{"id":"https://openalex.org/W3090476579","doi":"https://doi.org/10.1609/aaai.v35i2.16217","title":"DIRV: Dense Interaction Region Voting for End-to-End Human-Object Interaction Detection","display_name":"DIRV: Dense Interaction Region Voting for End-to-End Human-Object Interaction Detection","publication_year":2021,"publication_date":"2021-05-18","ids":{"openalex":"https://openalex.org/W3090476579","doi":"https://doi.org/10.1609/aaai.v35i2.16217","mag":"3090476579"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v35i2.16217","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v35i2.16217","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/16217/16024","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://ojs.aaai.org/index.php/AAAI/article/download/16217/16024","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061763793","display_name":"Hao-Shu Fang","orcid":"https://orcid.org/0000-0002-0758-0293"},"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":true,"raw_author_name":"Hao-Shu Fang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046598816","display_name":"Yichen Xie","orcid":"https://orcid.org/0000-0002-0974-5979"},"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":"Yichen Xie","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008382252","display_name":"Dian Shao","orcid":"https://orcid.org/0000-0002-0862-9941"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dian Shao","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010726528","display_name":"Cewu Lu","orcid":"https://orcid.org/0009-0003-7254-9318"},"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":"Cewu Lu","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061763793"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":2.6916,"has_fulltext":true,"cited_by_count":50,"citation_normalized_percentile":{"value":0.93209169,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"35","issue":"2","first_page":"1291","last_page":"1299"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9997000098228455,"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":0.9991999864578247,"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/inference","display_name":"Inference","score":0.7877638339996338},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.770257294178009},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.743529200553894},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.7115665674209595},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6135309934616089},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5621265172958374},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.560523509979248},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5103053450584412},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.47987714409828186},{"id":"https://openalex.org/keywords/majority-rule","display_name":"Majority rule","score":0.46982812881469727},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4148483872413635},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40480613708496094},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.29171764850616455},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.09055185317993164},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06213045120239258}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7877638339996338},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.770257294178009},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.743529200553894},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.7115665674209595},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6135309934616089},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5621265172958374},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.560523509979248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5103053450584412},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.47987714409828186},{"id":"https://openalex.org/C153668964","wikidata":"https://www.wikidata.org/wiki/Q27636","display_name":"Majority rule","level":2,"score":0.46982812881469727},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4148483872413635},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40480613708496094},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29171764850616455},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.09055185317993164},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06213045120239258},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v35i2.16217","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v35i2.16217","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/16217/16024","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.v35i2.16217","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v35i2.16217","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/16217/16024","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":[{"id":"https://metadata.un.org/sdg/16","score":0.6000000238418579,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1866817718","display_name":null,"funder_award_id":"2018-RGZN-02046","funder_id":"https://openalex.org/F4320325413","funder_display_name":"Shanghai Municipal Commission of Economy and Informatization"},{"id":"https://openalex.org/G4130140615","display_name":null,"funder_award_id":"61772332","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320318547","display_name":"Baidu","ror":"https://ror.org/03vs3wt56"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320325413","display_name":"Shanghai Municipal Commission of Economy and Informatization","ror":"https://ror.org/04166ws88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3090476579.pdf","grobid_xml":"https://content.openalex.org/works/W3090476579.grobid-xml"},"referenced_works_count":67,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1551928752","https://openalex.org/W1861492603","https://openalex.org/W2214124602","https://openalex.org/W2479423890","https://openalex.org/W2565639579","https://openalex.org/W2608915011","https://openalex.org/W2613718673","https://openalex.org/W2798453399","https://openalex.org/W2883697687","https://openalex.org/W2884561390","https://openalex.org/W2887585070","https://openalex.org/W2888096830","https://openalex.org/W2888814092","https://openalex.org/W2902407103","https://openalex.org/W2925742741","https://openalex.org/W2933067512","https://openalex.org/W2938667732","https://openalex.org/W2940963663","https://openalex.org/W2962202279","https://openalex.org/W2962844592","https://openalex.org/W2962954622","https://openalex.org/W2963097937","https://openalex.org/W2963351448","https://openalex.org/W2963480047","https://openalex.org/W2963532541","https://openalex.org/W2963781481","https://openalex.org/W2964121744","https://openalex.org/W2964225075","https://openalex.org/W2969441691","https://openalex.org/W2973728204","https://openalex.org/W2990268359","https://openalex.org/W2990599624","https://openalex.org/W2997150218","https://openalex.org/W2997856838","https://openalex.org/W2998296459","https://openalex.org/W3001641764","https://openalex.org/W3004349648","https://openalex.org/W3009224666","https://openalex.org/W3009811369","https://openalex.org/W3011275446","https://openalex.org/W3014792118","https://openalex.org/W3016269914","https://openalex.org/W3033238119","https://openalex.org/W3034934229","https://openalex.org/W3034951775","https://openalex.org/W3034971973","https://openalex.org/W3035047011","https://openalex.org/W3035180180","https://openalex.org/W3035440494","https://openalex.org/W3035598501","https://openalex.org/W3101631402","https://openalex.org/W3103651098","https://openalex.org/W3106121867","https://openalex.org/W4299522971","https://openalex.org/W4306979059","https://openalex.org/W6605892068","https://openalex.org/W6631190155","https://openalex.org/W6639102338","https://openalex.org/W6721769334","https://openalex.org/W6730734845","https://openalex.org/W6730903564","https://openalex.org/W6733728423","https://openalex.org/W6742348326","https://openalex.org/W6774907850","https://openalex.org/W6775827216"],"related_works":["https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W3121841074","https://openalex.org/W2901018557","https://openalex.org/W2055572829","https://openalex.org/W1894159578","https://openalex.org/W4297796115","https://openalex.org/W4285600173","https://openalex.org/W3125086856"],"abstract_inverted_index":{"Recent":[0],"years,":[1],"human-object":[2,90],"interaction":[3,67,83,119,134],"(HOI)":[4],"detection":[5,55,114],"has":[6],"achieved":[7],"impressive":[8],"advances.":[9],"However,":[10],"conventional":[11,139],"two-stage":[12],"methods":[13,25],"are":[14],"usually":[15],"slow":[16],"in":[17,58,108,136],"inference.":[18],"On":[19],"the":[20,29,46,70,80,96,105,113,164],"other":[21],"hand,":[22],"existing":[23,157],"one-stage":[24,53],"mainly":[26],"focus":[27],"on":[28,62,79,145],"union":[30],"regions":[31,84,135],"of":[32,116,131,138],"interactions,":[33],"which":[34],"introduce":[35,122],"unnecessary":[36],"visual":[37,98],"information":[38],"as":[39,93],"disturbances":[40],"to":[41,94,104,110],"HOI":[42,54,71],"detection.":[43],"To":[44],"tackle":[45],"problems":[47],"above,":[48],"we":[49,121],"propose":[50],"a":[51,63,117,123,160],"novel":[52,124],"approach":[56,77,155],"DIRV":[57],"this":[59],"paper,":[60],"based":[61],"new":[64],"concept":[65],"called":[66],"region":[68],"for":[69,88,112],"problem.":[72],"Unlike":[73],"previous":[74],"methods,":[75],"our":[76,154],"concentrates":[78],"densely":[81],"sampled":[82],"across":[85],"different":[86],"scales":[87],"each":[89],"pair,":[91],"so":[92],"capture":[95],"subtle":[97],"features":[99],"that":[100,127,153],"is":[101,174],"most":[102],"essential":[103],"interaction.":[106],"Moreover,":[107],"order":[109],"compensate":[111],"flaws":[115],"single":[118],"region,":[120],"voting":[125],"strategy":[126],"makes":[128],"full":[129],"use":[130],"those":[132],"overlapped":[133],"place":[137],"Non-Maximal":[140],"Suppression":[141],"(NMS).":[142],"Extensive":[143],"experiments":[144],"two":[146],"popular":[147],"benchmarks:":[148],"V-COCO":[149],"and":[150,168],"HICO-DET":[151],"show":[152],"outperforms":[156],"state-of-the-arts":[158],"by":[159],"large":[161],"margin":[162],"with":[163],"highest":[165],"inference":[166],"speed":[167],"lightest":[169],"network":[170],"architecture.":[171],"Our":[172],"code":[173],"publicly":[175],"available":[176],"at":[177],"www.github.com/MVIG-SJTU/DIRV.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":7}],"updated_date":"2026-05-16T08:24:45.110214","created_date":"2025-10-10T00:00:00"}