{"id":"https://openalex.org/W4387611823","doi":"https://doi.org/10.1145/3607822.3616409","title":"Enhanced Transformer Interaction Components for Human-Object Interaction Detection","display_name":"Enhanced Transformer Interaction Components for Human-Object Interaction Detection","publication_year":2023,"publication_date":"2023-10-13","ids":{"openalex":"https://openalex.org/W4387611823","doi":"https://doi.org/10.1145/3607822.3616409"},"language":"en","primary_location":{"id":"doi:10.1145/3607822.3616409","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3607822.3616409","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM Symposium on Spatial User Interaction","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/A5055182013","display_name":"Jinhui Zhang","orcid":"https://orcid.org/0009-0001-2687-1985"},"institutions":[{"id":"https://openalex.org/I4210118629","display_name":"NARI Group (China)","ror":"https://ror.org/02egn3136","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210118629"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jinhui Zhang","raw_affiliation_strings":["NARI Group Corporation (State Grid Electric Power Research Institute), China and China Realtime Database Co., Ltd., China"],"affiliations":[{"raw_affiliation_string":"NARI Group Corporation (State Grid Electric Power Research Institute), China and China Realtime Database Co., Ltd., China","institution_ids":["https://openalex.org/I4210118629"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014061999","display_name":"Yuxiao Zhao","orcid":"https://orcid.org/0009-0006-7709-1459"},"institutions":[{"id":"https://openalex.org/I4210118629","display_name":"NARI Group (China)","ror":"https://ror.org/02egn3136","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210118629"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiao Zhao","raw_affiliation_strings":["NARI Group Corporation (State Grid Electric Power Research Institute), China and China Realtime Database Co., Ltd., China"],"affiliations":[{"raw_affiliation_string":"NARI Group Corporation (State Grid Electric Power Research Institute), China and China Realtime Database Co., Ltd., China","institution_ids":["https://openalex.org/I4210118629"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103053747","display_name":"Xian Zhang","orcid":"https://orcid.org/0009-0009-2529-0896"},"institutions":[{"id":"https://openalex.org/I4210118629","display_name":"NARI Group (China)","ror":"https://ror.org/02egn3136","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210118629"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Zhang","raw_affiliation_strings":["NARI Group Corporation (State Grid Electric Power Research Institute), China and China Realtime Database Co., Ltd., China"],"affiliations":[{"raw_affiliation_string":"NARI Group Corporation (State Grid Electric Power Research Institute), China and China Realtime Database Co., Ltd., China","institution_ids":["https://openalex.org/I4210118629"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101706336","display_name":"Xiang Wang","orcid":"https://orcid.org/0009-0004-0420-3179"},"institutions":[{"id":"https://openalex.org/I4210118629","display_name":"NARI Group (China)","ror":"https://ror.org/02egn3136","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210118629"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Wang","raw_affiliation_strings":["NARI Group Corporation (State Grid Electric Power Research Institute), China and China Realtime Database Co., Ltd., China"],"affiliations":[{"raw_affiliation_string":"NARI Group Corporation (State Grid Electric Power Research Institute), China and China Realtime Database Co., Ltd., China","institution_ids":["https://openalex.org/I4210118629"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108069902","display_name":"Yuxuan Zhao","orcid":"https://orcid.org/0009-0008-7856-120X"},"institutions":[{"id":"https://openalex.org/I4210118629","display_name":"NARI Group (China)","ror":"https://ror.org/02egn3136","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210118629"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxuan Zhao","raw_affiliation_strings":["NARI Group Corporation (State Grid Electric Power Research Institute), China and China Realtime Database Co., Ltd., China"],"affiliations":[{"raw_affiliation_string":"NARI Group Corporation (State Grid Electric Power Research Institute), China and China Realtime Database Co., Ltd., China","institution_ids":["https://openalex.org/I4210118629"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101920978","display_name":"Peng Wang","orcid":"https://orcid.org/0009-0001-6556-075X"},"institutions":[{"id":"https://openalex.org/I4210118629","display_name":"NARI Group (China)","ror":"https://ror.org/02egn3136","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210118629"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Wang","raw_affiliation_strings":["NARI Group Corporation (State Grid Electric Power Research Institute), China and China Realtime Database Co., Ltd., China"],"affiliations":[{"raw_affiliation_string":"NARI Group Corporation (State Grid Electric Power Research Institute), China and China Realtime Database Co., Ltd., China","institution_ids":["https://openalex.org/I4210118629"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101890439","display_name":"Jian Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210118629","display_name":"NARI Group (China)","ror":"https://ror.org/02egn3136","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210118629"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Hu","raw_affiliation_strings":["NARI Group Corporation (State Grid Electric Power Research Institute), China and China Realtime Database Co., Ltd., China"],"affiliations":[{"raw_affiliation_string":"NARI Group Corporation (State Grid Electric Power Research Institute), China and China Realtime Database Co., Ltd., China","institution_ids":["https://openalex.org/I4210118629"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5055182013"],"corresponding_institution_ids":["https://openalex.org/I4210118629"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12744534,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987000226974487,"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":0.9976999759674072,"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/transformer","display_name":"Transformer","score":0.7277481555938721},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.7114837169647217},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6974320411682129},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5409989356994629},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5302923321723938},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48671868443489075},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.421130508184433},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3598589599132538},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1691211462020874},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.13208946585655212},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12778401374816895}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7277481555938721},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7114837169647217},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6974320411682129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5409989356994629},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5302923321723938},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48671868443489075},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.421130508184433},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3598589599132538},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1691211462020874},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.13208946585655212},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12778401374816895},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3607822.3616409","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3607822.3616409","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM Symposium on Spatial User Interaction","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":29,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2007057886","https://openalex.org/W2194775991","https://openalex.org/W2883697687","https://openalex.org/W2888096830","https://openalex.org/W2962844592","https://openalex.org/W2963097937","https://openalex.org/W2982232158","https://openalex.org/W2984933298","https://openalex.org/W3009811369","https://openalex.org/W3034934229","https://openalex.org/W3035598501","https://openalex.org/W3090476579","https://openalex.org/W3096609285","https://openalex.org/W3136469583","https://openalex.org/W3171169846","https://openalex.org/W3174164794","https://openalex.org/W3174480456","https://openalex.org/W3181762391","https://openalex.org/W3191257570","https://openalex.org/W3212153990","https://openalex.org/W4206834126","https://openalex.org/W4210478666","https://openalex.org/W4223989014","https://openalex.org/W4285545380","https://openalex.org/W4306407769","https://openalex.org/W4365420337","https://openalex.org/W4381736004","https://openalex.org/W4382279290"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4390721878"],"abstract_inverted_index":{"Human-Object":[0],"Interaction":[1],"task":[2],"(HOI)":[3],"aims":[4],"to":[5,58,65,68,78,83,109],"detect":[6,37],"all":[7],"<human,":[8],"action,":[9],"object>":[10],"triplets":[11],"in":[12,40,86],"the":[13,45,50,69,75,80,84,87,92,96,101,104,123,131],"image":[14],"that":[15],"exist":[16],"interaction.":[17],"General":[18],"methods":[19],"contain":[20],"two-stage":[21],"and":[22,90,119,127,130],"one-stage":[23],"algorithms.":[24],"Recently,":[25],"some":[26],"works":[27],"based":[28],"on":[29,122],"Transformer":[30,64],"have":[31],"been":[32],"proposed.":[33],"Transformer-based":[34],"approaches":[35],"directly":[36],"HOI":[38,52,70],"relationships":[39],"an":[41],"end-to-end":[42],"way,":[43],"making":[44],"whole":[46],"pipeline":[47],"simpler.":[48],"For":[49],"existing":[51],"detection":[53,71],"model":[54],"HOTR,":[55],"we":[56],"aim":[57],"optimize":[59],"its":[60],"internal":[61],"structure":[62,77],"of":[63,103],"better":[66],"adapt":[67],"task.":[72],"We":[73],"use":[74],"residual":[76],"strengthen":[79],"components":[81],"related":[82],"interaction":[85,88],"detection,":[89],"input":[91],"enhanced":[93],"results":[94],"into":[95],"next":[97],"decoder":[98],"layer.":[99],"Finally,":[100],"accuracy":[102,132],"baseline":[105],"method":[106],"is":[107,114],"improved":[108,115],"a":[110],"certain":[111],"extent,":[112],"which":[113],"by":[116],"1.44%":[117],"mAP":[118,121],"3.21%":[120],"benchmark":[124],"datasets":[125],"V-COCO":[126],"HICO-DET":[128],"respectively,":[129],"exceeds":[133],"most":[134],"mainstream":[135],"methods.":[136]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}