{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T12:13:43Z","timestamp":1774440823317,"version":"3.50.1"},"reference-count":37,"publisher":"China Science Publishing & Media Ltd.","issue":"1","content-domain":{"domain":["engine.scichina.com"],"crossmark-restriction":false},"short-container-title":["DI"],"published-print":{"date-parts":[[2026,3,1]]},"DOI":"10.3724\/2096-7004.di.2025.0127","type":"journal-article","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T07:07:12Z","timestamp":1758524832000},"page":"244-267","update-policy":"https:\/\/doi.org\/10.1360\/scp-crossmark-policy-page","source":"Crossref","is-referenced-by-count":1,"title":["Modifying SwinTextSpotter for Vietnamese Scene Text Spotting"],"prefix":"10.3724","volume":"8","author":[{"given":"Yimin","family":"Wen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhui","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiqi","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liyu","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lianxi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vinh Loc","family":"Cu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"2026","published-online":{"date-parts":[[2025,9,22]]},"reference":[{"key":"","unstructured":"Zhao Z., Tang J., Lin C., Wu B., Huang C., Liu H., Tan X., Zhang Z., and Xie Y., \u201cMulti-modal in-context learning makes an ego-evolving scene text recognizer,\u201d in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 15567\u201315576."},{"key":"","unstructured":"Wen Y., Shayegh B., Huang C., Cao Y., and Mou L., \u201cEbbs: An ensemble with bi-level beam search for zero-shot machine translation,\u201d in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, no. 24, 2025, pp. 25479\u201325487."},{"key":"","unstructured":"Nguyen N., Nguyen T., Tran V., Tran M.-T., Ngo T. D., Nguyen T. H., and Hoai M., \u201cDictionary-guided scene text recognition,\u201d in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 7383\u20137392."},{"key":"","unstructured":"Huang M., Liu Y., Peng Z., Liu C., Lin D., Zhu S., Yuan N., Ding K., and Jin L., \u201cSwintextspotter: Scene text spotting via better synergy between text detection and text recognition,\u201d in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 4593\u20134603."},{"key":"","unstructured":"Wang Q., Wu B., Zhu P., Li P., Zuo W., and Hu Q., \u201cEca-net: Efficient channel attention for deep convolutional neural networks,\u201d in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 2020, pp. 11534\u201311542."},{"key":"","unstructured":"Huang Z., Wang X., Huang L., Huang C., Wei Y., and Liu W., \u201cCcnet: Criss-cross attention for semantic segmentation,\u201d in Proceedings of the IEEE\/CVF international conference on computer vision, 2019, pp. 603\u2013612."},{"key":"","unstructured":"Zhang S., Zhu X., Hou J., Liu C., Yang C., Wang H., and Yin X., \u201cDeep relational reasoning graph network for arbitrary shape text detection,\u201d in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 9699\u20139708."},{"key":"","unstructured":"Zhang S., Zhu X., Chen L., Hou J., and Yin X., \u201cArbitrary shape text detection via segmentation with probability maps,\u201d IEEE transactions on pattern analysis and machine intelligence, vol. 45, no. 3, pp. 2736\u20132750, 2022."},{"key":"","unstructured":"Qin X., Lyu P., Zhang C., Zhou Y., Yao K., Zhang P., Lin H., and Wang W., \u201cTowards robust real-time scene text detection: From semantic to instance representation learning,\u201d in Proceedings of the 31 st  ACM International Conference on Multimedia, 2023, pp. 2025\u20132034."},{"key":"","unstructured":"Shu Y., Wang W., Zhou Y., Liu S., Zhang A., Yang D., and Wang W., \u201cPerceiving ambiguity and semantics without recognition: an efficient and effective ambiguous scene text detector,\u201d in Proceedings of the 31 st  ACM International Conference on Multimedia, 2023, pp. 1851\u20131862."},{"key":"","unstructured":"Shi B., Bai X., and Yao C., \u201cAn end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition,\u201d IEEE transactions on pattern analysis and machine intelligence, vol. 39, no. 11, pp. 2298\u20132304, 2016."},{"key":"","unstructured":"Wang T., Zhu Y., Jin L., Luo C., Chen X., Wu Y., Wang Q., and Cai M., \u201cDecoupled attention network for text recognition,\u201d in Proceedings of the AAAI conference on artificial intelligence, vol. 34, no. 07, 2020, pp. 12216\u201312224."},{"key":"","unstructured":"Lu N., Yu W., Qi X., Chen Y., Gong P., Xiao R., and Bai X., \u201cMaster: Multi-aspect non-local network for scene text recognition,\u201d Pattern Recognition, vol. 117, p. 107980, 2021."},{"key":"","unstructured":"Lin Q., Luo C., Jin L., and Lai S., \u201cStan: A sequential transformation attention-based network for scene text recognition,\u201d Pattern Recognition, vol. 111, p. 107692, 2021."},{"key":"","unstructured":"Liao M., Shi B., Bai X., Wang X., and Liu W., \u201cTextboxes: A fast text detector with a single deep neural network,\u201d in Proceedings of the AAAI conference on artificial intelligence, vol. 31, no. 1, 2017, pp. 4161\u20134167."},{"key":"","unstructured":"Liao M., Shi B., and Bai X., \u201cTextboxes++: A single-shot oriented scene text detector,\u201d IEEE transactions on image processing, vol. 27, no. 8, pp. 3676\u20133690, 2018."},{"key":"","unstructured":"Liu X., Liang D., Yan S., Chen D., Qiao Y., and Yan J., \u201cFots: Fast oriented text spotting with a unified network,\u201d in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 5676\u20135685."},{"key":"","unstructured":"Zhou X., Yao C., Wen H., Wang Y., Zhou S., He W., and Liang J., \u201cEast: an efficient and accurate scene text detector,\u201d in Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, 2017, pp. 5551\u20135560."},{"key":"","unstructured":"Xing L., Tian Z., Huang W., and Scott M. R., \u201cConvolutional character networks,\u201d in Proceedings of the IEEE\/CVF international conference on computer vision, 2019, pp. 9126\u20139136."},{"key":"","unstructured":"Liu Y., Chen H., Shen C., He T., Jin L., and Wang L., \u201cAbcnet: Real-time scene text spotting with adaptive beziercurve network,\u201d in proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 2020, pp. 9809\u20139818."},{"key":"","unstructured":"Lyu P., Liao M., Yao C., Wu W., and Bai X., \u201cMask textspotter: An end-to-end trainable neural network for spotting text with arbitrary shapes,\u201d in Proceedings of the European conference on computer vision (ECCV), 2018, pp. 67\u201383."},{"key":"","unstructured":"Liao M., Lyu P., He M., Yao C., Wu W., and Bai X., \u201cMask textspotter: An end-to-end trainable neural network for spotting text with arbitrary shapes,\u201d in IEEE Trans. Pattern Anal. Mach. Intell., 2019, pp. 71\u201388."},{"key":"","unstructured":"Liao M., Pang G., Huang J., Hassner T., and Bai X., \u201cMask textspotter v3: Segmentation proposal network for robust scene text spotting,\u201d in Proceedings of the 16th European Conference on Computer Vision. Springer, 2020, pp. 706\u2013722."},{"key":"","unstructured":"Feng Y. and Wen Y., \u201cVietnamese scene text detection based on modified mask r-cnn,\u201d in Journal of Computer Applications, vol. 41, no. 12, 2021, pp. 3551\u20133557, (in Chinese)."},{"key":"","unstructured":"Le Xuan T., Thi H. P., and Do H. N., \u201cVietnamese text detection, recognition and classification in images,\u201d in Proceedings of 2022 14 th  International Conference on Knowledge and Systems Engineering (KSE). IEEE, 2022, pp. 1\u20136."},{"key":"","unstructured":"Wang L., Feng Y., and Wen Y., \u201cRecognition of vietnamese text in natural scene based on modified dan,\u201d Journal of Data Acquisition and Processing, vol. 38, no. 5, pp. 1058\u20131068, 2023, (in Chinese)."},{"key":"","unstructured":"Huynh Van Huy N. T. T. and Ngo Q. T., \u201cVietnamese scene text detection method based on deep learning,\u201d Journal on Information Technologies & Communications, pp. 1\u20131, 2024."},{"key":"","unstructured":"Huang W., Shi S., and Wen Y., \u201cFocusing on diacritics to improve vietnamese scene text detection,\u201d in The International Joint Conference on Neural Networks, 2024, p. 1\u20138."},{"key":"","unstructured":"Jiang L., Shi S., Huang W., Xu Z., Cu V. L., and Wen Y., \u201cVietnamese scene text detection via edge information and text region feature enhancement,\u201d in Proceedings of International Conference on Pattern Recognition. Springer, 2024, pp. 151\u2013166."},{"key":"","unstructured":"Le A., Mai D. T. H., and Lam T., \u201cA dataset of vietnamese documents for text detection,\u201d in Proceedings of International Conference on Future Data and Security Engineering. Springer, 2023, pp. 418\u2013429."},{"key":"","unstructured":"Van Hoai D. P., Duong H.-T., and Hoang V. T., \u201cText recognition for vietnamese identity card based on deep features network,\u201d Proceedings of International Journal on Document Analysis and Recognition (IJDAR), vol. 24, no. 1, pp. 123\u2013131, 2021."},{"key":"","unstructured":"Liu Z., Lin Y., Cao Y., Hu H., Wei Y., Zhang Z., Lin S., and Guo B., \u201cSwin transformer: Hierarchical vision transformer using shifted windows,\u201d in Proceedings of the IEEE\/CVF international conference on computer vision, 2021, pp. 10012\u201310022."},{"key":"","unstructured":"Carion N., Massa F., Synnaeve G., Usunier N., Kirillov A., and Zagoruyko S., \u201cEnd-to-end object detection with transformers,\u201d in Proceedings of European conference on computer vision. Springer, 2020, pp. 213\u2013229."},{"key":"","unstructured":"Lin T.-Y., Goyal P., Girshick R., He K., and Doll\u00e1r P., \u201cFocal loss for dense object detection,\u201d in Proceedings of the IEEE international conference on computer vision, 2017, pp. 2980\u20132988."},{"key":"","unstructured":"Rezatofighi H., Tsoi N., Gwak J., Sadeghian A., Reid I., and Savarese S., \u201cGeneralized intersection over union: A metric and a loss for bounding box regression,\u201d in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 2019, pp. 658\u2013666."},{"key":"","unstructured":"Hu J., Cao L., Lu Y., Zhang S., Wang Y., Li K., Huang F., Shao L., and Ji R., \u201cIstr: End-to-end instance segmentation with transformers,\u201d arXiv preprint arXiv: 2105.00637, 2021."},{"key":"","unstructured":"Milletari F., Navab N., and Ahmadi S.-A., \u201cV-net: Fully convolutional neural networks for volumetric medical image segmentation,\u201d in Proceedings of 2016 fourth international conference on 3D vision (3DV). Ieee, 2016, pp. 565\u2013571."}],"container-title":["Data Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.sciengine.com\/doi\/pdf\/4A8B1CD0C1C64CB6AE99716E00C1098B","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.sciengine.com\/doi\/10.3724\/2096-7004.di.2025.0127","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.sciengine.com\/doi\/pdf\/4A8B1CD0C1C64CB6AE99716E00C1098B","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T09:04:53Z","timestamp":1774429493000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.sciengine.com\/doi\/10.3724\/2096-7004.di.2025.0127"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,22]]},"references-count":37,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,9,22]]},"published-print":{"date-parts":[[2026,3,1]]}},"URL":"https:\/\/doi.org\/10.3724\/2096-7004.di.2025.0127","relation":{},"ISSN":["2096-7004"],"issn-type":[{"value":"2096-7004","type":"print"}],"subject":[],"published":{"date-parts":[[2025,9,22]]}}}