{"id":"https://openalex.org/W4402387113","doi":"https://doi.org/10.1145/3664647.3680927","title":"Unseen No More: Unlocking the Potential of CLIP for Generative Zero-shot HOI Detection","display_name":"Unseen No More: Unlocking the Potential of CLIP for Generative Zero-shot HOI Detection","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4402387113","doi":"https://doi.org/10.1145/3664647.3680927"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680927","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680927","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2408.05974","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111541476","display_name":"Yi Guo","orcid":"https://orcid.org/0000-0003-0736-0992"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yixin Guo","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004895426","display_name":"Yu Liu","orcid":"https://orcid.org/0000-0002-2067-9175"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Liu","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059603338","display_name":"Jianghao Li","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianghao Li","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042192401","display_name":"Weimin Wang","orcid":"https://orcid.org/0000-0001-6557-7175"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weimin Wang","raw_affiliation_strings":["Dalian University of Techonoly, Dalian, China","Dalian University of Technology Dalian, China"],"affiliations":[{"raw_affiliation_string":"Dalian University of Techonoly, Dalian, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"Dalian University of Technology Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101812176","display_name":"Qi Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Jia","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5111541476"],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":2.3749,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.9020215,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1711","last_page":"1720"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"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":0.9983999729156494,"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":0.7335407733917236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6807229518890381},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5377647280693054},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5128543376922607},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5045551061630249},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4924825131893158},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.46262550354003906},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4428308606147766},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43829113245010376},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43460750579833984},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4316948652267456},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3438577651977539}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7335407733917236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6807229518890381},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5377647280693054},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5128543376922607},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5045551061630249},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4924825131893158},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.46262550354003906},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4428308606147766},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43829113245010376},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43460750579833984},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4316948652267456},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3438577651977539},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3680927","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680927","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2408.05974","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.05974","pdf_url":"https://arxiv.org/pdf/2408.05974","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2408.05974","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.05974","pdf_url":"https://arxiv.org/pdf/2408.05974","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2634789579","display_name":null,"funder_award_id":"62102061","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G331381905","display_name":null,"funder_award_id":"62272083","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7836423780","display_name":null,"funder_award_id":"Liaoning","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8845200034","display_name":null,"funder_award_id":"62306059","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4402387113.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2596164567","https://openalex.org/W2607662938","https://openalex.org/W2888814092","https://openalex.org/W2962844592","https://openalex.org/W2963283377","https://openalex.org/W2964225075","https://openalex.org/W2997150218","https://openalex.org/W3000538487","https://openalex.org/W3034199269","https://openalex.org/W3049440217","https://openalex.org/W3096831136","https://openalex.org/W3101631402","https://openalex.org/W3129157062","https://openalex.org/W3132217314","https://openalex.org/W3159481202","https://openalex.org/W3168279596","https://openalex.org/W3168488421","https://openalex.org/W3174164794","https://openalex.org/W3197395033","https://openalex.org/W3198377975","https://openalex.org/W3201927751","https://openalex.org/W4284681282","https://openalex.org/W4286611314","https://openalex.org/W4312241193","https://openalex.org/W4312343844","https://openalex.org/W4312446811","https://openalex.org/W4312848112","https://openalex.org/W4312960102","https://openalex.org/W4382240040","https://openalex.org/W4386071869","https://openalex.org/W4386072519","https://openalex.org/W4386075985","https://openalex.org/W4386076374","https://openalex.org/W4386790226","https://openalex.org/W4387341288","https://openalex.org/W4387968023","https://openalex.org/W4388210825","https://openalex.org/W4390872886","https://openalex.org/W4390874582","https://openalex.org/W4394625696"],"related_works":["https://openalex.org/W2487162673","https://openalex.org/W2793211469","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W2942366970","https://openalex.org/W2807634898","https://openalex.org/W1692008701","https://openalex.org/W2597588799","https://openalex.org/W1968265719","https://openalex.org/W2971551846"],"abstract_inverted_index":{"Zero-shot":[0],"human-object":[1],"interaction":[2],"(HOI)":[3],"detector":[4],"is":[5,211],"capable":[6],"of":[7,100,106,124,135],"generalizing":[8],"to":[9,29,96,148],"HOI":[10,36,90,158,169,180],"categories":[11],"even":[12],"not":[13],"encountered":[14],"during":[15,57],"training.":[16],"Inspired":[17],"by":[18,24],"the":[19,43,55,69,82,98,122,146,157],"impressive":[20],"zero-shot":[21,35,89,203],"capabilities":[22],"offered":[23],"CLIP,":[25],"latest":[26],"methods":[27,41],"strive":[28],"leverage":[30],"CLIP":[31,87,101],"embeddings":[32],"for":[33,54,88,102,195],"improving":[34],"detection.":[37],"However,":[38],"these":[39],"embedding-based":[40],"train":[42,149],"classifier":[44],"on":[45,186],"seen":[46,72,136,150,197],"classes":[47,153,200],"only,":[48],"inevitably":[49],"resulting":[50],"in":[51,119,166,177],"seen-unseen":[52],"confusion":[53],"model":[56,85,147],"inference.":[58],"Besides,":[59],"we":[60,80,113,131,160],"find":[61],"that":[62],"using":[63,86],"prompt-tuning":[64],"and":[65,73,127,138,151,172,198],"adapters":[66],"further":[67],"increases":[68],"gap":[70],"between":[71],"unseen":[74,152,199],"accuracy.":[75],"To":[76,110,155],"tackle":[77],"this":[78],"challenge,":[79],"present":[81],"first":[83],"generation-based":[84],"detection,":[91],"coined":[92],"HOIGen.":[93],"It":[94],"allows":[95],"unlock":[97],"potential":[99],"feature":[103,107,117],"generation":[104,123],"instead":[105],"extraction":[108],"only.":[109],"achieve":[111],"it,":[112],"develop":[114],"a":[115,162,167,173],"CLIP-injected":[116],"generator":[118],"accordance":[120],"with":[121,141,206],"human,":[125],"object":[126],"union":[128],"features.":[129],"Then,":[130],"extract":[132],"realistic":[133],"features":[134,143],"samples":[137],"mix":[139],"them":[140],"synthetic":[142],"together,":[144],"allowing":[145],"jointly.":[154],"enrich":[156],"scores,":[159],"construct":[161],"generative":[163],"prototype":[164,175],"bank":[165,176],"pairwise":[168],"recognition":[170,181],"branch,":[171,182],"multi-knowledge":[174],"an":[178],"image-wise":[179],"respectively.":[183],"Extensive":[184],"experiments":[185],"HICO-DET":[187],"benchmark":[188],"demonstrate":[189],"our":[190],"HOIGen":[191],"achieves":[192],"superior":[193],"performance":[194],"both":[196],"under":[201],"various":[202],"settings,":[204],"compared":[205],"other":[207],"top-performing":[208],"methods.":[209],"Code":[210],"available":[212],"at:":[213],"https://github.com/soberguo/HOIGen":[214]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}