{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T06:03:02Z","timestamp":1780639382246,"version":"3.54.1"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Linkage Project","award":["LP210300009"],"award-info":[{"award-number":["LP210300009"]}]},{"name":"Linkage Project","award":["LP230100083"],"award-info":[{"award-number":["LP230100083"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3660167","type":"journal-article","created":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T20:55:41Z","timestamp":1770152141000},"page":"3932-3944","source":"Crossref","is-referenced-by-count":0,"title":["Dual Visual Prompting With Context-Modulated Diffusion Prompts"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3693-8576","authenticated-orcid":false,"given":"Huan","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computing and Information Technology, University of Wollongong, Wollongong, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0868-9554","authenticated-orcid":false,"given":"Haoran","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computing and Information Technology, University of Wollongong, Wollongong, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5678-472X","authenticated-orcid":false,"given":"Huaming","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Electrical & Computer Engineering, University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6474-1049","authenticated-orcid":false,"given":"Jun","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Computing and Information Technology, University of Wollongong, Wollongong, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4933-0081","authenticated-orcid":false,"given":"Jiahua","family":"Shi","sequence":"additional","affiliation":[{"name":"Centre for Nutrition and Food Sciences, University of Queensland, Brisbane, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9403-7140","authenticated-orcid":false,"given":"Jun","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Computing and Information Technology, University of Wollongong, Wollongong, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"An image is worth 16  16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref2","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01805"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01075"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02722"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3325965"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3358112"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00556"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02550"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1049\/icp.2023.2947"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref16","article-title":"Exploring visual prompts for adapting large-scale models","author":"Bahng","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3413318"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3310282"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.167"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539382"},{"key":"ref21","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref22","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00210"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2571"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0068"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1973"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref31","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01359"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.24818\/ida-ql\/2019.5"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3648307"},{"key":"ref37","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu","year":"2019"},{"key":"ref38","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref39","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00414"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1561\/0600000105"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00490"},{"key":"ref43","first-page":"61060","article-title":"InfoPrompt: Information-theoretic soft prompt tuning for natural language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00772"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02513"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02181"},{"key":"ref50","first-page":"47500","article-title":"Diffusion Hyperfeatures: Searching through time and space for semantic correspondence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Luo","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref52","first-page":"47783","article-title":"Understanding and mitigating copying in diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Somepalli","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"},{"key":"ref54","first-page":"6216","article-title":"Data determines distributional robustness in contrastive language image pre-training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fang","year":"2022"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref56","first-page":"7002","article-title":"Loss function learning for domain generalization by implicit gradient","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gao","year":"2022"},{"key":"ref57","first-page":"794","article-title":"GradNorm: Gradient normalization for adaptive loss balancing in deep multitask networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2018"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5724-z"},{"key":"ref59","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"ref60","first-page":"40075","article-title":"Improving visual prompt tuning for self-supervised vision transformers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yoo","year":"2023"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_15"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29766"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref73","first-page":"5389","article-title":"Do ImageNet classifiers generalize to ImageNet?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht","year":"2019"},{"key":"ref74","first-page":"10506","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2019"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref78","first-page":"1","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Podell","year":"2024"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11370236.pdf?arnumber=11370236","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:22:42Z","timestamp":1780636962000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11370236\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3660167","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}