{"id":"https://openalex.org/W7165807763","doi":"https://doi.org/10.1109/tip.2026.3705170","title":"Language-Driven Visual Data Generation for Zero-Shot HOI Detection","display_name":"Language-Driven Visual Data Generation for Zero-Shot HOI Detection","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7165807763","doi":"https://doi.org/10.1109/tip.2026.3705170","pmid":"https://pubmed.ncbi.nlm.nih.gov/42340906"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3705170","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3705170","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5139281123","display_name":"Pei Geng","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pei Geng","raw_affiliation_strings":["PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412142","display_name":"Shanshan Zhang","orcid":"https://orcid.org/0000-0003-4013-6300"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanshan Zhang","raw_affiliation_strings":["PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4013-6300","affiliations":[{"raw_affiliation_string":"PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100726984","display_name":"Jian Yang","orcid":"https://orcid.org/0000-0003-4800-832X"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4800-832X","affiliations":[{"raw_affiliation_string":"PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.83035337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"6876","last_page":"6885"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6958000063896179,"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":0.6958000063896179,"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/T10799","display_name":"Data Visualization and Analytics","score":0.04439999908208847,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.03229999914765358,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42260000109672546},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.41929998993873596},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.3813999891281128},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.3531999886035919},{"id":"https://openalex.org/keywords/data-visualization","display_name":"Data visualization","score":0.3377000093460083},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.3345000147819519},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3109000027179718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.727400004863739},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6585000157356262},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6506999731063843},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3813999891281128},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3531999886035919},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.3377000093460083},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3345000147819519},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2840000092983246},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27709999680519104},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C92630104","wikidata":"https://www.wikidata.org/wiki/Q4115103","display_name":"Optical imaging","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3705170","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3705170","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:42340906","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42340906","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6360242122","display_name":null,"funder_award_id":"62322602","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7877036025","display_name":null,"funder_award_id":"BK20230033","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Zero-shot":[0],"human-object":[1],"interaction":[2,12],"(HOI)":[3],"detection":[4],"aims":[5],"to":[6,24,42,44,79,95,119,162],"recognize":[7],"both":[8],"seen":[9,38,104,157],"and":[10,17,40,99,137],"unseen":[11,31,45,70,80,111,177,204],"categories":[13,205],"while":[14],"detecting":[15],"humans":[16],"objects":[18],"in":[19],"an":[20,74],"image.":[21],"However,":[22],"due":[23],"the":[25,115,134,144,191],"absence":[26],"of":[27,69,176],"training":[28],"samples":[29],"for":[30],"categories,":[32],"existing":[33],"methods":[34],"often":[35],"overfit":[36],"on":[37,84,103,126,186,203],"HOIs":[39,81,105,158,178],"struggle":[41],"generalize":[43],"ones.":[46],"To":[47],"address":[48],"this":[49,169],"issue,":[50],"we":[51,88,113],"introduce":[52],"a":[53,91,164],"novel":[54],"Language-Driven":[55],"Visual":[56],"Data":[57],"Generation":[58],"(LD-VDG)":[59],"approach":[60],"that":[61,190],"generates":[62],"pseudo":[63,140,150],"visual":[64,85,100,141,182],"features":[65,142,151,155],"from":[66,156],"textual":[67,123],"semantics":[68],"HOIs.":[71],"This":[72],"provides":[73],"innovative":[75],"solution":[76],"enabling":[77],"generalization":[78],"without":[82],"relying":[83],"samples.":[86],"Specifically,":[87],"first":[89],"design":[90],"text-to-vision":[92],"(T-V)":[93],"adapter":[94],"align":[96],"HOI":[97,127,166],"text":[98],"features,":[101],"trained":[102],"with":[106,153],"paired":[107],"image-text":[108],"data.":[109],"For":[110],"HOIs,":[112],"guide":[114],"large":[116],"language":[117],"model":[118,136],"produce":[120],"multiple":[121],"fine-grained":[122],"descriptions":[124],"based":[125],"labels,":[128],"which":[129],"are":[130,159],"then":[131],"encoded":[132],"by":[133,179],"vision-language":[135],"transformed":[138],"into":[139],"via":[143],"T-V":[145],"adapter.":[146],"After":[147],"that,":[148],"these":[149],"together":[152],"real":[154],"jointly":[160],"used":[161],"train":[163],"transformer-based":[165],"detector.":[167],"In":[168,197],"way,":[170],"our":[171],"method":[172],"enables":[173],"effective":[174],"recognition":[175],"leveraging":[180],"language-driven":[181],"representations.":[183],"Experimental":[184],"results":[185],"standard":[187],"datasets":[188],"demonstrate":[189],"proposed":[192],"LD-VDG":[193],"outperforms":[194],"previous":[195],"methods.":[196],"particular,":[198],"it":[199],"achieves":[200],"superior":[201],"performance":[202],"under":[206],"various":[207],"zero-shot":[208],"settings.":[209]},"counts_by_year":[],"updated_date":"2026-06-30T06:16:30.551410","created_date":"2026-06-25T00:00:00"}