[25,89,148],"frameworks\u2014SOV-STG-VLA":[26],"Hybrid-SOV\u2014that":[28],"jointly":[29],"push":[30],"the":[31,91],"frontier":[32],"of":[33],"accurate":[34],"efficient":[36,98],"interaction":[37],"understanding.":[38],"SOV-STG-VLA":[39],"reformulates":[40],"HOI":[41,82,108],"prediction":[42],"as":[43],"a":[44,51,66,102],"subject\u2013object\u2013verb":[45],"(SOV)":[46],"decoding":[47],"problem":[48],"introduces":[50],"Split":[52],"Target":[53],"Guided":[54],"(STG)":[55],"denoising":[56],"strategy":[57],"that":[58,105,142],"accelerates":[59],"convergence":[60],"while":[61],"enhancing":[62],"structural":[63],"consistency.":[64],"Furthermore,":[65],"Vision\u2013Language":[67],"Advisor":[68],"(VLA)":[69],"integrates":[70],"priors":[71],"large":[73],"multimodal":[74],"models":[75],"to":[76],"enrich":[77],"verb":[78],"semantics":[79],"improve":[81],"classification.":[83],"Building":[84],"upon":[85],"this,":[86],"Hybrid-SOV":[87,127],"aligns":[88],"with":[90,123,131,160],"latest":[92],"object-detection":[93],"paradigms":[94],"by":[95],"incorporating":[96],"an":[97,153],"hybrid":[99],"encoder":[100],"query-selection":[103],"mechanism":[104],"directly":[106],"constructs":[107],"queries":[109],"visual":[111],"features,":[112,126],"eliminating":[113],"predefined":[114],"embeddings":[115],"enabling":[117],"more":[118],"interpretable":[119],"decoding.":[120],"When":[121],"coupled":[122],"DINO-v3":[124],"achieves":[128],"state-of-the-art":[129],"accuracy":[130],"superior":[132],"inference":[133],"efficiency.":[134],"Extensive":[135],"experiments":[136],"on":[137],"HICO-DET":[138],"V-COCO":[140],"demonstrate":[141],"our":[143],"frameworks":[144],"not":[145],"only":[146],"advance":[147],"performance":[149],"but":[150],"also":[151],"establish":[152],"effective":[154],"path":[155],"toward":[156],"bridging":[157]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-30T00:00:00"}