{"id":"https://openalex.org/W4416214886","doi":"https://doi.org/10.1109/tmm.2025.3632627","title":"ASK-HOI: Affordance-Scene Knowledge Prompting for Human-Object Interaction Detection","display_name":"ASK-HOI: Affordance-Scene Knowledge Prompting for Human-Object Interaction Detection","publication_year":2025,"publication_date":"2025-11-14","ids":{"openalex":"https://openalex.org/W4416214886","doi":"https://doi.org/10.1109/tmm.2025.3632627"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2025.3632627","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3632627","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/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 Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2011-100X","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dehui Kong","orcid":"https://orcid.org/0000-0001-7722-7172"},"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 Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7722-7172","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009890293","display_name":"Junna Gao","orcid":"https://orcid.org/0000-0002-0804-8688"},"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"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210152042","display_name":"Beijing Polytechnic","ror":"https://ror.org/03xgzn792","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junna Gao","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Polytechnic University, Beijing, China","Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0804-8688","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Polytechnic University, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210152042"]},{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101612294","display_name":"Jinghua Li","orcid":"https://orcid.org/0000-0001-6895-6672"},"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 Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6895-6672","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006266192","display_name":"Qianxing Li","orcid":"https://orcid.org/0009-0000-6088-0706"},"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":"Qianxing Li","raw_affiliation_strings":["Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-6088-0706","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":null,"display_name":"Baocai Yin","orcid":"https://orcid.org/0000-0003-3121-1823"},"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 Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3121-1823","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0951,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.79886112,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"28","issue":null,"first_page":"742","last_page":"756"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8030999898910522,"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":0.8030999898910522,"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":0.049800001084804535,"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":0.031700000166893005,"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/affordance","display_name":"Affordance","score":0.7894999980926514},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6723999977111816},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5625},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5407999753952026},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5357000231742859},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4652999937534332},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4537000060081482},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44190001487731934},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.396699994802475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8392000198364258},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.7894999980926514},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6723999977111816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6410999894142151},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5625},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5407999753952026},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5357000231742859},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4652999937534332},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4537000060081482},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45210000872612},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44190001487731934},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.396699994802475},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.375},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.34470000863075256},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.33250001072883606},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C84685590","wikidata":"https://www.wikidata.org/wiki/Q1540472","display_name":"Knowledge engineering","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.26649999618530273},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.2644999921321869}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3632627","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3632627","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6212863906","display_name":null,"funder_award_id":"U21B2038","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8638362840","display_name":null,"funder_award_id":"62172022","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8929940274","display_name":null,"funder_award_id":"62476179","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2194775991","https://openalex.org/W2423576022","https://openalex.org/W2589335264","https://openalex.org/W2623040213","https://openalex.org/W2732026016","https://openalex.org/W2789158025","https://openalex.org/W2801004733","https://openalex.org/W2810685774","https://openalex.org/W2885885306","https://openalex.org/W2888096830","https://openalex.org/W2896659472","https://openalex.org/W2962844592","https://openalex.org/W2963097937","https://openalex.org/W2963351448","https://openalex.org/W2964225075","https://openalex.org/W2976818183","https://openalex.org/W2997150218","https://openalex.org/W3034563158","https://openalex.org/W3034934229","https://openalex.org/W3034951775","https://openalex.org/W3035598501","https://openalex.org/W3049440217","https://openalex.org/W3087975588","https://openalex.org/W3095753865","https://openalex.org/W3096609285","https://openalex.org/W3106121867","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/W3174525637","https://openalex.org/W3179066717","https://openalex.org/W3181762391","https://openalex.org/W3197395033","https://openalex.org/W3215084804","https://openalex.org/W4285116117","https://openalex.org/W4295935152","https://openalex.org/W4311597143","https://openalex.org/W4312446811","https://openalex.org/W4312695182","https://openalex.org/W4312770707","https://openalex.org/W4312956471","https://openalex.org/W4312960102","https://openalex.org/W4313136445","https://openalex.org/W4319998180","https://openalex.org/W4328007341","https://openalex.org/W4379929708","https://openalex.org/W4382998830","https://openalex.org/W4385245566","https://openalex.org/W4385815576","https://openalex.org/W4386057783","https://openalex.org/W4386065350","https://openalex.org/W4386065740","https://openalex.org/W4386071869","https://openalex.org/W4386076271","https://openalex.org/W4386076501","https://openalex.org/W4386076683","https://openalex.org/W4386108484","https://openalex.org/W4386832335","https://openalex.org/W4387609200","https://openalex.org/W4387969759","https://openalex.org/W4388486515","https://openalex.org/W4390872009","https://openalex.org/W4390873645","https://openalex.org/W4390874582","https://openalex.org/W4396722842"],"related_works":[],"abstract_inverted_index":{"Human-object":[0],"interaction":[1],"(HOI)":[2],"detection":[3,49],"task":[4],"aims":[5],"to":[6,87,103,107,132,142,162,179,201,229,249],"learn":[7],"how":[8],"humans":[9],"interact":[10],"with":[11,151,253],"surrounding":[12],"objects":[13],"by":[14,168],"inferring":[15],"fine-grained":[16],"triples":[17],"of":[18,135,144,157,214],"<inline-formula":[19],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[20],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[21],"notation=\"LaTeX\">$\\left\\langle":[22],"\\rm":[23],"{\\emph":[24],"{human,":[25],"action,":[26],"object}}":[27],"\\right\\rangle$</tex-math></inline-formula>,":[28],"which":[29],"plays":[30],"a":[31,71,116,195,224],"vital":[32],"role":[33],"in":[34,70],"computer":[35],"vision":[36],"tasks":[37],"such":[38],"as":[39,98],"human-centered":[40],"scene":[41,96,160,196],"understanding":[42],"and":[43,55,78,95,147,159,194,217,240],"visual":[44,203],"question":[45],"answering.":[46],"However,":[47],"HOI":[48,62,105,226,233],"suffers":[50],"from":[51,64],"class":[52],"long-tailed":[53],"distributions":[54],"zero-shot":[56],"problems.":[57],"Current":[58],"methods":[59],"typically":[60],"identify":[61],"only":[63],"input":[65,164],"images":[66],"or":[67],"label":[68],"spaces":[69],"data-driven":[72],"manner,":[73],"lacking":[74],"sufficient":[75],"knowledge":[76,97,119,124,140,149,156,172,177,208,218],"prompts,":[77],"consequently":[79],"limits":[80],"their":[81],"potential":[82],"for":[83],"real-world":[84],"scenes.":[85],"Hence,":[86],"fill":[88],"this":[89,91,176],"gap,":[90],"paper":[92],"introduces":[93],"affordance":[94,158],"prompts":[99],"on":[100,237],"different":[101,183,215],"granularities":[102],"the":[104,133,139,148,152,155,163,180,207,245,254],"detector":[106],"improve":[108],"its":[109],"recognition":[110,227],"ability.":[111],"Concretely,":[112],"we":[113,185],"first":[114],"construct":[115],"large-scale":[117],"affordance-scene":[118],"graph,":[120],"named":[121],"ASKG,":[122],"whose":[123],"can":[125],"be":[126],"divided":[127],"into":[128,223],"two":[129,211],"categories":[130],"according":[131],"fields":[134,216],"image":[136,165,181],"information,":[137],"i.e.,":[138],"related":[141],"affordances":[143],"object":[145],"instances":[146],"associated":[150],"scene.":[153],"Subsequently,":[154],"specific":[161],"is":[166],"extracted":[167],"an":[169,188],"ASKG-based":[170],"prior":[171],"embedding":[173],"module.":[174],"Since":[175],"corresponds":[178],"at":[182],"granularities,":[184],"then":[186],"propose":[187],"instance":[189],"field":[190,197],"adaptive":[191,198],"fusion":[192,199],"module":[193,200,228],"enable":[202],"features":[204,213],"fully":[205],"absorb":[206],"prompts.":[209],"These":[210],"encoded":[212],"embeddings":[219],"are":[220],"finally":[221],"fed":[222],"proposed":[225,246],"predict":[230],"more":[231],"accurate":[232],"results.":[234],"Extensive":[235],"experiments":[236],"both":[238],"HICO-DET":[239],"V-COCO":[241],"benchmarks":[242],"demonstrate":[243],"that":[244],"method":[247],"leads":[248],"competitive":[250],"results":[251],"compared":[252],"state-of-the-art":[255],"methods.":[256]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-11-14T00:00:00"}