{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T17:46:24Z","timestamp":1780595184325,"version":"3.54.1"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T00:00:00Z","timestamp":1738195200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T00:00:00Z","timestamp":1738195200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62306113"],"award-info":[{"award-number":["62306113"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62272164"],"award-info":[{"award-number":["62272164"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s00371-025-03802-2","type":"journal-article","created":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T12:15:11Z","timestamp":1738239311000},"page":"7233-7248","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["MTMFNet: multi-threshold and multi-scale feature fusion network for text detection"],"prefix":"10.1007","volume":"41","author":[{"given":"Lei","family":"Dai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengyu","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihua","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,30]]},"reference":[{"key":"3802_CR1","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shu, M., Lyu, P., et\u00a0al.: Learning shape-aware embedding for scene text detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4234\u20134243 (2019)","DOI":"10.1109\/CVPR.2019.00436"},{"key":"3802_CR2","doi-asserted-by":"crossref","unstructured":"Liu, Y., Chen, H., Shen, C., et\u00a0al.: ABCNet: real-time scene text spotting with adaptive Bezier-curve network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9809\u20139818 (2020)","DOI":"10.1109\/CVPR42600.2020.00983"},{"key":"3802_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107767","volume":"236","author":"Y Zhong","year":"2022","unstructured":"Zhong, Y., Cheng, X., Chen, T., et al.: PRPN: progressive region prediction network for natural scene text detection. Knowl. Based Syst. 236, 107767 (2022)","journal-title":"Knowl. Based Syst."},{"key":"3802_CR4","doi-asserted-by":"crossref","unstructured":"Qian, B., Wen, Y., Sheng, B.: Self-paced co-training and foundation model for semi-supervised medical image segmentation. In: 2024 IEEE International Conference on Multimedia and Expo (ICME), IEEE, pp. 1\u20136 (2024)","DOI":"10.1109\/ICME57554.2024.10688310"},{"key":"3802_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.102919","volume":"154","author":"J Li","year":"2024","unstructured":"Li, J., Zhang, P., Yang, X., et al.: SSM-Net: semi-supervised multi-task network for joint lesion segmentation and classification from pancreatic EUS images. Artif. Intell. Med. 154, 102919 (2024)","journal-title":"Artif. Intell. Med."},{"key":"3802_CR6","doi-asserted-by":"crossref","unstructured":"Baek, Y., Lee, B., Han, D., et\u00a0al.: Character region awareness for text detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9365\u20139374 (2019)","DOI":"10.1109\/CVPR.2019.00959"},{"key":"3802_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., et\u00a0al.: Mask r-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017a)","DOI":"10.1109\/ICCV.2017.322"},{"key":"3802_CR8","doi-asserted-by":"crossref","unstructured":"Lyu, P., Liao, M., Yao, C., et\u00a0al.: Mask textspotter: an end-to-end trainable neural network for spotting text with arbitrary shapes. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 67\u201383 (2018)","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"3802_CR9","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Chen, J., Liang, L., et\u00a0al.: Fourier contour embedding for arbitrary-shaped text detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3123\u20133131 (2021)","DOI":"10.1109\/CVPR46437.2021.00314"},{"key":"3802_CR10","doi-asserted-by":"crossref","unstructured":"Liu, X., Liang, D., Yan, S., et\u00a0al.: FOTS: fast oriented text spotting with a unified network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5676\u20135685 (2018a)","DOI":"10.1109\/CVPR.2018.00595"},{"key":"3802_CR11","doi-asserted-by":"crossref","unstructured":"Huang, M., Liu, Y., Peng, Z., et\u00a0al.: Swintextspotter: scene text spotting via better synergy between text detection and text recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4593\u20134603 (2022)","DOI":"10.1109\/CVPR52688.2022.00455"},{"key":"3802_CR12","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., et\u00a0al.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"3802_CR13","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s11704-015-4488-0","volume":"10","author":"Y Zhu","year":"2016","unstructured":"Zhu, Y., Yao, C., Bai, X.: Scene text detection and recognition: recent advances and future trends. Front. Comput. Sci. 10, 19\u201336 (2016)","journal-title":"Front. Comput. Sci."},{"key":"3802_CR14","doi-asserted-by":"publisher","first-page":"1432","DOI":"10.1109\/TIP.2024.3364056","volume":"33","author":"Y Chen","year":"2024","unstructured":"Chen, Y., Jiang, R., Zheng, Y., et al.: Dual branch multi-level semantic learning for few-shot segmentation. IEEE Trans. Image Process. 33, 1432\u20131447 (2024)","journal-title":"IEEE Trans. Image Process."},{"issue":"7","key":"3802_CR15","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.1109\/TPAMI.2014.2366765","volume":"37","author":"Q Ye","year":"2014","unstructured":"Ye, Q., Doermann, D.: Text detection and recognition in imagery: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 37(7), 1480\u20131500 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"3802_CR16","doi-asserted-by":"publisher","first-page":"2775","DOI":"10.1007\/s00371-023-02985-w","volume":"40","author":"S Masood","year":"2024","unstructured":"Masood, S., Ali, S.G., Wang, X., et al.: Deep choroid layer segmentation using hybrid features extraction from OCT images. Vis. Comput. 40(4), 2775\u20132792 (2024)","journal-title":"Vis. Comput."},{"key":"3802_CR17","doi-asserted-by":"crossref","unstructured":"Liao, M., Shi, B., Bai, X., et\u00a0al.: Textboxes: a fast text detector with a single deep neural network. In: Proceedings of the AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"3802_CR18","doi-asserted-by":"crossref","unstructured":"Tian, Z., Huang, W., He, T., et\u00a0al.: Detecting text in natural image with connectionist text proposal network. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part VIII 14, Springer, Berlin, pp 56\u201372 (2016)","DOI":"10.1007\/978-3-319-46484-8_4"},{"key":"3802_CR19","doi-asserted-by":"crossref","unstructured":"Shi, B., Bai, X., Belongie, S.: Detecting oriented text in natural images by linking segments. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2550\u20132558 (2017)","DOI":"10.1109\/CVPR.2017.371"},{"issue":"11","key":"3802_CR20","doi-asserted-by":"publisher","first-page":"3111","DOI":"10.1109\/TMM.2018.2818020","volume":"20","author":"J Ma","year":"2018","unstructured":"Ma, J., Shao, W., Ye, H., et al.: Arbitrary-oriented scene text detection via rotation proposals. IEEE Trans. Multimedia 20(11), 3111\u20133122 (2018)","journal-title":"IEEE Trans. Multimedia"},{"key":"3802_CR21","unstructured":"Ren, S., He, K., Girshick, R., et\u00a0al.: Faster r-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems 28 (2015)"},{"key":"3802_CR22","doi-asserted-by":"crossref","unstructured":"Deng, D., Liu, H., Li, X., et\u00a0al.: Pixellink: detecting scene text via instance segmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12269"},{"key":"3802_CR23","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., et\u00a0al.: Shape robust text detection with progressive scale expansion network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9336\u20139345 (2019)","DOI":"10.1109\/CVPR.2019.00956"},{"key":"3802_CR24","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Song, X., et\u00a0al.: Efficient and accurate arbitrary-shaped text detection with pixel aggregation network. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8440\u20138449 (2019)","DOI":"10.1109\/ICCV.2019.00853"},{"key":"3802_CR25","doi-asserted-by":"crossref","unstructured":"Liao, M., Wan, Z., Yao, C., et\u00a0al.: Real-time scene text detection with differentiable binarization. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 11474\u201311481 (2020)","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"3802_CR26","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et\u00a0al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3802_CR27","doi-asserted-by":"crossref","unstructured":"He, W., Zhang, X.Y., Yin, F., et\u00a0al.: Deep direct regression for multi-oriented scene text detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 745\u2013753 (2017b)","DOI":"10.1109\/ICCV.2017.87"},{"key":"3802_CR28","doi-asserted-by":"crossref","unstructured":"Zhou, X., Yao, C., Wen, H., et\u00a0al.: EAST: an efficient and accurate scene text detector. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5551\u20135560 (2017)","DOI":"10.1109\/CVPR.2017.283"},{"key":"3802_CR29","doi-asserted-by":"crossref","unstructured":"Lyu, P., Yao, C., Wu, W., et\u00a0al.: Multi-oriented scene text detection via corner localization and region segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7553\u20137563 (2018)","DOI":"10.1109\/CVPR.2018.00788"},{"key":"3802_CR30","doi-asserted-by":"crossref","unstructured":"Dai, Y., Huang, Z., Gao, Y., et\u00a0al.: Fused text segmentation networks for multi-oriented scene text detection. In: 2018 24th International Conference on Pattern Recognition (ICPR), IEEE, pp. 3604\u20133609 (2018)","DOI":"10.1109\/ICPR.2018.8546066"},{"key":"3802_CR31","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, G., Yang, S., et\u00a0al.: Learning Markov clustering networks for scene text detection.(2018b). arXiv preprint arXiv:1805.08365","DOI":"10.1109\/CVPR.2018.00725"},{"key":"3802_CR32","doi-asserted-by":"crossref","unstructured":"Long, S., Ruan, J., Zhang, W., et\u00a0al.: TextSnake: a flexible representation for detecting text of arbitrary shapes. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 20\u201336 (2018)","DOI":"10.1007\/978-3-030-01216-8_2"},{"key":"3802_CR33","doi-asserted-by":"crossref","unstructured":"Liao, M., Zhu, Z., Shi, B., et\u00a0al.: Rotation-sensitive regression for oriented scene text detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5909\u20135918 (2018)","DOI":"10.1109\/CVPR.2018.00619"},{"key":"3802_CR34","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.06.020","volume":"96","author":"J Tang","year":"2019","unstructured":"Tang, J., Yang, Z., Wang, Y., et al.: Seglink++: detecting dense and arbitrary-shaped scene text by instance-aware component grouping. Pattern Recogn. 96, 106954 (2019)","journal-title":"Pattern Recogn."},{"key":"3802_CR35","doi-asserted-by":"crossref","unstructured":"Xue, C., Lu, S., Zhang, W.: MSR: multi-scale shape regression for scene text detection (2019). arXiv preprint arXiv:1901.02596","DOI":"10.24963\/ijcai.2019\/139"},{"key":"3802_CR36","doi-asserted-by":"publisher","first-page":"2864","DOI":"10.1109\/TIP.2022.3141844","volume":"31","author":"C Yang","year":"2022","unstructured":"Yang, C., Chen, M., Xiong, Z., et al.: CM-Net: concentric mask based arbitrary-shaped text detection. IEEE Trans. Image Process. 31, 2864\u20132877 (2022)","journal-title":"IEEE Trans. Image Process."},{"issue":"5","key":"3802_CR37","first-page":"1","volume":"40","author":"C Zhu","year":"2023","unstructured":"Zhu, C., Yi, B., Luo, L.: CNBCC: cubic non-uniform b-spline closed curve for arbitrary shape text detection. Vis. Comput. 40(5), 1\u201310 (2023)","journal-title":"Vis. Comput."},{"key":"3802_CR38","doi-asserted-by":"crossref","unstructured":"Ye, M., Zhang, J., Zhao, S., et\u00a0al.: DPTEXT-DETR: towards better scene text detection with dynamic points in transformer. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 3241\u20133249 (2023)","DOI":"10.1609\/aaai.v37i3.25430"},{"key":"3802_CR39","doi-asserted-by":"publisher","first-page":"1747","DOI":"10.1109\/TMM.2023.3286657","volume":"26","author":"SX Zhang","year":"2023","unstructured":"Zhang, S.X., Yang, C., Zhu, X., et al.: Arbitrary shape text detection via boundary transformer. IEEE Trans. Multimedia 26, 1747\u20131760 (2023)","journal-title":"IEEE Trans. Multimedia"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03802-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-03802-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03802-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T04:32:06Z","timestamp":1757133126000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-03802-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,30]]},"references-count":39,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["3802"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-03802-2","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,30]]},"assertion":[{"value":"3 January 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 January 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The relevant technology is filed for patenting with the patent application No. CN202311640081.7. The authors declare that they have no other non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}