{"id":"https://openalex.org/W4316660557","doi":"https://doi.org/10.1109/vcip56404.2022.10008855","title":"Mask-Guided Transformer for Human-Object Interaction Detection","display_name":"Mask-Guided Transformer for Human-Object Interaction Detection","publication_year":2022,"publication_date":"2022-12-13","ids":{"openalex":"https://openalex.org/W4316660557","doi":"https://doi.org/10.1109/vcip56404.2022.10008855"},"language":"en","primary_location":{"id":"doi:10.1109/vcip56404.2022.10008855","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/vcip56404.2022.10008855","pdf_url":null,"source":{"id":"https://openalex.org/S4363608486","display_name":"2022 IEEE International Conference on Visual Communications and Image Processing (VCIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Visual Communications and Image Processing (VCIP)","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":"https://openalex.org/A5062105355","display_name":"Daocheng Ying","orcid":null},"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":"Daocheng Ying","raw_affiliation_strings":["Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University,Shanghai Key Lab of Digital Media Processing and Transmission,Shanghai,China","MoE Key Lab of Artificial Intelligence, AI Institute Shanghai Jiao Tong University, China","Shanghai Key Lab of Digital Media Processing and Transmission, Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University,Shanghai Key Lab of Digital Media Processing and Transmission,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Key Lab of Digital Media Processing and Transmission, Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004324946","display_name":"Hua Yang","orcid":"https://orcid.org/0000-0002-5430-5630"},"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":"Hua Yang","raw_affiliation_strings":["Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University,Shanghai Key Lab of Digital Media Processing and Transmission,Shanghai,China","MoE Key Lab of Artificial Intelligence, AI Institute Shanghai Jiao Tong University, China","Shanghai Key Lab of Digital Media Processing and Transmission, Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University,Shanghai Key Lab of Digital Media Processing and Transmission,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Key Lab of Digital Media Processing and Transmission, Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101761197","display_name":"Jun Sun","orcid":"https://orcid.org/0000-0001-6864-0803"},"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":"Jun Sun","raw_affiliation_strings":["Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University,Shanghai Key Lab of Digital Media Processing and Transmission,Shanghai,China","MoE Key Lab of Artificial Intelligence, AI Institute Shanghai Jiao Tong University, China","Shanghai Key Lab of Digital Media Processing and Transmission, Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University,Shanghai Key Lab of Digital Media Processing and Transmission,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Key Lab of Digital Media Processing and Transmission, Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20091252,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","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":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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":0.9994999766349792,"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/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":0.7773556709289551},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7596007585525513},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7448738813400269},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.678005576133728},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5477404594421387},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5395935773849487},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.45428964495658875},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.44054871797561646},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33227065205574036},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.13469141721725464},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1290615200996399}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7773556709289551},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7596007585525513},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7448738813400269},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.678005576133728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5477404594421387},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5395935773849487},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45428964495658875},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.44054871797561646},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33227065205574036},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.13469141721725464},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1290615200996399},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"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:10.1109/vcip56404.2022.10008855","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/vcip56404.2022.10008855","pdf_url":null,"source":{"id":"https://openalex.org/S4363608486","display_name":"2022 IEEE International Conference on Visual Communications and Image Processing (VCIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4584818147","display_name":null,"funder_award_id":"62171281","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5382601922","display_name":null,"funder_award_id":"19DZ1209303,20DZ1200203,2021SHZDZXO102","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1551928752","https://openalex.org/W2012210378","https://openalex.org/W2222512263","https://openalex.org/W2888096830","https://openalex.org/W2908510526","https://openalex.org/W2952122856","https://openalex.org/W2962844592","https://openalex.org/W2963097937","https://openalex.org/W2963351448","https://openalex.org/W3095753865","https://openalex.org/W3096609285","https://openalex.org/W3115879670","https://openalex.org/W3171169846","https://openalex.org/W3174164794","https://openalex.org/W3174480456","https://openalex.org/W4200630800","https://openalex.org/W4385245566","https://openalex.org/W6632922691","https://openalex.org/W6639102338","https://openalex.org/W6739901393","https://openalex.org/W6754152559","https://openalex.org/W6757817989","https://openalex.org/W6778485988","https://openalex.org/W6785527955","https://openalex.org/W6787891590","https://openalex.org/W6805242730"],"related_works":["https://openalex.org/W4313561376","https://openalex.org/W3103825105","https://openalex.org/W3027880158","https://openalex.org/W3207533102","https://openalex.org/W1617565119","https://openalex.org/W160381218","https://openalex.org/W2512958550","https://openalex.org/W2004102934","https://openalex.org/W4366455350","https://openalex.org/W2329266651"],"abstract_inverted_index":{"Human-object":[0],"interaction":[1],"(HOI)":[2],"detection":[3,50,119],"is":[4,43,79],"a":[5,65,86,109],"meaningful":[6],"research":[7],"topic":[8],"on":[9,21,30,115],"human":[10,42],"activity":[11],"understanding.":[12],"Recent":[13],"works":[14],"have":[15],"made":[16],"significant":[17],"progress":[18],"by":[19,54,94],"focusing":[20],"efficient":[22],"triplet":[23],"matching":[24],"and":[25,45,105],"leveraging":[26],"image-wide":[27],"features":[28],"based":[29],"encoder-decoder":[31],"architecture.":[32],"However,":[33],"the":[34,101,116],"ability":[35],"to":[36],"gather":[37],"relevant":[38],"contextual":[39],"information":[40],"about":[41],"limited":[44],"different":[46],"sub-tasks":[47],"in":[48,57],"HOI":[49,70,118],"are":[51],"not":[52,89],"differentiated":[53],"specific":[55],"decoupling":[56],"previous":[58],"methods.":[59],"To":[60],"this":[61],"end,":[62],"we":[63],"propose":[64],"new":[66],"transformer-based":[67],"method":[68],"for":[69],"detection,":[71],"namely,":[72],"Mask-Guided":[73],"Transformer":[74],"(MGT).":[75],"Our":[76],"model,":[77],"which":[78],"composed":[80],"of":[81,103],"five":[82],"parallel":[83],"decoders":[84],"with":[85],"shared":[87],"encoder,":[88],"only":[90],"emphasizes":[91],"interactive":[92],"regions":[93],"applying":[95],"body":[96],"features,":[97],"but":[98],"also":[99],"disentangles":[100],"prediction":[102],"instance":[104],"interaction.":[106],"We":[107],"achieve":[108],"favorable":[110],"result":[111],"at":[112],"63.3":[113],"mAP":[114],"well-known":[117],"dataset":[120],"V-COCO.":[121]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}