{"id":"https://openalex.org/W4416250256","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227817","title":"Exploring Hierarchical Multi-modal Prompts Learning for HOI Detection via Hybrid Learning","display_name":"Exploring Hierarchical Multi-modal Prompts Learning for HOI Detection via Hybrid Learning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416250256","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227817"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227817","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5101975829","display_name":"Xiaoqian Han","orcid":"https://orcid.org/0000-0002-1385-6794"},"institutions":[{"id":"https://openalex.org/I108688024","display_name":"Qingdao University","ror":"https://ror.org/021cj6z65","country_code":"CN","type":"education","lineage":["https://openalex.org/I108688024"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoqian Han","raw_affiliation_strings":["Qingdao University,School of Computer Science and Technology,Qingdao,China"],"affiliations":[{"raw_affiliation_string":"Qingdao University,School of Computer Science and Technology,Qingdao,China","institution_ids":["https://openalex.org/I108688024"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100353447","display_name":"Xiaowei Zhang","orcid":"https://orcid.org/0000-0002-8619-3346"},"institutions":[{"id":"https://openalex.org/I108688024","display_name":"Qingdao University","ror":"https://ror.org/021cj6z65","country_code":"CN","type":"education","lineage":["https://openalex.org/I108688024"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaowei Zhang","raw_affiliation_strings":["Qingdao University,School of Computer Science and Technology,Qingdao,China"],"affiliations":[{"raw_affiliation_string":"Qingdao University,School of Computer Science and Technology,Qingdao,China","institution_ids":["https://openalex.org/I108688024"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101975829"],"corresponding_institution_ids":["https://openalex.org/I108688024"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34332375,"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":0.9945999979972839,"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":0.9945999979972839,"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":0.0007999999797903001,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0007999999797903001,"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/prior-probability","display_name":"Prior probability","score":0.6599000096321106},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6241999864578247},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.551800012588501},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4999000132083893},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4657999873161316},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4034000039100647},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.34450000524520874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7967000007629395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6600000262260437},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6599000096321106},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6241999864578247},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.551800012588501},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5424000024795532},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4999000132083893},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4657999873161316},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4034000039100647},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.34450000524520874},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3199999928474426},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2964000105857849},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26750001311302185}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227817","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2214124602","https://openalex.org/W3034951775","https://openalex.org/W3035598501","https://openalex.org/W3096609285","https://openalex.org/W3106121867","https://openalex.org/W3168279596","https://openalex.org/W3171169846","https://openalex.org/W3174164794","https://openalex.org/W3174480456","https://openalex.org/W3197395033","https://openalex.org/W3198377975","https://openalex.org/W4312446811","https://openalex.org/W4312574495","https://openalex.org/W4312770707","https://openalex.org/W4312848112","https://openalex.org/W4312960102","https://openalex.org/W4319998180","https://openalex.org/W4382240040","https://openalex.org/W4386071547","https://openalex.org/W4386071869","https://openalex.org/W4386076271","https://openalex.org/W4386076501","https://openalex.org/W4390872886","https://openalex.org/W4390874582","https://openalex.org/W4393149532","https://openalex.org/W4402351863","https://openalex.org/W4402352189","https://openalex.org/W4402772602"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Visual-Language":[1],"Models":[2],"(VLMs)":[3],"have":[4,29],"shown":[5],"great":[6],"potential":[7],"in":[8,157],"providing":[9],"interaction":[10,45],"priors":[11,104],"for":[12,74,141],"Human-Object":[13],"Interaction":[14],"(HOI)":[15],"detection.":[16],"However,":[17],"existing":[18],"VLM-based":[19],"HOI":[20,75,120],"detectors":[21],"mainly":[22],"focus":[23],"on":[24,150],"text":[25],"prompt":[26,38],"learning":[27,72,116],"and":[28,154,160],"yet":[30],"to":[31,42,89,96,105,127],"fully":[32],"explore":[33,107,128],"the":[34,134,139,152],"effectiveness":[35],"of":[36,51],"multimodal":[37,70,91],"learning.":[39],"Additionally,":[40],"due":[41],"annotation":[43],"sparsity,":[44],"head":[46],"generate":[47],"a":[48,57,68,114],"large":[49],"number":[50],"candidate":[52],"human-object":[53],"pairs,":[54],"but":[55],"only":[56],"small":[58],"subset":[59],"is":[60],"supervised.":[61],"To":[62],"address":[63],"these":[64],"challenges,":[65],"we":[66,83,112],"propose":[67],"hierarchical":[69,85],"prompts":[71,87,92],"approach":[73],"detection":[76],"via":[77],"hybrid":[78,115],"learning,":[79],"called":[80],"HMMP.":[81],"Specifically,":[82],"introduce":[84,113],"visual-textual":[86],"designed":[88],"build":[90],"across":[93],"three":[94],"levels":[95],"guide":[97],"knowledge":[98],"transfer":[99],"from":[100],"VLMs,":[101],"incorporating":[102],"spatial":[103],"further":[106],"multi-level":[108],"visual":[109],"information.":[110],"Furthermore,":[111],"method":[117],"that":[118],"combines":[119],"triplets":[121],"with":[122],"probabilistic":[123],"soft":[124],"label":[125],"supervision":[126],"implicit":[129],"relationships":[130],"between":[131],"interactions,":[132],"enhancing":[133],"model\u2019s":[135],"generalization":[136],"ability":[137],"without":[138],"need":[140],"additional":[142],"data.":[143],"Our":[144],"proposed":[145],"HMMP":[146],"achieves":[147],"state-of-the-art":[148],"performance":[149],"both":[151,158],"HICO-DET":[153],"V-COCO":[155],"datasets,":[156],"standard":[159],"zero-shot":[161],"settings.":[162]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-14T00:00:00"}