{"id":"https://openalex.org/W4311681959","doi":"https://doi.org/10.1145/3551626.3564944","title":"Parallel Queries for Human-Object Interaction Detection","display_name":"Parallel Queries for Human-Object Interaction Detection","publication_year":2022,"publication_date":"2022-12-07","ids":{"openalex":"https://openalex.org/W4311681959","doi":"https://doi.org/10.1145/3551626.3564944"},"language":"en","primary_location":{"id":"doi:10.1145/3551626.3564944","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3551626.3564944","pdf_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F3551626.3564944&file=a11-chen-supp.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F3551626.3564944&file=a11-chen-supp.pdf","any_repository_has_fulltext":null},"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, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"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, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"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":0.4084,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.60901266,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"202","issue":null,"first_page":"1","last_page":"7"},"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":0.9993000030517578,"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":0.9976000189781189,"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":0.8047244548797607},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7435920834541321},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5669202208518982},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5563948750495911},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5501428842544556},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5286729335784912},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5172577500343323},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4630562961101532},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4377833604812622},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39313697814941406},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3694441616535187},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16644981503486633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8047244548797607},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7435920834541321},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5669202208518982},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5563948750495911},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5501428842544556},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5286729335784912},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5172577500343323},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4630562961101532},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4377833604812622},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39313697814941406},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3694441616535187},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16644981503486633},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3551626.3564944","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3551626.3564944","pdf_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F3551626.3564944&file=a11-chen-supp.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3551626.3564944","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3551626.3564944","pdf_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F3551626.3564944&file=a11-chen-supp.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4311681959.pdf","grobid_xml":"https://content.openalex.org/works/W4311681959.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W2307770531","https://openalex.org/W2962766617","https://openalex.org/W2963097937","https://openalex.org/W2964225075","https://openalex.org/W2982232158","https://openalex.org/W2990599624","https://openalex.org/W3009811369","https://openalex.org/W3034951775","https://openalex.org/W3047999543","https://openalex.org/W3096609285","https://openalex.org/W3102452576","https://openalex.org/W3151099711","https://openalex.org/W3168279596","https://openalex.org/W3168488421","https://openalex.org/W3171169846","https://openalex.org/W3181762391","https://openalex.org/W6600175266","https://openalex.org/W6600185353"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W3203142394","https://openalex.org/W4302615923","https://openalex.org/W2542937328","https://openalex.org/W1974101135","https://openalex.org/W2351061015","https://openalex.org/W2183306018","https://openalex.org/W2017509870","https://openalex.org/W2549990292","https://openalex.org/W2345479200"],"abstract_inverted_index":{"Human-Object":[0],"Interaction":[1],"(HOI)":[2],"Detection":[3],"requires":[4],"localizing":[5],"a":[6,106],"pair":[7],"of":[8,132,158,166,180,195],"humans":[9,79,167],"and":[10,36,57,73,80,100,105,120,137,140,147,168],"objects.":[11],"Recent":[12],"transformer-based":[13],"methods":[14],"leverage":[15],"the":[16,21,34,40,49,55,66,78,97,114,117,122,128,133,141,144,152,156,159,163,177,181,189,196],"query":[17,161],"embeddings":[18,27,52,99,102,139,146],"to":[19,32,47,53,76,95,112],"represent":[20,33],"entire":[22],"HOI":[23],"instances.":[24],"The":[25,124],"target":[26],"after":[28],"decoding":[29,68,72,75,119],"are":[30,170],"used":[31,111],"object":[35,58,74,101,138,182],"human":[37,56,136],"characteristics":[38],"at":[39],"same":[41],"time.":[42],"However,":[43],"it":[44],"is":[45,110],"ambiguous":[46],"use":[48],"highly":[50],"integrated":[51],"localize":[54],"simultaneously.":[59],"To":[60],"address":[61],"this":[62],"problem,":[63],"we":[64],"split":[65],"detection":[67,118,183],"process":[69],"into":[70],"subject":[71,98],"detect":[77],"objects":[81,169],"in":[82,103,127],"parallel.":[83],"Our":[84],"proposed":[85,186],"method,":[86],"Parallel":[87],"Query":[88],"Network":[89],"(PQNet)":[90],"uses":[91],"two":[92],"transformer":[93,153],"decoders":[94],"decode":[96],"parallel,":[104],"novel":[107],"verb":[108,129],"decoder":[109,130],"fuse":[113],"representation":[115],"from":[116],"predict":[121],"interaction.":[123],"attention":[125,134,142],"mechanisms":[126],"consist":[131],"between":[135,143],"fused":[145],"global":[148],"semantic":[149],"features.":[150],"As":[151],"architecture":[154,187],"maintains":[155],"permutation":[157],"input":[160],"embeddings,":[162],"paired":[164],"boxes":[165],"directly":[171],"predicted":[172],"by":[173],"feed-forward":[174],"networks.":[175],"With":[176],"full":[178],"usage":[179],"part,":[184],"our":[185],"outperforms":[188],"state-of-the-art":[190],"baseline":[191],"method":[192],"with":[193],"half":[194],"training":[197],"epochs.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-02T13:48:15.688549","created_date":"2025-10-10T00:00:00"}