{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T14:29:37Z","timestamp":1773152977711,"version":"3.50.1"},"reference-count":79,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100003399","name":"Shanghai Municipality Science and Technology Commission","doi-asserted-by":"publisher","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222607"],"award-info":[{"award-number":["62222607"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62002252"],"award-info":[{"award-number":["62002252"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Artificial Intelligence"],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1016\/j.artint.2025.104417","type":"journal-article","created":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T21:32:31Z","timestamp":1757539951000},"page":"104417","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Rethinking visual prompt learning as masked visual token modeling"],"prefix":"10.1016","volume":"348","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3764-2555","authenticated-orcid":false,"given":"Ning","family":"Liao","sequence":"first","affiliation":[]},{"given":"Bowen","family":"Shi","sequence":"additional","affiliation":[]},{"given":"Xiaopeng","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Min","family":"Cao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9639-7679","authenticated-orcid":false,"given":"Junchi","family":"Yan","sequence":"additional","affiliation":[]},{"given":"Qi","family":"Tian","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.artint.2025.104417_br0010","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9729","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2020"},{"key":"10.1016\/j.artint.2025.104417_br0020","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9650","article-title":"Emerging properties in self-supervised vision transformers","author":"Caron","year":"2021"},{"key":"10.1016\/j.artint.2025.104417_br0030","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9640","article-title":"An empirical study of training self-supervised vision transformers","author":"Chen","year":"2021"},{"key":"10.1016\/j.artint.2025.104417_br0040","first-page":"21271","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","volume":"33","author":"Grill","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.artint.2025.104417_br0050","series-title":"Improving Language Understanding by Generative Pre-Training","author":"Radford","year":"2018"},{"key":"10.1016\/j.artint.2025.104417_br0060","article-title":"Unified language model pre-training for natural language understanding and generation","volume":"32","author":"Dong","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.artint.2025.104417_br0070","article-title":"Xlnet: generalized autoregressive pretraining for language understanding","volume":"32","author":"Yang","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.artint.2025.104417_br0080","series-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","first-page":"7871","article-title":"Bart: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","author":"Lewis","year":"2020"},{"issue":"9","key":"10.1016\/j.artint.2025.104417_br0090","first-page":"1","article-title":"Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing","volume":"55","author":"Liu","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.artint.2025.104417_br0100","series-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","article-title":"Language models as knowledge bases?","author":"Petroni","year":"2019"},{"issue":"140","key":"10.1016\/j.artint.2025.104417_br0110","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.artint.2025.104417_br0120","series-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","first-page":"3816","article-title":"Making pre-trained language models better few-shot learners","author":"Gao","year":"2021"},{"key":"10.1016\/j.artint.2025.104417_br0130","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","first-page":"4171","article-title":"Bert: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.artint.2025.104417_br0140","series-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","first-page":"1441","article-title":"Ernie: enhanced language representation with informative entities","author":"Zhang","year":"2019"},{"key":"10.1016\/j.artint.2025.104417_br0150","series-title":"International Conference on Machine Learning","first-page":"1378","article-title":"Ask me anything: dynamic memory networks for natural language processing","author":"Kumar","year":"2016"},{"key":"10.1016\/j.artint.2025.104417_br0160","author":"McCann"},{"key":"10.1016\/j.artint.2025.104417_br0170","series-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","article-title":"Knowledgeable prompt-tuning: incorporating knowledge into prompt verbalizer for text classification","author":"Hu","year":"2022"},{"key":"10.1016\/j.artint.2025.104417_br0180","series-title":"Proceedings of the 28th International Conference on Computational Linguistics","first-page":"5569","article-title":"Automatically identifying words that can serve as labels for few-shot text classification","author":"Schick","year":"2020"},{"key":"10.1016\/j.artint.2025.104417_br0190","series-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","first-page":"7038","article-title":"Surface form competition: why the highest probability answer isn't always right","author":"Holtzman","year":"2021"},{"key":"10.1016\/j.artint.2025.104417_br0200","series-title":"International Conference on Learning Representations","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.artint.2025.104417_br0210","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.artint.2025.104417_br0220","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.artint.2025.104417_br0230","series-title":"European Conference on Computer Vision","first-page":"709","article-title":"Visual prompt tuning","author":"Jia","year":"2022"},{"key":"10.1016\/j.artint.2025.104417_br0240","author":"Bahng"},{"key":"10.1016\/j.artint.2025.104417_br0250","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19133","article-title":"Understanding and improving visual prompting: a label-mapping perspective","author":"Chen","year":"2023"},{"key":"10.1016\/j.artint.2025.104417_br0260","article-title":"Unleashing the power of visual prompting at the pixel level","author":"Wu","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.artint.2025.104417_br0270","author":"Loedeman"},{"key":"10.1016\/j.artint.2025.104417_br0280","author":"Peng"},{"issue":"6","key":"10.1016\/j.artint.2025.104417_br0290","doi-asserted-by":"crossref","first-page":"4653","DOI":"10.1109\/TCSVT.2023.3327605","article-title":"Pro-tuning: unified prompt tuning for vision tasks","volume":"34","author":"Nie","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.artint.2025.104417_br0300","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19840","article-title":"Visual prompt tuning for generative transfer learning","author":"Sohn","year":"2023"},{"key":"10.1016\/j.artint.2025.104417_br0310","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"Imagenet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.artint.2025.104417_br0320","series-title":"International Conference on Learning Representations","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2022"},{"key":"10.1016\/j.artint.2025.104417_br0330","series-title":"International Conference on Artificial Neural Networks","first-page":"222","article-title":"Eliciting knowledge from pretrained language models for prototypical prompt verbalizer","author":"Wei","year":"2022"},{"key":"10.1016\/j.artint.2025.104417_br0340","series-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"7014","article-title":"Prototypical verbalizer for prompt-based few-shot tuning","author":"Cui","year":"2022"},{"key":"10.1016\/j.artint.2025.104417_br0350","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"5","key":"10.1016\/j.artint.2025.104417_br0360","doi-asserted-by":"crossref","DOI":"10.1007\/s11704-024-40013-9","article-title":"A glance at in-context learning","volume":"18","author":"Wu","year":"2024","journal-title":"Front. Comput. Sci."},{"key":"10.1016\/j.artint.2025.104417_br0370","series-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","article-title":"The power of scale for parameter-efficient prompt tuning","author":"Lester","year":"2021"},{"key":"10.1016\/j.artint.2025.104417_br0380","series-title":"Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume","article-title":"Exploiting cloze-questions for few-shot text classification and natural language inference","author":"Schick","year":"2021"},{"key":"10.1016\/j.artint.2025.104417_br0390","series-title":"Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021","first-page":"1835","article-title":"Template-based named entity recognition using bart","author":"Cui","year":"2021"},{"key":"10.1016\/j.artint.2025.104417_br0400","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1162\/tacl_a_00298","article-title":"What bert is not: lessons from a new suite of psycholinguistic diagnostics for language models","volume":"8","author":"Ettinger","year":"2020","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.artint.2025.104417_br0410","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2020","first-page":"1896","article-title":"Unifiedqa: crossing format boundaries with a single qa system","author":"Khashabi","year":"2020"},{"key":"10.1016\/j.artint.2025.104417_br0420","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1162\/tacl_a_00324","article-title":"How can we know what language models know?","volume":"8","author":"Jiang","year":"2020","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.artint.2025.104417_br0430","author":"Schick"},{"key":"10.1016\/j.artint.2025.104417_br0440","series-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","article-title":"Prefix-tuning: optimizing continuous prompts for generation","author":"Li","year":"2021"},{"key":"10.1016\/j.artint.2025.104417_br0450","first-page":"27263","article-title":"Bartscore: evaluating generated text as text generation","volume":"34","author":"Yuan","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.artint.2025.104417_br0460","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1016\/j.aiopen.2023.08.012","article-title":"Gpt understands, too","volume":"5","author":"Liu","year":"2024","journal-title":"AI Open"},{"key":"10.1016\/j.artint.2025.104417_br0470","series-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","first-page":"4921","article-title":"Warp: word-level adversarial reprogramming","author":"Hambardzumyan","year":"2021"},{"key":"10.1016\/j.artint.2025.104417_br0480","series-title":"International Conference on Learning Representations","article-title":"Differentiable prompt makes pre-trained language models better few-shot learners","author":"Zhang","year":"2021"},{"key":"10.1016\/j.artint.2025.104417_br0490","series-title":"Proceedings of the Asian Conference on Computer Vision","first-page":"4260","article-title":"Learning common and specific visual prompts for domain generalization","author":"Li","year":"2022"},{"key":"10.1016\/j.artint.2025.104417_br0500","author":"Gao"},{"key":"10.1016\/j.artint.2025.104417_br0510","author":"Zheng"},{"key":"10.1016\/j.artint.2025.104417_br0520","author":"Yang"},{"key":"10.1016\/j.artint.2025.104417_br0530","author":"Liu"},{"key":"10.1016\/j.artint.2025.104417_br0540","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10878","article-title":"Diversity-aware meta visual prompting","author":"Huang","year":"2023"},{"issue":"7","key":"10.1016\/j.artint.2025.104417_br0550","doi-asserted-by":"crossref","first-page":"5268","DOI":"10.1109\/TPAMI.2024.3435939","article-title":"Neural prompt search","volume":"47","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.artint.2025.104417_br0560","series-title":"European Conference on Computer Vision","first-page":"631","article-title":"Dualprompt: complementary prompting for rehearsal-free continual learning","author":"Wang","year":"2022"},{"key":"10.1016\/j.artint.2025.104417_br0570","series-title":"The Eleventh International Conference on Learning Representations","article-title":"Lpt: long-tailed prompt tuning for image classification","author":"Dong","year":"2022"},{"key":"10.1016\/j.artint.2025.104417_br0580","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16000","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2022"},{"key":"10.1016\/j.artint.2025.104417_br0590","series-title":"International Conference on Learning Representations","article-title":"Image bert pre-training with online tokenizer","author":"Zhou","year":"2021"},{"issue":"1","key":"10.1016\/j.artint.2025.104417_br0600","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1007\/s11263-023-01852-4","article-title":"Context autoencoder for self-supervised representation learning","volume":"132","author":"Chen","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.artint.2025.104417_br0610","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9653","article-title":"Simmim: a simple framework for masked image modeling","author":"Xie","year":"2022"},{"key":"10.1016\/j.artint.2025.104417_br0620","series-title":"The Eleventh International Conference on Learning Representations","article-title":"Masked frequency modeling for self-supervised visual pre-training","author":"Xie","year":"2023"},{"key":"10.1016\/j.artint.2025.104417_br0630","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19358","article-title":"Eva: exploring the limits of masked visual representation learning at scale","author":"Fang","year":"2023"},{"issue":"2","key":"10.1016\/j.artint.2025.104417_br0640","doi-asserted-by":"crossref","first-page":"760","DOI":"10.1007\/s11263-024-02204-6","article-title":"Masked channel modeling for bootstrapping visual pre-training","volume":"133","author":"Liu","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.artint.2025.104417_br0650","series-title":"International Conference on Machine Learning","first-page":"8821","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021"},{"key":"10.1016\/j.artint.2025.104417_br0660","series-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.artint.2025.104417_br0670","series-title":"2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing","first-page":"722","article-title":"Automated flower classification over a large number of classes","author":"Nilsback","year":"2008"},{"key":"10.1016\/j.artint.2025.104417_br0680","series-title":"European Conference on Computer Vision","first-page":"446","article-title":"Food-101\u2013mining discriminative components with random forests","author":"Bossard","year":"2014"},{"issue":"7","key":"10.1016\/j.artint.2025.104417_br0690","doi-asserted-by":"crossref","first-page":"2217","DOI":"10.1109\/JSTARS.2019.2918242","article-title":"Eurosat: a novel dataset and deep learning benchmark for land use and land cover classification","volume":"12","author":"Helber","year":"2019","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"10.1016\/j.artint.2025.104417_br0700","series-title":"NIPS Workshop on Deep Learning and Unsupervised Feature Learning","first-page":"7","article-title":"Reading digits in natural images with unsupervised feature learning","volume":"vol. 2011","author":"Netzer","year":"2011"},{"key":"10.1016\/j.artint.2025.104417_br0710","series-title":"2012 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3498","article-title":"Cats and dogs","author":"Parkhi","year":"2012"},{"key":"10.1016\/j.artint.2025.104417_br0720","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3606","article-title":"Describing textures in the wild","author":"Cimpoi","year":"2014"},{"issue":"10","key":"10.1016\/j.artint.2025.104417_br0730","doi-asserted-by":"crossref","first-page":"1865","DOI":"10.1109\/JPROC.2017.2675998","article-title":"Remote sensing image scene classification: benchmark and state of the art","volume":"105","author":"Cheng","year":"2017","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.artint.2025.104417_br0740","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"210","article-title":"Rotation equivariant cnns for digital pathology","author":"Veeling","year":"2018"},{"issue":"9","key":"10.1016\/j.artint.2025.104417_br0750","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","article-title":"Learning to prompt for vision-language models","volume":"130","author":"Zhou","year":"2022","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.artint.2025.104417_br0760","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16816","article-title":"Conditional prompt learning for vision-language models","author":"Zhou","year":"2022"},{"issue":"6","key":"10.1016\/j.artint.2025.104417_br0770","doi-asserted-by":"crossref","first-page":"5885","DOI":"10.1109\/TCSVT.2024.3524181","article-title":"M-tuning: prompt tuning with mitigated label bias in open-set scenarios","volume":"35","author":"Liao","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.artint.2025.104417_br0780","author":"Zang"},{"key":"10.1016\/j.artint.2025.104417_br0790","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19113","article-title":"Maple: multi-modal prompt learning","author":"Khattak","year":"2023"}],"container-title":["Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0004370225001365?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0004370225001365?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T22:44:25Z","timestamp":1773096265000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0004370225001365"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":79,"alternative-id":["S0004370225001365"],"URL":"https:\/\/doi.org\/10.1016\/j.artint.2025.104417","relation":{},"ISSN":["0004-3702"],"issn-type":[{"value":"0004-3702","type":"print"}],"subject":[],"published":{"date-parts":[[2025,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Rethinking visual prompt learning as masked visual token modeling","name":"articletitle","label":"Article Title"},{"value":"Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.artint.2025.104417","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104417"}}