{"id":"https://openalex.org/W3168488421","doi":"https://doi.org/10.1109/cvpr46437.2021.00889","title":"Reformulating HOI Detection as Adaptive Set Prediction","display_name":"Reformulating HOI Detection as Adaptive Set Prediction","publication_year":2021,"publication_date":"2021-06-01","ids":{"openalex":"https://openalex.org/W3168488421","doi":"https://doi.org/10.1109/cvpr46437.2021.00889","mag":"3168488421"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr46437.2021.00889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr46437.2021.00889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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":null,"display_name":"Mingfei Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingfei Chen","raw_affiliation_strings":["Huazhong University of Science and Technology","SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002061412","display_name":"Yue Liao","orcid":"https://orcid.org/0000-0002-2671-0655"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Liao","raw_affiliation_strings":["Institute of Artificial Intelligence, Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330138","display_name":"Si Liu","orcid":"https://orcid.org/0000-0002-9180-2935"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Si Liu","raw_affiliation_strings":["Institute of Artificial Intelligence, Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438521","display_name":"Zhiyuan Chen","orcid":"https://orcid.org/0000-0003-3210-0324"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyuan Chen","raw_affiliation_strings":["SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100455958","display_name":"Fei Wang","orcid":"https://orcid.org/0000-0003-3462-8472"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei Wang","raw_affiliation_strings":["SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100657544","display_name":"Chen Qian","orcid":"https://orcid.org/0000-0002-8761-5563"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Qian","raw_affiliation_strings":["SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.899,"has_fulltext":false,"cited_by_count":159,"citation_normalized_percentile":{"value":0.98849949,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"9000","last_page":"9009"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994000196456909,"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":0.9958999752998352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8295249342918396},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.565578281879425},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5443832278251648},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5403691530227661},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.49084168672561646},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.46759599447250366},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.46262311935424805},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.45191413164138794},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4404347240924835},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42824625968933105},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.382843554019928},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3749701976776123},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07652047276496887}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8295249342918396},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.565578281879425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5443832278251648},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5403691530227661},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.49084168672561646},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.46759599447250366},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.46262311935424805},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.45191413164138794},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4404347240924835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42824625968933105},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.382843554019928},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3749701976776123},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07652047276496887},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr46437.2021.00889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr46437.2021.00889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.41999998688697815}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1551928752","https://openalex.org/W1861492603","https://openalex.org/W2194775991","https://openalex.org/W2222512263","https://openalex.org/W2307770531","https://openalex.org/W2613718673","https://openalex.org/W2801004733","https://openalex.org/W2888096830","https://openalex.org/W2888814092","https://openalex.org/W2901532862","https://openalex.org/W2905048190","https://openalex.org/W2908510526","https://openalex.org/W2953106684","https://openalex.org/W2955882737","https://openalex.org/W2962766617","https://openalex.org/W2962844592","https://openalex.org/W2963097937","https://openalex.org/W2963323244","https://openalex.org/W2963351448","https://openalex.org/W2963480047","https://openalex.org/W2964225075","https://openalex.org/W2982232158","https://openalex.org/W2984933298","https://openalex.org/W2990599624","https://openalex.org/W3009811369","https://openalex.org/W3021735172","https://openalex.org/W3033425243","https://openalex.org/W3034325957","https://openalex.org/W3034427487","https://openalex.org/W3034463304","https://openalex.org/W3034772468","https://openalex.org/W3034895839","https://openalex.org/W3034934229","https://openalex.org/W3034951775","https://openalex.org/W3035170495","https://openalex.org/W3035189477","https://openalex.org/W3035440494","https://openalex.org/W3035598501","https://openalex.org/W3092961994","https://openalex.org/W3095127874","https://openalex.org/W3095753865","https://openalex.org/W3102452576","https://openalex.org/W3106121867","https://openalex.org/W3106988096","https://openalex.org/W3108748824","https://openalex.org/W3109754877","https://openalex.org/W3109813419","https://openalex.org/W6620707391","https://openalex.org/W6632922691","https://openalex.org/W6639102338","https://openalex.org/W6697925102","https://openalex.org/W6754152559","https://openalex.org/W6756874041","https://openalex.org/W6757817989","https://openalex.org/W6763509872","https://openalex.org/W6767216089","https://openalex.org/W6769695595","https://openalex.org/W6778909459","https://openalex.org/W6779604294","https://openalex.org/W6780751581","https://openalex.org/W6781548975","https://openalex.org/W6785479356","https://openalex.org/W6786217690"],"related_works":["https://openalex.org/W2047973478","https://openalex.org/W4295532600","https://openalex.org/W2063823869","https://openalex.org/W2067569035","https://openalex.org/W2090985514","https://openalex.org/W2012531322","https://openalex.org/W2885323543","https://openalex.org/W2785900585","https://openalex.org/W2145649715","https://openalex.org/W2353730437"],"abstract_inverted_index":{"Determining":[0],"which":[1,28],"image":[2],"regions":[3],"to":[4,76,119],"concentrate":[5],"is":[6,100,165],"critical":[7],"for":[8],"Human-Object":[9],"Interaction":[10],"(HOI)":[11],"detection.":[12],"Conventional":[13],"HOI":[14,40,148],"detectors":[15],"focus":[16],"on":[17,145,158],"either":[18],"detected":[19],"human":[20,140],"and":[21,63,142],"object":[22],"pairs":[23],"or":[24],"pre-defined":[25],"interaction":[26,64,73,78,109,129],"locations,":[27],"limits":[29],"learning":[30],"of":[31],"the":[32,87,97,108,124,128],"effective":[33,115],"features.":[34],"In":[35],"this":[36,49],"paper,":[37],"we":[38,52,69,112,152],"reformulate":[39],"detection":[41,149],"as":[42],"an":[43,54,77,114],"adaptive":[44],"set":[45,75,80],"prediction":[46,79],"problem,":[47],"with":[48,60,81,107],"novel":[50],"formulation,":[51],"propose":[53],"Adaptive":[55],"Set-based":[56],"one-stage":[57],"framework":[58],"(AS-Net)":[59],"parallel":[61],"instance":[62,125],"branches.":[65],"To":[66],"attain":[67],"this,":[68],"map":[70],"a":[71,159],"trainable":[72],"query":[74,84],"transformer.":[82],"Each":[83],"adaptively":[85,102],"aggregates":[86],"interaction-relevant":[88],"features":[89,122,144],"from":[90,123],"global":[91],"contexts":[92],"through":[93],"multi-head":[94],"co-attention.":[95],"Besides,":[96],"training":[98],"process":[99],"supervised":[101],"by":[103],"matching":[104],"each":[105],"ground-truth":[106],"prediction.":[110],"Furthermore,":[111],"design":[113],"instance-aware":[116],"attention":[117],"module":[118],"introduce":[120],"instructive":[121],"branch":[126],"into":[127],"branch.":[130],"Our":[131],"method":[132],"outperforms":[133],"previous":[134],"state-of-the-art":[135],"methods":[136],"without":[137],"any":[138],"extra":[139],"pose":[141],"language":[143],"three":[146],"challenging":[147],"datasets.":[150],"Especially,":[151],"achieve":[153],"over":[154],"31%":[155],"relative":[156],"improvement":[157],"large":[160],"scale":[161],"HICO-DET":[162],"dataset.":[163],"Code":[164],"available":[166],"at":[167],"https://github.com/yoyomimi/AS-Net.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":27},{"year":2024,"cited_by_count":46},{"year":2023,"cited_by_count":44},{"year":2022,"cited_by_count":31},{"year":2021,"cited_by_count":4}],"updated_date":"2026-08-19T15:00:24.278416","created_date":"2025-10-10T00:00:00"}