{"id":"https://openalex.org/W4416685239","doi":"https://doi.org/10.1109/iccv51701.2025.02108","title":"No More Sibling Rivalry: Debiasing Human-Object Interaction Detection","display_name":"No More Sibling Rivalry: Debiasing Human-Object Interaction Detection","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416685239","doi":"https://doi.org/10.1109/iccv51701.2025.02108"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02108","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02108","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.00760","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101793904","display_name":"Bin Yang","orcid":"https://orcid.org/0000-0002-7883-0739"},"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":"Bin Yang","raw_affiliation_strings":["ShanghaiTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100778270","display_name":"Yulin Zhang","orcid":"https://orcid.org/0000-0001-7231-3880"},"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":"Yulin Zhang","raw_affiliation_strings":["ShanghaiTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hong-Yu Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong-Yu Zhou","raw_affiliation_strings":["School of Biomedical Engineering, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biomedical Engineering, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043811579","display_name":"Sibei Yang","orcid":"https://orcid.org/0000-0002-6910-9958"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sibei Yang","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22707","last_page":"22717"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7900999784469604,"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":0.7900999784469604,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.09520000219345093,"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":0.022099999710917473,"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/debiasing","display_name":"Debiasing","score":0.9761999845504761},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.6466000080108643},{"id":"https://openalex.org/keywords/sibling","display_name":"Sibling","score":0.5965999960899353},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4571000039577484},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.37209999561309814}],"concepts":[{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.9761999845504761},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.6466000080108643},{"id":"https://openalex.org/C2776194465","wikidata":"https://www.wikidata.org/wiki/Q31184","display_name":"Sibling","level":2,"score":0.5965999960899353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5673999786376953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5001000165939331},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4571000039577484},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4253999888896942},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3668999969959259},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27320000529289246},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.2705000042915344},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2565999925136566},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2547000050544739}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02108","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02108","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:2509.00760","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.00760","pdf_url":"https://arxiv.org/pdf/2509.00760","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.00760","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.00760","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.00760","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.00760","pdf_url":"https://arxiv.org/pdf/2509.00760","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Detection":[0],"transformers":[1],"have":[2],"been":[3],"applied":[4],"to":[5,57,133,144],"human-object":[6],"interaction":[7,33,59],"(HOI)":[8],"detection,":[9],"enhancing":[10],"the":[11,32,58,81,100,154,161],"localization":[12],"and":[13,45,54,98,102,113,160],"recognition":[14],"of":[15,83],"human-action-object":[16],"triplets":[17,42,112],"in":[18],"images.":[19],"Despite":[20],"remarkable":[21],"progress,":[22],"this":[23],"study":[24],"identifies":[25],"a":[26],"critical":[27],"issue-\"Toxic":[28],"Siblings\"":[29],"bias-which":[30],"hinders":[31],"decoder's":[34],"learning,":[35],"as":[36,76],"numerous":[37],"similar":[38],"yet":[39],"distinct":[40],"HOI":[41,111],"interfere":[43],"with":[44],"even":[46],"compete":[47],"against":[48],"each":[49],"other":[50,137],"both":[51,153],"input":[52,101],"side":[53,56],"output":[55,103],"decoder.":[60],"This":[61],"bias":[62],"arises":[63],"from":[64,136],"high":[65],"confusion":[66],"among":[67,130],"sibling":[68,131],"triplets/categories,":[69],"where":[70],"increased":[71],"similarity":[72],"paradoxically":[73],"reduces":[74],"precision,":[75],"one's":[77],"gain":[78],"comes":[79],"at":[80],"expense":[82],"its":[84],"toxic":[85],"sibling's":[86],"decline.":[87],"To":[88],"address":[89],"this,":[90],"we":[91,150],"propose":[92],"two":[93],"novel":[94],"debiasing":[95],"learning":[96],"objectives-\"contrastive-then-calibration\"":[97],"\"merge-then-split\"-targeting":[99],"perspectives,":[104],"respectively.":[105],"The":[106,124],"former":[107],"samples":[108],"sibling-like":[109],"incorrect":[110],"reconstructs":[114],"them":[115,135],"into":[116],"correct":[117],"ones,":[118],"guided":[119],"by":[120],"strong":[121],"positional":[122],"priors.":[123],"latter":[125],"first":[126],"learns":[127],"shared":[128],"features":[129],"categories":[132],"distinguish":[134],"groups,":[138],"then":[139],"explicitly":[140],"refines":[141],"intra-group":[142],"differentiation":[143],"preserve":[145],"uniqueness.":[146],"Experiments":[147],"show":[148],"that":[149],"significantly":[151],"outperform":[152],"baseline":[155],"(+9.18%":[156],"mAP":[157],"on":[158],"HICO-Det)":[159],"state-of-the-art":[162],"(+3.59%":[163],"mAP)":[164],"across":[165],"various":[166],"settings.":[167]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
