{"id":"https://openalex.org/W7127291783","doi":"https://doi.org/10.1109/tmm.2026.3660167","title":"Dual Visual Prompting With Context-Modulated Diffusion Prompts","display_name":"Dual Visual Prompting With Context-Modulated Diffusion Prompts","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7127291783","doi":"https://doi.org/10.1109/tmm.2026.3660167"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3660167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3660167","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":null,"display_name":"Huan Wang","orcid":"https://orcid.org/0009-0000-3693-8576"},"institutions":[{"id":"https://openalex.org/I204824540","display_name":"University of Wollongong","ror":"https://ror.org/00jtmb277","country_code":"AU","type":"education","lineage":["https://openalex.org/I204824540"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Huan Wang","raw_affiliation_strings":["School of Computing and Information Technology, University of Wollongong, Wollongong, NSW, Australia"],"raw_orcid":"https://orcid.org/0009-0000-3693-8576","affiliations":[{"raw_affiliation_string":"School of Computing and Information Technology, University of Wollongong, Wollongong, NSW, Australia","institution_ids":["https://openalex.org/I204824540"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327742","display_name":"Haoran Li","orcid":"https://orcid.org/0000-0003-0868-9554"},"institutions":[{"id":"https://openalex.org/I204824540","display_name":"University of Wollongong","ror":"https://ror.org/00jtmb277","country_code":"AU","type":"education","lineage":["https://openalex.org/I204824540"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Haoran Li","raw_affiliation_strings":["School of Computing and Information Technology, University of Wollongong, Wollongong, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0868-9554","affiliations":[{"raw_affiliation_string":"School of Computing and Information Technology, University of Wollongong, Wollongong, NSW, Australia","institution_ids":["https://openalex.org/I204824540"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Huaming Chen","orcid":"https://orcid.org/0000-0001-5678-472X"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Huaming Chen","raw_affiliation_strings":["School of Electrical &amp; Computer Engineering, University of Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-5678-472X","affiliations":[{"raw_affiliation_string":"School of Electrical &amp; Computer Engineering, University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602","https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jun Yan","orcid":"https://orcid.org/0000-0002-6474-1049"},"institutions":[{"id":"https://openalex.org/I204824540","display_name":"University of Wollongong","ror":"https://ror.org/00jtmb277","country_code":"AU","type":"education","lineage":["https://openalex.org/I204824540"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jun Yan","raw_affiliation_strings":["School of Computing and Information Technology, University of Wollongong, Wollongong, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-6474-1049","affiliations":[{"raw_affiliation_string":"School of Computing and Information Technology, University of Wollongong, Wollongong, NSW, Australia","institution_ids":["https://openalex.org/I204824540"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124966766","display_name":"Jiahua Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jiahua Shi","raw_affiliation_strings":["Centre for Nutrition and Food Sciences, University of Queensland, Brisbane, QLD, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4933-0081","affiliations":[{"raw_affiliation_string":"Centre for Nutrition and Food Sciences, University of Queensland, Brisbane, QLD, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124940465","display_name":"Jun Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I204824540","display_name":"University of Wollongong","ror":"https://ror.org/00jtmb277","country_code":"AU","type":"education","lineage":["https://openalex.org/I204824540"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jun Shen","raw_affiliation_strings":["School of Computing and Information Technology, University of Wollongong, Wollongong, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9403-7140","affiliations":[{"raw_affiliation_string":"School of Computing and Information Technology, University of Wollongong, Wollongong, NSW, Australia","institution_ids":["https://openalex.org/I204824540"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11802712,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"3932","last_page":"3944"},"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":0.3402999937534332,"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":0.3402999937534332,"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":0.32280001044273376,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0771000012755394,"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/embedding","display_name":"Embedding","score":0.6633999943733215},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6291999816894531},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.592199981212616},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5842000246047974},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5666999816894531},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43309998512268066},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.39160001277923584},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.36000001430511475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8535000085830688},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6633999943733215},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6291999816894531},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.592199981212616},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5842000246047974},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5666999816894531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5472999811172485},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43309998512268066},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4072999954223633},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.39160001277923584},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3752000033855438},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.36000001430511475},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2757999897003174},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3660167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3660167","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":[],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Prompt":[0],"learning":[1,98],"has":[2],"emerged":[3],"as":[4,135,178],"an":[5],"efficient":[6,139],"tuning":[7],"paradigm":[8],"for":[9,138,181],"fine-tuning":[10,36],"powerful":[11],"pre-trained":[12],"models":[13],"on":[14,24,214],"downstream":[15],"tasks":[16],"in":[17,82,169,206],"specific":[18],"domains.":[19],"Existing":[20],"efforts":[21],"mainly":[22],"focus":[23],"dataset-level":[25,132],"implicit":[26,133,176],"embeddings":[27],"by":[28],"introducing":[29],"extra":[30],"learnable":[31],"parameters":[32],"instead":[33],"of":[34,67,78,146,163,189,204,250,259],"fully":[35],"large-scale":[37],"visual":[38,96,128],"models.":[39],"However,":[40],"we":[41,85,191],"find":[42],"that":[43,118,199,221],"these":[44],"static":[45],"post-training":[46],"prompts":[47,137,180,205],"are":[48],"not":[49],"flexible":[50],"enough":[51],"to":[52,64,94,172,185,234,246],"adapt":[53],"various":[54,215],"input":[55,80,182],"instances":[56],"within":[57],"the":[58,65,68,74,143,147,170,187,201,235,248,257],"same":[59],"dataset,":[60],"which":[61],"might":[62],"lead":[63],"loss":[66],"model's":[69,160],"generalization":[70,231],"capability.":[71],"To":[72],"leverage":[73],"meaningful":[75],"contextual":[76],"information":[77,145],"each":[79,260],"instance,":[81],"this":[83],"paper,":[84],"propose":[86],"a":[87,114,126,154,196],"straightforward":[88],"yet":[89],"effective":[90],"method,":[91],"termed":[92],"CoMoDP,":[93],"enhance":[95],"prompt":[97,129,156],"with":[99],"<italic":[100,105,108,123,151],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[101,103,106,109,124,152],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Co</i>ntext-<italic":[102],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Mo</i>dulated":[104],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">D</i>iffusion":[107],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">P</i>rompts.":[110],"Specifically,":[111],"CoMoDP":[112,255],"is":[113],"dual-visual":[115,252],"prompting":[116,253],"scheme":[117,254],"comprises":[119],"two":[120],"key":[121],"components:":[122],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">(i)":[125],"unified":[127,136],"designer</i>,":[130],"producing":[131],"embedding":[134,177],"adaptation":[140],"without":[141,262],"corrupting":[142],"underlying":[144],"original":[148],"image;":[149],"and":[150,166,209,217,227,243,256],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">(ii)":[153],"diffusion":[155,159,179],"simulator</i>,":[157],"leveraging":[158],"meticulous":[161],"understanding":[162],"semantic":[164],"structure":[165],"texture":[167],"edges":[168],"images":[171],"dynamically":[173],"generate":[174],"instance-level":[175],"samples.":[183],"Moreover,":[184],"reduce":[186],"overfitting":[188],"prompts,":[190],"also":[192,239],"introduce":[193],"momentum":[194],"alignment,":[195],"self-regulating":[197],"strategy":[198],"restricts":[200],"optimization":[202],"region":[203],"both":[207,241],"feature":[208],"logit":[210],"spaces.":[211],"Extensive":[212],"experiments":[213],"standard":[216],"few-shot":[218],"datasets":[219],"demonstrate":[220,240],"our":[222,251],"method":[223],"brings":[224],"substantial":[225],"improvements":[226],"yields":[228],"strong":[229],"domain":[230],"performance,":[232],"compared":[233],"state-of-the-art":[236],"methods.":[237],"We":[238],"zero-shot":[242],"out-of-distribution":[244],"performance":[245],"establish":[247],"utility":[249],"efficiency":[258],"component,":[261],"involving":[263],"excessive":[264],"parameters.":[265]},"counts_by_year":[],"updated_date":"2026-06-05T06:17:00.636019","created_date":"2026-02-04T00:00:00"}