{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T05:12:30Z","timestamp":1776489150536,"version":"3.51.2"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Joint Funds of the National Natural Science Foundation of China Joint Fund Project","award":["U1603262"],"award-info":[{"award-number":["U1603262"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62137002"],"award-info":[{"award-number":["62137002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Municipal Science and Technology Innovation Committee Project","award":["GJGJZD20210408092806017"],"award-info":[{"award-number":["GJGJZD20210408092806017"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s40747-024-01689-5","type":"journal-article","created":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T08:13:05Z","timestamp":1732695185000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Correlation-guided decoding strategy for low-resource Uyghur scene text recognition"],"prefix":"10.1007","volume":"11","author":[{"given":"Miaomiao","family":"Xu","sequence":"first","affiliation":[]},{"given":"Jiang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Lianghui","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Wushour","family":"Silamu","sequence":"additional","affiliation":[]},{"given":"Yanbing","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,27]]},"reference":[{"key":"1689_CR1","doi-asserted-by":"crossref","unstructured":"Baek J, Kim G, Lee J, Park S, Han D, Yun S, Oh SJ, Lee H (2019) What is wrong with scene text recognition model comparisons? dataset and model analysis. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 4715\u20134723","DOI":"10.1109\/ICCV.2019.00481"},{"issue":"2","key":"1689_CR2","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1109\/TAI.2021.3116216","volume":"3","author":"C Zhang","year":"2021","unstructured":"Zhang C, Tao Y, Du K, Ding W, Wang B, Liu J, Wang W (2021) Character-level street view text spotting based on deep multisegmentation network for smarter autonomous driving. IEEE Trans Artif Intell 3(2):297\u2013308","journal-title":"IEEE Trans Artif Intell"},{"key":"1689_CR3","doi-asserted-by":"crossref","unstructured":"Tsai SS, Chen H, Chen D, Schroth G, Grzeszczuk R, Girod B (2011) Mobile visual search on printed documents using text and low bit-rate features. In: 2011 18th IEEE international conference on image processing. IEEE, pp 2601\u20132604","DOI":"10.1109\/ICIP.2011.6116198"},{"key":"1689_CR4","doi-asserted-by":"crossref","unstructured":"Laroca R, Cardoso EV, Lucio DR, Estevam V, Menotti D (2022) On the cross-dataset generalization in license plate recognition. arXiv preprint arXiv:2201.00267","DOI":"10.5220\/0010846800003124"},{"issue":"21","key":"1689_CR5","doi-asserted-by":"publisher","first-page":"16373","DOI":"10.1007\/s00500-023-09164-y","volume":"27","author":"H Dou","year":"2023","unstructured":"Dou H, Liu Y, Chen S, Zhao H, Bilal H (2023) A hybrid CEEMD-GMM scheme for enhancing the detection of traffic flow on highways. Soft Comput 27(21):16373\u201316388","journal-title":"Soft Comput"},{"issue":"23","key":"1689_CR6","doi-asserted-by":"publisher","first-page":"18195","DOI":"10.1007\/s00500-023-09278-3","volume":"27","author":"Q Wu","year":"2023","unstructured":"Wu Q, Li X, Wang K, Bilal H (2023) Regional feature fusion for on-road detection of objects using camera and 3d-lidar in high-speed autonomous vehicles. Soft Comput 27(23):18195\u201318213","journal-title":"Soft Comput"},{"key":"1689_CR7","unstructured":"Islam N, Islam Z, Noor N (2017) A survey on optical character recognition system. arXiv preprint arXiv:1710.05703"},{"key":"1689_CR8","doi-asserted-by":"crossref","unstructured":"Sabu AM, Das AS (2018) A survey on various optical character recognition techniques. In: 2018 Conference on emerging devices and smart systems (ICEDSS). IEEE, pp 152\u2013155","DOI":"10.1109\/ICEDSS.2018.8544323"},{"issue":"01","key":"1689_CR9","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1109\/34.824820","volume":"22","author":"G Nagy","year":"2000","unstructured":"Nagy G (2000) Twenty years of document image analysis in pami. IEEE Trans Pattern Anal Mach Intell 22(01):38\u201362","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1689_CR10","unstructured":"Somerville PJ (1991) Method and apparatus for barcode recognition in a digital image. Google Patents. US Patent 4,992,650"},{"key":"1689_CR11","doi-asserted-by":"crossref","unstructured":"Li P, Zhu J, Peng L, Guo Y (2016) RNN based Uyghur text line recognition and its training strategy. In: 2016 12th IAPR workshop on document analysis systems (DAS). IEEE, pp 19\u201324","DOI":"10.1109\/DAS.2016.20"},{"issue":"1","key":"1689_CR12","first-page":"51","volume":"13","author":"M Ibrayim","year":"2021","unstructured":"Ibrayim M, Simayi W, Hamdulla A (2021) Unconstrained online handwritten Uyghur word recognition based on recurrent neural networks and connectionist temporal classification. Int J Biom 13(1):51\u201363","journal-title":"Int J Biom"},{"key":"1689_CR13","doi-asserted-by":"crossref","unstructured":"Li W, Mahpirat Kang W, Aysa A, Ubul K (2021) Multi-lingual hybrid handwritten signature recognition based on deep residual attention network. In: Biometric recognition: 15th Chinese conference, CCBR 2021, Shanghai, China, September 10\u201312, 2021, Proceedings 15. Springer, pp 148\u2013156","DOI":"10.1007\/978-3-030-86608-2_17"},{"issue":"6","key":"1689_CR14","doi-asserted-by":"publisher","first-page":"293","DOI":"10.3390\/info13060293","volume":"13","author":"N Xamxidin","year":"2022","unstructured":"Xamxidin N, Mahpirat Yao Z, Aysa A, Ubul K (2022) Multilingual offline signature verification based on improved inverse discriminator network. Information 13(6):293","journal-title":"Information"},{"key":"1689_CR15","doi-asserted-by":"crossref","unstructured":"Zheng T, Chen Z, Fang S, Xie H, Jiang Y-G (2023) Cdistnet: Perceiving multi-domain character distance for robust text recognition. Int J Comput Vis, 1\u201319","DOI":"10.1007\/s11263-023-01880-0"},{"key":"1689_CR16","doi-asserted-by":"crossref","unstructured":"Bautista D, Atienza R (2022) Scene text recognition with permuted autoregressive sequence models. In: European conference on computer vision. Springer, pp 178\u2013196","DOI":"10.1007\/978-3-031-19815-1_11"},{"key":"1689_CR17","doi-asserted-by":"crossref","unstructured":"Fang S, Xie H, Wang Y, Mao Z, Zhang Y (2021) Read like humans: autonomous, bidirectional and iterative language modeling for scene text recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7098\u20137107","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"1689_CR18","doi-asserted-by":"crossref","unstructured":"Li M, Lv T, Chen J, Cui L, Lu Y, Florencio D, Zhang C, Li Z, Wei F (2023) Trocr: Transformer-based optical character recognition with pre-trained models. In: Proceedings of the AAAI conference on artificial intelligence, vol 37, pp 13094\u201313102","DOI":"10.1609\/aaai.v37i11.26538"},{"key":"1689_CR19","doi-asserted-by":"crossref","unstructured":"Zhao S, Quan R, Zhu L, Yang Y (2023) Clip4str: a simple baseline for scene text recognition with pre-trained vision-language model. arXiv preprint arXiv:2305.14014","DOI":"10.1109\/TIP.2024.3512354"},{"key":"1689_CR20","doi-asserted-by":"crossref","unstructured":"Wang Z, Xie H, Wang Y, Xu J, Zhang B, Zhang Y (2023) Symmetrical linguistic feature distillation with clip for scene text recognition. In: Proceedings of the 31st ACM international conference on multimedia, pp 509\u2013518","DOI":"10.1145\/3581783.3611769"},{"key":"1689_CR21","doi-asserted-by":"crossref","unstructured":"Fujitake M (2024) Dtrocr: Decoder-only transformer for optical character recognition. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 8025\u20138035","DOI":"10.1109\/WACV57701.2024.00784"},{"key":"1689_CR22","doi-asserted-by":"crossref","unstructured":"Zheng Q, Chen K, Zhou Y, Gu C, Guan H (2011) Text localization and recognition in complex scenes using local features. In: Computer Vision\u2013ACCV 2010: 10th Asian conference on computer vision, Queenstown, New Zealand, November 8\u201312, 2010, Revised Selected Papers, Part III 10. Springer, pp 121\u2013132","DOI":"10.1007\/978-3-642-19318-7_10"},{"key":"1689_CR23","doi-asserted-by":"crossref","unstructured":"Su B, Lu S (2015) Accurate scene text recognition based on recurrent neural network. In: Computer vision\u2013ACCV 2014: 12th Asian conference on computer vision, Singapore, Singapore, November 1\u20135, 2014, Revised selected papers, Part I 12. Springer, pp 35\u201348","DOI":"10.1007\/978-3-319-16865-4_3"},{"key":"1689_CR24","doi-asserted-by":"crossref","unstructured":"Borisyuk F, Gordo A, Sivakumar V (2018) Rosetta: large scale system for text detection and recognition in images. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery and data mining, pp 71\u201379","DOI":"10.1145\/3219819.3219861"},{"issue":"11","key":"1689_CR25","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2016","unstructured":"Shi B, Bai X, Yao C (2016) An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Trans Pattern Anal Mach Intell 39(11):2298\u20132304","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1689_CR26","doi-asserted-by":"crossref","unstructured":"He P, Huang W, Qiao Y, Loy C, Tang X (2016) Reading scene text in deep convolutional sequences. In: Proceedings of the AAAI conference on artificial intelligence, vol 30","DOI":"10.1609\/aaai.v30i1.10465"},{"key":"1689_CR27","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S et al (2020) An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929"},{"key":"1689_CR28","doi-asserted-by":"crossref","unstructured":"Atienza R (2021) Vision transformer for fast and efficient scene text recognition. In: International conference on document analysis and recognition. Springer, pp 319\u2013334","DOI":"10.1007\/978-3-030-86549-8_21"},{"key":"1689_CR29","doi-asserted-by":"crossref","unstructured":"Du Y, Chen Z, Jia C, Yin X, Zheng T, Li C, Du Y, Jiang Y-G (2022) Svtr: scene text recognition with a single visual model. arXiv preprint arXiv:2205.00159","DOI":"10.24963\/ijcai.2022\/124"},{"key":"1689_CR30","doi-asserted-by":"crossref","unstructured":"Wang P, Da C, Yao C (2022) Multi-granularity prediction for scene text recognition. In: European conference on computer vision. Springer, pp 339\u2013355","DOI":"10.1007\/978-3-031-19815-1_20"},{"issue":"17","key":"1689_CR31","doi-asserted-by":"publisher","first-page":"9539","DOI":"10.3390\/app13179539","volume":"13","author":"W Li","year":"2023","unstructured":"Li W, Zhang Y, Huang Y, Shen Y, Wang Z (2023) A three-stage Uyghur recognition model combining the attention mechanism and different convolutional recurrent networks. Appl Sci 13(17):9539","journal-title":"Appl Sci"},{"issue":"7","key":"1689_CR32","doi-asserted-by":"publisher","first-page":"332","DOI":"10.3390\/info13070332","volume":"13","author":"M Ibrayim","year":"2022","unstructured":"Ibrayim M, Mattohti A, Hamdulla A (2022) An effective method for detection and recognition of Uyghur texts in images with backgrounds. Information 13(7):332","journal-title":"Information"},{"key":"1689_CR33","doi-asserted-by":"crossref","unstructured":"Wang Y, Ao N, Guo R, Mamat H, Ubul K (2022) Scene Uyghur recognition with embedded coordinate attention. In: 2022 3rd International conference on pattern recognition and machine learning (PRML). IEEE, pp 253\u2013260","DOI":"10.1109\/PRML56267.2022.9882248"},{"issue":"20","key":"1689_CR34","doi-asserted-by":"publisher","first-page":"8610","DOI":"10.3390\/s23208610","volume":"23","author":"Y Liu","year":"2023","unstructured":"Liu Y, Kong F, Xu M, Silamu W, Li Y (2023) Scene Uyghur recognition based on visual prediction enhancement. Sensors 23(20):8610","journal-title":"Sensors"},{"key":"1689_CR35","doi-asserted-by":"crossref","unstructured":"Lee C-Y, Osindero S (2016) Recursive recurrent nets with attention modeling for OCR in the wild. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2231\u20132239","DOI":"10.1109\/CVPR.2016.245"},{"key":"1689_CR36","unstructured":"Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J, et al. (2021) Learning transferable visual models from natural language supervision. In: International conference on machine learning. PMLR, pp 8748\u20138763"},{"key":"1689_CR37","unstructured":"Rang M, Bi Z, Liu C, Wang Y, Han K (2023) An empirical study of scaling law for OCR. arXiv e-prints, 2401"},{"key":"1689_CR38","doi-asserted-by":"crossref","unstructured":"Cubuk ED, Zoph B, Shlens J, Le QV (2020) Randaugment: practical automated data augmentation with a reduced search space. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) workshops","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"1689_CR39","doi-asserted-by":"crossref","unstructured":"Xu M, Zhang J, Xu L, Li Y, Wushour S (2024) Dual feature enhanced scene text recognition method for low-resource Uyghur. In: Proceedings of the 7th Chinese conference on pattern recognition and computer vision (PRCV 2024), Urumqi, China. Accepted for publication","DOI":"10.1007\/978-981-97-8511-7_5"},{"key":"1689_CR40","doi-asserted-by":"crossref","unstructured":"Xu M, Zhang J, Xu L, Silamu W, Li Y (2024) Collaborative encoding method for scene text recognition in low linguistic resources: the Uyghur language case study. Appl Sci 14(5):1707","DOI":"10.3390\/app14051707"},{"key":"1689_CR41","doi-asserted-by":"crossref","unstructured":"Xu M, Zhang J, Xu L, Li Y, Wushour S (2024) Hybrid encoding method for scene text recognition in low-resource Uyghur. In: Proceedings of the 7th Chinese conference on pattern recognition and computer vision (PRCV 2024), Urumqi, China. Accepted for publication","DOI":"10.1007\/978-981-97-8511-7_7"},{"key":"1689_CR42","doi-asserted-by":"crossref","unstructured":"Du Y, Chen Z, Su Y, Jia C, Jiang Y-G (2024) Instruction-guided scene text recognition. arXiv preprint arXiv:2401.17851","DOI":"10.1109\/TPAMI.2025.3525526"},{"key":"1689_CR43","unstructured":"Cheng X, Zhou W, Li X, Chen X, Yang J, Li T, Li Z (2024) Viptr: a vision permutable extractor for fast and efficient scene text recognition. arXiv preprint arXiv:2401.10110"}],"container-title":["Complex & Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-024-01689-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-024-01689-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-024-01689-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T20:18:05Z","timestamp":1738268285000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-024-01689-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,27]]},"references-count":43,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["1689"],"URL":"https:\/\/doi.org\/10.1007\/s40747-024-01689-5","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,27]]},"assertion":[{"value":"3 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 November 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 November 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"57"}}