{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T18:57:54Z","timestamp":1785783474798,"version":"3.56.0"},"reference-count":121,"publisher":"Zhejiang University Press","issue":"1","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Front Inform Technol Electron Eng"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1631\/fitee.2300389","type":"journal-article","created":{"date-parts":[[2024,2,8]],"date-time":"2024-02-08T03:04:06Z","timestamp":1707361446000},"page":"42-63","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["Prompt learning in computer vision: a survey","\u8ba1\u7b97\u673a\u89c6\u89c9\u4e2d\u7684\u63d0\u793a\u5b66\u4e60:\u7efc\u8ff0"],"prefix":"10.1631","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1349-7074","authenticated-orcid":false,"given":"Yiming","family":"Lei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingqi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zilong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0604-3197","authenticated-orcid":false,"given":"Hongming","family":"Shan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"635","published-online":{"date-parts":[[2024,2,8]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00453"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01767"},{"key":"ref3","volume-title":"Exploring visual prompts for adapting large-scale models.","author":"Bahng","year":"2022"},{"key":"ref4","first-page":"25005","article-title":"Visual prompting via image inpainting","author":"Bar","year":"2022","journal-title":"Proc 36th Conf on Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531330"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/rs15061639"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3057879"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01834"},{"key":"ref9","article-title":"PLOT: prompt learning with optimal transport for vision-language models","author":"Chen","year":"2023","journal-title":"Proc 11th Int Conf on Learning Representations"},{"key":"ref10","article-title":"Vision Trans-former adapter for dense predictions","author":"Chen","year":"2023","journal-title":"Proc 11th Int Conf on Learning Representations"},{"key":"ref11","first-page":"2292","article-title":"Sinkhorn distances: lightspeed computation of optimal transport","volume-title":"Proc 26th Int Conf on Neural Information Processing Systems","author":"Cuturi","year":"2013"},{"key":"ref12","first-page":"4171","article-title":"BERT: pretraining of deep bidirectional Transformers for language understanding","volume-title":"Proc Conf of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Devlin","year":"2019"},{"key":"ref13","article-title":"LPT: long-tailed prompt tuning for image classification","author":"Dong","year":"2023","journal-title":"Proc 11th Int Conf on Learning Representations"},{"key":"ref14","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"Proc 9th Int Conf on Learning Representations"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01369"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00779"},{"key":"ref17","volume-title":"CLIP-Adapter: better vision-language models with feature adapters.","author":"Gao","year":"2021"},{"key":"ref18","volume-title":"Domain adaptation via prompt learning.","author":"Ge","year":"2022"},{"key":"ref19","volume-title":"Chain of thought prompt tuning in vision language models.","author":"Ge","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref21","article-title":"Open-vocabularyobject detection via vision and language knowledge distil-lation","author":"Gu","year":"2022","journal-title":"Proc 10th Int Conf on Learning Representations"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3152247"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2014.2330611"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01553"},{"key":"ref26","first-page":"574","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc 34th Int Conf on Neural Information Processing Systems","author":"Ho","year":"2020"},{"key":"ref27","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","author":"Houlsby","year":"2019","journal-title":"Proc 36th Int Conf on Machine Learning"},{"key":"ref28","article-title":"LoRA: low-rank adaptation of large language models","author":"Hu","year":"2022","journal-title":"Proc 10th Int Conf on Learning Representations"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00635"},{"key":"ref30","volume-title":"Pixel-BERT: aligning image pixels with text by deep multimodal Transformers.","author":"Huang","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073659"},{"key":"ref32","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021","journal-title":"Proc 38th Int Conf on Machine Learning"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00976"},{"key":"ref36","volume-title":"Scaling laws for neural language models.","author":"Kaplan","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00453"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00813"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2106.12423"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00582"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01832"},{"key":"ref43","first-page":"5583","article-title":"ViLT: vision-and-language Transformer without convolution or region supervision","author":"Kim","year":"2021","journal-title":"Proc 38th Int Conf on Machine Learning"},{"key":"ref44","volume-title":"Auto-encoding variational Bayes.","author":"Kingma","year":"2013"},{"key":"ref45","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.00371","volume-title":"Segment anything.","author":"Kirillov","year":"2023"},{"key":"ref46","article-title":"Large language models are zero-shot reasoners","author":"Kojima","year":"2022","journal-title":"Proc 36th Conf on Neural Information Processing Systems"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00654"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.298"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s43657-021-00025-y"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/jas.2022.105668"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43990-2_38"},{"issue":"2023b","key":"ref52","volume-title":"LICO: explainable models with language-image consistency.","author":"Lei"},{"key":"ref53","first-page":"12888","article-title":"BLIP: bootstrapping language-image pretraining for unified vision-language understanding and generation","author":"Li","year":"2022","journal-title":"Proc 39th Int Conf on Machine Learning"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10096571"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10096602"},{"key":"ref56","volume-title":"MaskCL: semantic mask-driven contrastive learning for unsupervised person reidentification with clothes change.","author":"Li","year":"2023"},{"key":"ref57","article-title":"OrdinalCLIP: learning rank prompts for language-guided ordinal regression","author":"Li","year":"2022","journal-title":"Proc 36th Conf on Neural Information Processing Systems"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01438"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/icme52920.2022.9859720"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.324"},{"key":"ref61","volume-title":"Exploring visual prompts for whole slide image classification with multiple instance learning.","author":"Lin","year":"2023"},{"key":"ref62","first-page":"16331","article-title":"EditGAN: high-precision semantic image editing","author":"Ling","year":"2021","journal-title":"Proc 35th Conf on Neural Information Processing Systems"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01862"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01048"},{"key":"ref66","article-title":"Unified-IO: a unified model for vision, language, and multimodal tasks","author":"Lu","year":"2023","journal-title":"Proc 11th Int Conf on Learning Representations"},{"key":"ref67","first-page":"2507","article-title":"Learn to explain: multimodal reasoning via thought chains for science question answering","author":"Lu","year":"2022","journal-title":"Proc 36th Conf on Neural Information Processing Systems"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00514"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01117"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01368"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00267"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/3dv.2016.79"},{"key":"ref73","first-page":"16784","article-title":"GLIDE: towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2022","journal-title":"Proc 39th Int Conf on Machine Learning"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02320"},{"key":"ref75","volume-title":"Invertible conditional GANs for image editing.","author":"Perarnau","year":"2016"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.39"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.7"},{"key":"ref78","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"Proc 38th Int Conf on Machine Learning"},{"key":"ref79","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023","journal-title":"Proc 40th Int Conf on Machine Learning"},{"key":"ref80","first-page":"8821","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"Proc 38th Int Conf on Machine Learning"},{"key":"ref81","volume-title":"Hierarchical text-conditional image generation with CLIP latents.","author":"Ramesh","year":"2022"},{"issue":"2016a","key":"ref82","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc 33rd Int Conf on Machine Learning","author":"Reed"},{"issue":"2016b","key":"ref83","first-page":"217","article-title":"Learning what and where to draw","volume-title":"Proc 30th Int Conf on Neural Information Processing Systems","author":"Reed"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02155"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.74"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102802"},{"key":"ref88","volume-title":"Continual diffusion: continual customization of text-to-image diffusion with C-LoRA.","author":"Smith","year":"2023"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01900"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00516"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/wacv51458.2022.00323"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01602"},{"key":"ref93","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc 31st Int Conf on Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"ref94","article-title":"Learning to decompose visual features with latent textual prompts","author":"Wang","year":"2023","journal-title":"Proc 11th Int Conf on Learning Representations"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01761"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00917"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00660"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00024"},{"key":"ref99","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei","year":"2022","journal-title":"Proc 36th Conf on Neural Information Processing Systems"},{"key":"ref100","volume-title":"Instruction-ViT: multimodal prompts for instruction learning in ViT.","author":"Xiao","year":"2023"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02148"},{"key":"ref102","volume-title":"Class-aware visual prompt tuning for vision-language pre-trained model.","author":"Xing","year":"2022"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00143"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2010.2042098"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/s43657-022-00051-4"},{"key":"ref106","volume-title":"Prompt-based time series forecasting: a new task and dataset.","author":"Xue","year":"2022"},{"key":"ref107","volume-title":"CPT: colorful prompt tuning for pre-trained vision-language models.","author":"Yao","year":"2021"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00577"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00457"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00674"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/bibm55620.2022.9995157"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.629"},{"key":"ref113","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.00355","volume-title":"Adding conditional control to text-to-image diffusion models.","author":"Zhang","year":"2023"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413939"},{"key":"ref115","article-title":"Automatic chain of thought prompting in large language models","author":"Zhang","year":"2022","journal-title":"Proc 11th Int Conf on Learning Representations"},{"key":"ref116","volume-title":"Multimodal chain-of-thought reasoning in language models.","author":"Zhang","year":"2023"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01631"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00230"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3055816"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00918"}],"container-title":["Frontiers of Information Technology & Electronic Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1631\/FITEE.2300389.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1631\/FITEE.2300389\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1631\/FITEE.2300389.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T07:45:24Z","timestamp":1771659924000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1631\/FITEE.2300389"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":121,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["389"],"URL":"https:\/\/doi.org\/10.1631\/fitee.2300389","relation":{},"ISSN":["2095-9184","2095-9230"],"issn-type":[{"value":"2095-9184","type":"print"},{"value":"2095-9230","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1]]},"assertion":[{"value":"31 May 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 October 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 February 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"All the authors declare that they have no conflict of interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethics guidelines"}}]}}