{"id":"https://openalex.org/W4386072519","doi":"https://doi.org/10.23919/mva57639.2023.10215534","title":"QAHOI: Query-Based Anchors for Human-Object Interaction Detection","display_name":"QAHOI: Query-Based Anchors for Human-Object Interaction Detection","publication_year":2023,"publication_date":"2023-07-23","ids":{"openalex":"https://openalex.org/W4386072519","doi":"https://doi.org/10.23919/mva57639.2023.10215534"},"language":"en","primary_location":{"id":"doi:10.23919/mva57639.2023.10215534","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mva57639.2023.10215534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 18th International Conference on Machine Vision and Applications (MVA)","raw_type":"proceedings-article"},"type":"article","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":"https://openalex.org/A5101808761","display_name":"Junwen Chen","orcid":"https://orcid.org/0000-0001-9808-1520"},"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":["The University of Electro-Communications,Department of Informatics,Tokyo,Japan","Department of Informatics, The University of Electro-Communications, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications,Department of Informatics,Tokyo,Japan","institution_ids":["https://openalex.org/I20529979"]},{"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/A5054600485","display_name":"\u202aKeiji Yanai\u202c","orcid":"https://orcid.org/0000-0002-0431-183X"},"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":["The University of Electro-Communications,Department of Informatics,Tokyo,Japan","Department of Informatics, The University of Electro-Communications, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications,Department of Informatics,Tokyo,Japan","institution_ids":["https://openalex.org/I20529979"]},{"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/A5101808761"],"corresponding_institution_ids":["https://openalex.org/I20529979"],"apc_list":null,"apc_paid":null,"fwci":4.3045,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.95757062,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9944999814033508,"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":0.9921000003814697,"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":0.7706030607223511},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7077241539955139},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6521643996238708},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6069972515106201},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5763053894042969},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5289179086685181},{"id":"https://openalex.org/keywords/human-interaction","display_name":"Human interaction","score":0.46270444989204407},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4468308389186859},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4115149974822998},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34498804807662964},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32143089175224304},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.12465113401412964},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07811707258224487}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7706030607223511},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7077241539955139},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6521643996238708},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6069972515106201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5763053894042969},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5289179086685181},{"id":"https://openalex.org/C2987082051","wikidata":"https://www.wikidata.org/wiki/Q223642","display_name":"Human interaction","level":2,"score":0.46270444989204407},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4468308389186859},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4115149974822998},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34498804807662964},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32143089175224304},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.12465113401412964},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07811707258224487},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/mva57639.2023.10215534","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mva57639.2023.10215534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 18th International Conference on Machine Vision and Applications (MVA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2222512263","https://openalex.org/W2908510526","https://openalex.org/W2963097937","https://openalex.org/W2963351448","https://openalex.org/W2964225075","https://openalex.org/W3030520226","https://openalex.org/W3034934229","https://openalex.org/W3035598501","https://openalex.org/W3092462694","https://openalex.org/W3106121867","https://openalex.org/W3138516171","https://openalex.org/W3168488421","https://openalex.org/W3171169846","https://openalex.org/W3174164794","https://openalex.org/W3174480456","https://openalex.org/W3181762391","https://openalex.org/W4385245566","https://openalex.org/W6639102338","https://openalex.org/W6757817989","https://openalex.org/W6778485988","https://openalex.org/W6784094891"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W4287991909","https://openalex.org/W4390721878","https://openalex.org/W4292830139"],"abstract_inverted_index":{"Human-object":[0],"interaction":[1,21,31],"(HOI)":[2],"detection":[3,9],"as":[4],"a":[5,56,68,95,106],"downstream":[6],"of":[7,14,45,87],"object":[8],"task":[10],"requires":[11],"localizing":[12],"pairs":[13],"humans":[15],"and":[16,18,43,78,103],"objects":[17,47],"recognizing":[19],"the":[20,38,41,85,117],"between":[22],"them.":[23],"Recent":[24],"one-stage":[25],"approaches":[26],"focus":[27],"on":[28,116],"detecting":[29],"possible":[30],"points":[32],"or":[33],"filtering":[34],"human-object":[35],"pairs,":[36],"ignoring":[37],"variability":[39],"in":[40],"location":[42],"size":[44],"different":[46,75],"at":[48],"spatial":[49,76],"scales.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54],"propose":[55],"transformer-based":[57,107],"method,":[58],"QAHOI":[59,104],"(Query-Based":[60],"Anchors":[61],"for":[62,101],"Human-Object":[63],"Interaction":[64],"detection),":[65],"which":[66],"leverages":[67],"multi-scale":[69],"architecture":[70],"to":[71,82],"extract":[72],"features":[73],"from":[74],"scales":[77],"uses":[79],"query-based":[80],"anchors":[81],"predict":[83],"all":[84],"elements":[86],"an":[88],"HOI":[89],"instance.":[90],"We":[91],"further":[92],"investigate":[93],"that":[94],"powerful":[96],"backbone":[97,108],"significantly":[98],"increases":[99],"accuracy":[100],"QAHOI,":[102],"with":[105],"outperforms":[109],"recent":[110],"state-of-the-art":[111],"methods":[112],"by":[113],"large":[114],"margins":[115],"HICO-DET":[118],"benchmark.":[119]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":9}],"updated_date":"2026-01-14T23:40:02.550235","created_date":"2025-10-10T00:00:00"}