{"id":"https://openalex.org/W4402351863","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650093","title":"Dual-Branch Knowledge Enhancement Network with Vision-Language Model for Human-Object Interaction Detection","display_name":"Dual-Branch Knowledge Enhancement Network with Vision-Language Model for Human-Object Interaction Detection","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402351863","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650093"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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/A5109778669","display_name":"Guangpu Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangpu Zhou","raw_affiliation_strings":["Beijing University of Technology,Department of Information,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Department of Information,Beijing,China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090117724","display_name":"Dehui Kong","orcid":"https://orcid.org/0000-0003-1890-6911"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dehui Kong","raw_affiliation_strings":["Beijing University of Technology,Department of Information,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Department of Information,Beijing,China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100600766","display_name":"Jinghua Li","orcid":"https://orcid.org/0000-0002-8476-9460"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinghua Li","raw_affiliation_strings":["Beijing University of Technology,Department of Information,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Department of Information,Beijing,China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039567778","display_name":"Dongpan Chen","orcid":"https://orcid.org/0000-0003-2011-100X"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongpan Chen","raw_affiliation_strings":["Beijing University of Technology,Department of Information,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Department of Information,Beijing,China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101389903","display_name":"Zhuowei Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuowei Bai","raw_affiliation_strings":["Beijing University of Technology,Department of Information,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Department of Information,Beijing,China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102834580","display_name":"Baocai Yin","orcid":"https://orcid.org/0000-0002-8125-4648"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baocai Yin","raw_affiliation_strings":["Beijing University of Technology,Department of Information,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Department of Information,Beijing,China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"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":0.9998999834060669,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9987999796867371,"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":0.998199999332428,"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":0.7352890968322754},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6523830890655518},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5174298882484436},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5144505500793457},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.48379701375961304},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.405517041683197},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.18733209371566772},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08308213949203491}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7352890968322754},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6523830890655518},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5174298882484436},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5144505500793457},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.48379701375961304},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.405517041683197},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.18733209371566772},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08308213949203491},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1551928752","https://openalex.org/W2077069816","https://openalex.org/W2302086703","https://openalex.org/W2884822772","https://openalex.org/W2888096830","https://openalex.org/W2888814092","https://openalex.org/W2890531016","https://openalex.org/W2908510526","https://openalex.org/W2955882737","https://openalex.org/W2962844592","https://openalex.org/W2963076818","https://openalex.org/W2963097937","https://openalex.org/W2963351448","https://openalex.org/W2964225075","https://openalex.org/W2990599624","https://openalex.org/W2997150218","https://openalex.org/W3009811369","https://openalex.org/W3034934229","https://openalex.org/W3035598501","https://openalex.org/W3090476579","https://openalex.org/W3095753865","https://openalex.org/W3096609285","https://openalex.org/W3097802466","https://openalex.org/W3106121867","https://openalex.org/W3106988096","https://openalex.org/W3109754877","https://openalex.org/W3151099711","https://openalex.org/W3168279596","https://openalex.org/W3168488421","https://openalex.org/W3171169846","https://openalex.org/W3174164794","https://openalex.org/W3174480456","https://openalex.org/W3197395033","https://openalex.org/W3212153990","https://openalex.org/W4226451294","https://openalex.org/W4312446811","https://openalex.org/W4312770707","https://openalex.org/W4312960102","https://openalex.org/W4385245566","https://openalex.org/W4386057783","https://openalex.org/W4386071869","https://openalex.org/W4386076501","https://openalex.org/W4388514595","https://openalex.org/W4390872886","https://openalex.org/W4390874582","https://openalex.org/W6632922691","https://openalex.org/W6754152559","https://openalex.org/W6757817989","https://openalex.org/W6785527955","https://openalex.org/W6791353385","https://openalex.org/W6799822930","https://openalex.org/W6857487352"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Human-Object":[0],"Interaction":[1],"(HOI)":[2],"detection":[3,26],"aims":[4],"to":[5,35,38,59,72,104,140],"localize":[6],"human-object":[7],"pairs":[8],"and":[9,75,148],"comprehend":[10],"their":[11,20],"interactions.":[12],"Recently,":[13],"pre-trained":[14],"Vision-Language":[15],"Models":[16],"(VLM)":[17],"have":[18],"shown":[19],"great":[21],"recognition":[22],"ability":[23],"in":[24],"HOI":[25,131],"task.":[27],"However,":[28],"these":[29],"VLM":[30,53,129],"based":[31],"methods":[32,142],"are":[33],"struggle":[34],"transfer":[36,108],"knowledge":[37,86,107],"achieve":[39],"desired":[40],"performance.":[41],"To":[42],"this":[43],"end,":[44],"we":[45,66,94],"propose":[46,67,95],"a":[47,68,84,96],"Dual-Branch":[48],"Knowledge":[49],"Enhancement":[50],"Network":[51],"with":[52,89],"(DBKEN-VLM)":[54],"within":[55],"the":[56,61,101,126],"two-stage":[57],"paradigm":[58],"enhance":[60],"effectiveness":[62],"of":[63,109,128],"VLM.":[64,110],"Specifically,":[65],"semantic":[69,77],"mining":[70],"decoder":[71],"supplement":[73],"contextual":[74],"action-related":[76],"information":[78],"into":[79],"our":[80],"model.":[81],"It":[82],"forms":[83],"dual-branch":[85],"enhancement":[87],"network":[88,103],"spatial":[90],"guided":[91],"decoder.":[92],"Furthermore,":[93],"two-level":[97],"fusion":[98],"strategy":[99],"for":[100,130],"dualbranch":[102],"facilitate":[105],"better":[106],"One":[111],"is":[112,121],"feature-level":[113],"fusion,":[114,123],"producing":[115],"more":[116],"instructive":[117],"interaction":[118],"features;":[119],"another":[120],"decision-level":[122],"further":[124],"enhancing":[125],"capability":[127],"detection.":[132],"The":[133],"proposed":[134],"method":[135],"achieves":[136],"competitive":[137],"performance":[138],"compared":[139],"recent":[141],"on":[143],"two":[144],"benchmark":[145],"datasets,":[146],"HICO-DET":[147],"V-COCO.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}