{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:53:50Z","timestamp":1784300030141,"version":"3.55.0"},"reference-count":109,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Earth System Big Data Platform of the School of Earth Sciences, Zhejiang University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tip.2024.3512354","type":"journal-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:43:21Z","timestamp":1735155801000},"page":"6893-6904","source":"Crossref","is-referenced-by-count":51,"title":["CLIP4STR: A Simple Baseline for Scene Text Recognition With Pre-Trained Vision-Language Model"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1320-4283","authenticated-orcid":false,"given":"Shuai","family":"Zhao","sequence":"first","affiliation":[{"name":"ReLER Laboratory, Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4077-1398","authenticated-orcid":false,"given":"Ruijie","family":"Quan","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4093-7557","authenticated-orcid":false,"given":"Linchao","family":"Zhu","sequence":"additional","affiliation":[{"name":"ReLER Laboratory, CCAI, Zhejiang University, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0512-880X","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"ReLER Laboratory, CCAI, Zhejiang University, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref2","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. ICML","author":"Jia"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.421"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28475"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.357"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-30761-2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86549-8_21"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547784"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26538"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01369-0"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CRV55824.2022.00026"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00252"},{"key":"ref16","first-page":"5","article-title":"Uber-text: A large-scale dataset for optical character recognition from street-level imagery","volume-title":"Proc. SUNw: Scene Understand. Workshop (CVPR)","author":"Zhang"},{"key":"ref17","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref18","volume-title":"Pixels Still Beat Text: Attacking the OpenAI CLIP Model With Text Patches and Adversarial Pixel Perturbations","author":"Fort","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00030"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_11"},{"key":"ref25","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021","journal-title":"arXiv:2111.11432"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531950"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3204444"},{"key":"ref28","first-page":"1","article-title":"Test-time adaptation with CLIP reward for zero-shot generalization in vision-language models","volume-title":"Proc. ICLR","author":"Zhao"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.39"},{"key":"ref30","article-title":"ERNIE-ViLG: Unified generative pre-training for bidirectional vision-language generation","author":"Zhang","year":"2021","journal-title":"arXiv:2112.15283"},{"key":"ref31","first-page":"1","article-title":"CoCa: Contrastive captioners are image-text foundation models","volume":"2022","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref32","first-page":"23318","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. ICML","author":"Wang"},{"key":"ref33","article-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm","author":"Li","year":"2021","journal-title":"arXiv:2110.05208"},{"key":"ref34","article-title":"FILIP: Fine-grained interactive language-image pre-training","author":"Yao","year":"2022","journal-title":"ICLR"},{"key":"ref35","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. NeurIPS","volume":"34","author":"Li"},{"key":"ref36","volume-title":"COYO-700M: Image-Text Pair Dataset","author":"Byeon","year":"2022"},{"key":"ref37","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. NeurIPS","volume":"35","author":"Schuhmann"},{"key":"ref38","article-title":"Openclip","author":"Ilharco","year":"2021"},{"key":"ref39","first-page":"1","article-title":"How much can CLIP benefit vision-and-language tasks?","volume-title":"Proc. ICLR","author":"Shen"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10465"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219861"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018714"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6891"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_10"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.543"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2848939"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_19"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_26"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.245"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3051485"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3045602"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00130"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00784"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612247"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222406"},{"key":"ref58","article-title":"Synthetic data and artificial neural networks for natural scene text recognition","author":"Jaderberg","year":"2014","journal-title":"arXiv:1406.2227"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00313"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01878"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01479"},{"issue":"8","key":"ref63","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref64","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. ICML","author":"Kim"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01984"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611769"},{"key":"ref67","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"issue":"1","key":"ref68","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref69","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref70","first-page":"1","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin"},{"key":"ref71","article-title":"Neural machine translation of rare words with subword units","author":"Sennrich","year":"2015","journal-title":"arXiv:1508.07909"},{"key":"ref72","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Proc. NeurIPS"},{"key":"ref73","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"Goyal","year":"2017","journal-title":"arXiv:1706.02677"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.127"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.07.008"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126402"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.76"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01393"},{"key":"ref79","article-title":"COCO-text: Dataset and benchmark for text detection and recognition in natural images","author":"Veit","year":"2016","journal-title":"arXiv:1601.07140"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.233"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00250"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00253"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00869"},{"key":"ref85","volume-title":"OpenImages: A Public Dataset for Large-Scale Multi-Label and Multi-Class Image Classification","author":"Krasin","year":"2017"},{"key":"ref86","first-page":"379","article-title":"Open images V5 text annotation and yet another mask text spotter","volume-title":"Proc. ACML","author":"Krylov"},{"key":"ref87","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref88","first-page":"1","article-title":"Mixed precision training","volume-title":"Proc. ICLR","author":"Micikevicius"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86337-1_11"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3197981"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01467"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01790"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01784"},{"key":"ref95","first-page":"1","article-title":"DataComp: In search of the next generation of multimodal datasets","volume-title":"Proc. NeurIPS","volume":"36","author":"Gadre"},{"key":"ref96","article-title":"Data filtering networks","author":"Fang","year":"2023","journal-title":"arXiv:2309.17425"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3381893"},{"key":"ref99","first-page":"561","article-title":"Ray: A distributed framework for emerging AI applications","volume-title":"Proc. OSDI","author":"Moritz"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref101","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. ICML","author":"Touvron"},{"key":"ref102","first-page":"1","article-title":"ImageNet-21K pretraining for the masses","volume-title":"Proc. NeurIPS","author":"Ridnik"},{"key":"ref103","first-page":"1","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. ICLR","author":"Bao"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref107","first-page":"12991","article-title":"LST: Ladder side-tuning for parameter and memory efficient transfer learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Sung"},{"key":"ref108","first-page":"1","article-title":"Pruning Filters for Efficient ConvNets","volume-title":"Proc. ICLR","author":"Li"},{"key":"ref109","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NeurIPS","volume":"33","author":"Brown"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10346232\/10816351.pdf?arnumber=10816351","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T06:21:36Z","timestamp":1735626096000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10816351\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":109,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3512354","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}