{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T21:13:31Z","timestamp":1778102011875,"version":"3.51.4"},"reference-count":70,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"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"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476234"],"award-info":[{"award-number":["62476234"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.engappai.2026.114751","type":"journal-article","created":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T13:44:49Z","timestamp":1776433489000},"page":"114751","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P2","title":["Dimensional feature-enhanced transformer for low-resource Uyghur scene text recognition"],"prefix":"10.1016","volume":"176","author":[{"given":"Miaomiao","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanbing","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wushour","family":"Silamu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2026.114751_b1","doi-asserted-by":"crossref","unstructured":"Atienza, R., 2021a. Data augmentation for scene text recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 1561\u20131570.","DOI":"10.1109\/ICCVW54120.2021.00181"},{"key":"10.1016\/j.engappai.2026.114751_b2","series-title":"International Conference on Document Analysis and Recognition","first-page":"319","article-title":"Vision transformer for fast and efficient scene text recognition","author":"Atienza","year":"2021"},{"key":"10.1016\/j.engappai.2026.114751_b3","doi-asserted-by":"crossref","unstructured":"Baek, J., Kim, G., Lee, J., Park, S., Han, D., Yun, S., Oh, S.J., Lee, H., 2019a. 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"},{"key":"10.1016\/j.engappai.2026.114751_b4","doi-asserted-by":"crossref","unstructured":"Baek, J., Kim, G., Lee, J., Park, S., Han, D., Yun, S., Oh, S.J., Lee, H., 2019b. What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. ICCV, pp. 4715\u20134723.","DOI":"10.1109\/ICCV.2019.00481"},{"key":"10.1016\/j.engappai.2026.114751_b5","series-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014"},{"key":"10.1016\/j.engappai.2026.114751_b6","doi-asserted-by":"crossref","unstructured":"Bai, F., Cheng, Z., Niu, Y., Pu, S., Zhou, S., 2018. Edit Probability for Scene Text Recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 1508\u20131516.","DOI":"10.1109\/CVPR.2018.00163"},{"key":"10.1016\/j.engappai.2026.114751_b7","series-title":"European Conference on Computer Vision","first-page":"178","article-title":"Scene text recognition with permuted autoregressive sequence models","author":"Bautista","year":"2022"},{"key":"10.1016\/j.engappai.2026.114751_b8","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Bai, F., Xu, Y., Zheng, G., Pu, S., Zhou, S., 2017. Focusing Attention: Towards Accurate Text Recognition in Natural Images. In: Proceedings of the IEEE International Conference on Computer Vision. ICCV, pp. 5076\u20135084.","DOI":"10.1109\/ICCV.2017.543"},{"key":"10.1016\/j.engappai.2026.114751_b9","doi-asserted-by":"crossref","unstructured":"Cheng, X., Zhou, W., Li, X., Yang, J., Zhang, H., Sun, T., Zhang, W., Mai, Y., Li, T., Chen, X., et al., 2024. SVIPTR: Fast and Efficient Scene Text Recognition with Vision Permutable Extractor. In: Proceedings of the 33rd ACM International Conference on Information and Knowledge Management. pp. 365\u2013373.","DOI":"10.1145\/3627673.3679618"},{"key":"10.1016\/j.engappai.2026.114751_b10","doi-asserted-by":"crossref","unstructured":"Chng, C.K., Liu, Y., Sun, Y., Ng, C.C., Luo, C., Ni, Z., Fang, C., Zhang, S., Han, J., Ding, E., Liu, J., Karatzas, D., Chan, C.S., Jin, L., 2019. ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text - RRC-ArT. In: 2019 International Conference on Document Analysis and Recognition. ICDAR, pp. 1571\u20131576.","DOI":"10.1109\/ICDAR.2019.00252"},{"key":"10.1016\/j.engappai.2026.114751_b11","series-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"key":"10.1016\/j.engappai.2026.114751_b12","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"issue":"21","key":"10.1016\/j.engappai.2026.114751_b13","doi-asserted-by":"crossref","first-page":"16373","DOI":"10.1007\/s00500-023-09164-y","article-title":"A hybrid CEEMD-GMM scheme for enhancing the detection of traffic flow on highways","volume":"27","author":"Dou","year":"2023","journal-title":"Soft Comput."},{"key":"10.1016\/j.engappai.2026.114751_b14","series-title":"Context perception parallel decoder for scene text recognition","author":"Du","year":"2023"},{"key":"10.1016\/j.engappai.2026.114751_b15","article-title":"Instruction-guided scene text recognition","author":"Du","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"10.1016\/j.engappai.2026.114751_b16","article-title":"Finsentiment: predicting financial sentiment through transfer learning","volume":"32","author":"Ergun","year":"2025","journal-title":"Intell. Syst. Account. Financ. Manag."},{"key":"10.1016\/j.engappai.2026.114751_b17","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":"10.1016\/j.engappai.2026.114751_b18","series-title":"Reading scene text with attention convolutional sequence modeling","author":"Gao","year":"2017"},{"key":"10.1016\/j.engappai.2026.114751_b19","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J., 2006. Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning. pp. 369\u2013376.","DOI":"10.1145\/1143844.1143891"},{"key":"10.1016\/j.engappai.2026.114751_b20","article-title":"Unconstrained on-line handwriting recognition with recurrent neural networks","volume":"20","author":"Graves","year":"2007","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.114751_b21","doi-asserted-by":"crossref","first-page":"107046","DOI":"10.1109\/ACCESS.2021.3100717","article-title":"Arabic scene text recognition in the deep learning era: Analysis on a novel dataset","volume":"9","author":"Hassan","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.engappai.2026.114751_b22","first-page":"888","article-title":"Visual semantics allow for textual reasoning better in scene text recognition","volume":"vol. 36","author":"He","year":"2022"},{"key":"10.1016\/j.engappai.2026.114751_b23","article-title":"Reading scene text in deep convolutional sequences","volume":"vol. 30","author":"He","year":"2016"},{"key":"10.1016\/j.engappai.2026.114751_b24","doi-asserted-by":"crossref","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-term Memory","author":"Hochreiter","year":"1997","journal-title":"Neural Comput. MIT-Press"},{"key":"10.1016\/j.engappai.2026.114751_b25","series-title":"A survey on optical character recognition system","author":"Islam","year":"2017"},{"key":"10.1016\/j.engappai.2026.114751_b26","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Gomez-Bigorda, L., Nicolaou, A., Ghosh, S., Bagdanov, A., Iwamura, M., Matas, J., Neumann, L., Chandrasekhar, V.R., Lu, S., Shafait, F., Uchida, S., Valveny, E., 2015. ICDAR 2015 competition on Robust Reading. In: 2015 13th International Conference on Document Analysis and Recognition. ICDAR, pp. 1156\u20131160.","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"10.1016\/j.engappai.2026.114751_b27","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Shafait, F., Uchida, S., Iwamura, M., Bigorda, L.G.i., Mestre, S.R., Mas, J., Mota, D.F., Almaz\u00e0n, J.A., de las Heras, L.P., 2013. ICDAR 2013 Robust Reading Competition. In: 2013 12th International Conference on Document Analysis and Recognition. pp. 1484\u20131493.","DOI":"10.1109\/ICDAR.2013.221"},{"key":"10.1016\/j.engappai.2026.114751_b28","series-title":"Asian Conference on Machine Learning","first-page":"379","article-title":"Open images v5 text annotation and yet another mask text spotter","author":"Krylov","year":"2021"},{"key":"10.1016\/j.engappai.2026.114751_b29","series-title":"On the cross-dataset generalization in license plate recognition","author":"Laroca","year":"2022"},{"key":"10.1016\/j.engappai.2026.114751_b30","first-page":"13094","article-title":"Trocr: Transformer-based optical character recognition with pre-trained models","volume":"vol. 37","author":"Li","year":"2023"},{"key":"10.1016\/j.engappai.2026.114751_b31","first-page":"8610","article-title":"Show, attend and read: A simple and strong baseline for irregular text recognition","volume":"vol. 33","author":"Li","year":"2019"},{"key":"10.1016\/j.engappai.2026.114751_b32","first-page":"7","article-title":"STAR-Net: a SpaTial attention residue network for scene text recognition","volume":"vol. 2","author":"Liu","year":"2016"},{"key":"10.1016\/j.engappai.2026.114751_b33","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.patcog.2019.01.020","article-title":"MORAN: A multi-object rectified attention network for scene text recognition","volume":"90","author":"Luo","year":"2019","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.engappai.2026.114751_b34","series-title":"BMVC-British Machine Vision Conference","article-title":"Scene text recognition using higher order language priors","author":"Mishra","year":"2012"},{"key":"10.1016\/j.engappai.2026.114751_b35","doi-asserted-by":"crossref","unstructured":"Nayef, N., Patel, Y., Busta, M., Chowdhury, P.N., Karatzas, D., Khlif, W., Matas, J., Pal, U., Burie, J.-C., Liu, C.-l., Ogier, J.-M., 2019. ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition \u2014 RRC-MLT-2019. In: 2019 International Conference on Document Analysis and Recognition. ICDAR, pp. 1582\u20131587.","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"10.1016\/j.engappai.2026.114751_b36","doi-asserted-by":"crossref","unstructured":"Phan, T.Q., Shivakumara, P., Tian, S., Tan, C.L., 2013. Recognizing Text with Perspective Distortion in Natural Scenes. In: Proceedings of the IEEE International Conference on Computer Vision. ICCV, pp. 569\u2013576.","DOI":"10.1109\/ICCV.2013.76"},{"key":"10.1016\/j.engappai.2026.114751_b37","doi-asserted-by":"crossref","unstructured":"Qiao, Z., Zhou, Y., Yang, D., Zhou, Y., Wang, W., 2020. SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 13528\u201313537.","DOI":"10.1109\/CVPR42600.2020.01354"},{"key":"10.1016\/j.engappai.2026.114751_b38","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"issue":"18","key":"10.1016\/j.engappai.2026.114751_b39","doi-asserted-by":"crossref","first-page":"8027","DOI":"10.1016\/j.eswa.2014.07.008","article-title":"A robust arbitrary text detection system for natural scene images","volume":"41","author":"Risnumawan","year":"2014","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.engappai.2026.114751_b40","series-title":"2019 International Conference on Document Analysis and Recognition","first-page":"781","article-title":"NRTR: A no-recurrence sequence-to-sequence model for scene text recognition","author":"Sheng","year":"2019"},{"issue":"11","key":"10.1016\/j.engappai.2026.114751_b41","doi-asserted-by":"crossref","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","article-title":"An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition","volume":"39","author":"Shi","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.engappai.2026.114751_b42","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4168","article-title":"Robust scene text recognition with automatic rectification","author":"Shi","year":"2016"},{"key":"10.1016\/j.engappai.2026.114751_b43","first-page":"1429","article-title":"ICDAR2017 competition on reading Chinese text in the wild (RCTW-17)","volume":"vol. 01","author":"Shi","year":"2017"},{"key":"10.1016\/j.engappai.2026.114751_b44","doi-asserted-by":"crossref","unstructured":"Singh, A., Pang, G., Toh, M., Huang, J., Galuba, W., Hassner, T., 2021. TextOCR: Towards Large-Scale End-to-End Reasoning for Arbitrary-Shaped Scene Text. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 8802\u20138812.","DOI":"10.1109\/CVPR46437.2021.00869"},{"key":"10.1016\/j.engappai.2026.114751_b45","doi-asserted-by":"crossref","unstructured":"Sun, Y., Ni, Z., Chng, C.-K., Liu, Y., Luo, C., Ng, C.C., Han, J., Ding, E., Liu, J., Karatzas, D., Chan, C.S., Jin, L., 2019. ICDAR 2019 Competition on Large-Scale Street View Text with Partial Labeling - RRC-LSVT. In: 2019 International Conference on Document Analysis and Recognition. ICDAR, pp. 1557\u20131562.","DOI":"10.1109\/ICDAR.2019.00250"},{"key":"10.1016\/j.engappai.2026.114751_b46","series-title":"2011 18th IEEE International Conference on Image Processing","first-page":"2601","article-title":"Mobile visual search on printed documents using text and low bit-rate features","author":"Tsai","year":"2011"},{"key":"10.1016\/j.engappai.2026.114751_b47","series-title":"Coco-text: Dataset and benchmark for text detection and recognition in natural images","author":"Veit","year":"2016"},{"key":"10.1016\/j.engappai.2026.114751_b48","doi-asserted-by":"crossref","unstructured":"Wang, K., Babenko, B., Belongie, S., 2011. End-to-end scene text recognition. In: 2011 International Conference on Computer Vision. pp. 1457\u20131464.","DOI":"10.1109\/ICCV.2011.6126402"},{"key":"10.1016\/j.engappai.2026.114751_b49","series-title":"European Conference on Computer Vision","first-page":"339","article-title":"Multi-granularity prediction for scene text recognition","author":"Wang","year":"2022"},{"key":"10.1016\/j.engappai.2026.114751_b50","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xie, H., Fang, S., Wang, J., Zhu, S., Zhang, Y., 2021. From Two to One: A New Scene Text Recognizer With Visual Language Modeling Network. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. ICCV, pp. 14194\u201314203.","DOI":"10.1109\/ICCV48922.2021.01393"},{"key":"10.1016\/j.engappai.2026.114751_b51","first-page":"12216","article-title":"Decoupled attention network for text recognition","volume":"vol 34","author":"Wang","year":"2020"},{"key":"10.1016\/j.engappai.2026.114751_b52","first-page":"5885","article-title":"Image as a language: Revisiting scene text recognition via balanced, unified and synchronized vision-language reasoning network","volume":"vol. 38","author":"Wei","year":"2024"},{"issue":"23","key":"10.1016\/j.engappai.2026.114751_b53","doi-asserted-by":"crossref","first-page":"18195","DOI":"10.1007\/s00500-023-09278-3","article-title":"Regional feature fusion for on-road detection of objects using camera and 3D-LiDAR in high-speed autonomous vehicles","volume":"27","author":"Wu","year":"2023","journal-title":"Soft Comput."},{"key":"10.1016\/j.engappai.2026.114751_b54","doi-asserted-by":"crossref","unstructured":"Xu, J., Wang, Y., Xie, H., Zhang, Y., 2024. OTE: Exploring Accurate Scene Text Recognition Using One Token. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 28327\u201328336.","DOI":"10.1109\/CVPR52733.2024.02676"},{"key":"10.1016\/j.engappai.2026.114751_b55","series-title":"Chinese Conference on Pattern Recognition and Computer Vision","first-page":"58","article-title":"Dual feature enhanced scene text recognition method for low-resource Uyghur","author":"Xu","year":"2024"},{"key":"10.1016\/j.engappai.2026.114751_b56","series-title":"Chinese Conference on Pattern Recognition and Computer Vision","first-page":"86","article-title":"Hybrid encoding method for scene text recognition in low-resource uyghur","author":"Xu","year":"2024"},{"issue":"5","key":"10.1016\/j.engappai.2026.114751_b57","doi-asserted-by":"crossref","first-page":"1707","DOI":"10.3390\/app14051707","article-title":"Collaborative encoding method for scene text recognition in low linguistic resources: The uyghur language case study","volume":"14","author":"Xu","year":"2024","journal-title":"Appl. Sci."},{"issue":"1","key":"10.1016\/j.engappai.2026.114751_b58","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s40747-024-01689-5","article-title":"Correlation-guided decoding strategy for low-resource Uyghur scene text recognition","volume":"11","author":"Xu","year":"2025","journal-title":"Complex Intell. Syst."},{"key":"10.1016\/j.engappai.2026.114751_b59","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.110244","article-title":"Class-Aware Mask-guided feature refinement for scene text recognition","volume":"149","author":"Yang","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.engappai.2026.114751_b60","series-title":"Scene text recognition with sliding convolutional character models","author":"Yin","year":"2017"},{"key":"10.1016\/j.engappai.2026.114751_b61","doi-asserted-by":"crossref","unstructured":"Yu, D., Li, X., Zhang, C., Liu, T., Han, J., Liu, J., Ding, E., 2020. Towards Accurate Scene Text Recognition With Semantic Reasoning Networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 12113\u201312122.","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"10.1016\/j.engappai.2026.114751_b62","series-title":"Recurrent neural network regularization","author":"Zaremba","year":"2014"},{"key":"10.1016\/j.engappai.2026.114751_b63","doi-asserted-by":"crossref","unstructured":"Zhan, F., Lu, S., 2019. ESIR: End-To-End Scene Text Recognition via Iterative Image Rectification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 2059\u20132068.","DOI":"10.1109\/CVPR.2019.00216"},{"key":"10.1016\/j.engappai.2026.114751_b64","first-page":"5","article-title":"Uber-text: A large-scale dataset for optical character recognition from street-level imagery","volume":"vol. 2017","author":"Zhang","year":"2017"},{"issue":"2","key":"10.1016\/j.engappai.2026.114751_b65","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1109\/TAI.2021.3116216","article-title":"Character-level street view text spotting based on deep multisegmentation network for smarter autonomous driving","volume":"3","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.114751_b66","series-title":"Linguistic more: Taking a further step toward efficient and accurate scene text recognition","author":"Zhang","year":"2023"},{"key":"10.1016\/j.engappai.2026.114751_b67","doi-asserted-by":"crossref","unstructured":"Zhang, R., Zhou, Y., Jiang, Q., Song, Q., Li, N., Zhou, K., Wang, L., Wang, D., Liao, M., Yang, M., Bai, X., Shi, B., Karatzas, D., Lu, S., Jawahar, C.V., 2019. ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard. In: 2019 International Conference on Document Analysis and Recognition. ICDAR, pp. 1577\u20131581.","DOI":"10.1109\/ICDAR.2019.00253"},{"key":"10.1016\/j.engappai.2026.114751_b68","doi-asserted-by":"crossref","first-page":"6893","DOI":"10.1109\/TIP.2024.3512354","article-title":"CLIP4STR: A simple baseline for scene text recognition with pre-trained vision-language model","volume":"33","author":"Zhao","year":"2024","journal-title":"IEEE Trans. Image Process."},{"issue":"2","key":"10.1016\/j.engappai.2026.114751_b69","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1007\/s11263-023-01880-0","article-title":"CDistNet: Perceiving multi-domain character distance for robust text recognition","volume":"132","author":"Zheng","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.engappai.2026.114751_b70","series-title":"European Conference on Computer Vision","first-page":"464","article-title":"SGBANet: Semantic GAN and balanced attention network for arbitrarily oriented scene text recognition","author":"Zhong","year":"2022"}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095219762601033X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095219762601033X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T20:33:18Z","timestamp":1778099598000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S095219762601033X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":70,"alternative-id":["S095219762601033X"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114751","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Dimensional feature-enhanced transformer for low-resource Uyghur scene text recognition","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114751","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114751"}}