{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:14:18Z","timestamp":1784301258873,"version":"3.55.0"},"reference-count":73,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2024,3,5]],"date-time":"2024-03-05T00:00:00Z","timestamp":1709596800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,5]],"date-time":"2024-03-05T00:00:00Z","timestamp":1709596800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1007\/s11263-024-02022-w","type":"journal-article","created":{"date-parts":[[2024,3,5]],"date-time":"2024-03-05T09:02:38Z","timestamp":1709629358000},"page":"3119-3138","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["CBNet: A Plug-and-Play Network for Segmentation-Based Scene Text Detection"],"prefix":"10.1007","volume":"132","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4934-0976","authenticated-orcid":false,"given":"Xi","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingjing","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhangang","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinghe","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingping","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,5]]},"reference":[{"key":"2022_CR1","doi-asserted-by":"crossref","unstructured":"Baek, Y., Lee, B., Han, D., Yun, S., & Lee, H. (2019). Character region awareness for text detection. In Proceedings of CVPR (pp. 9365\u20139374).","DOI":"10.1109\/CVPR.2019.00959"},{"key":"2022_CR2","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F., Hu, H. (2019). Gcnet: Non-local networks meet squeeze-excitation networks and beyond. In Proceedings of ICCVW (pp. 1971\u20131980).","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"2022_CR3","doi-asserted-by":"crossref","unstructured":"Ch\u2019ng, C. K., & Chan, C. S. (2017). Total-text: A comprehensive dataset for scene text detection and recognition. In Proceedings of ICDAR (pp. 935\u2013942).","DOI":"10.1109\/ICDAR.2017.157"},{"key":"2022_CR4","doi-asserted-by":"crossref","unstructured":"Dai, P., Zhang, S., Zhang, H., & Cao, X. (2021). Progressive contour regression for arbitrary-shape scene text detection. In Proceedings of CVPR (pp. 7393\u20137402).","DOI":"10.1109\/CVPR46437.2021.00731"},{"key":"2022_CR5","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In Proceedings of CVPR (pp. 248\u2013255).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2022_CR6","doi-asserted-by":"crossref","unstructured":"Deng, D., Liu, H., Li, X., & Cai, D. (2018). Pixellink: Detecting scene text via instance segmentation. In Proceedings of AAAI (pp. 6773\u20136780).","DOI":"10.1609\/aaai.v32i1.12269"},{"issue":"3","key":"2022_CR7","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1007\/s11263-020-01388-x","volume":"129","author":"W Feng","year":"2021","unstructured":"Feng, W., Yin, F., Zhang, X.-Y., He, W., & Liu, C.-L. (2021). Residual dual scale scene text spotting by fusing bottom-up and top\u2013down processing. International Journal of Computer Vision, 129(3), 619\u2013637.","journal-title":"International Journal of Computer Vision"},{"key":"2022_CR8","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A. (2016). Synthetic data for text localisation in natural images. In Proceedings of CVPR (pp. 2315\u20132324).","DOI":"10.1109\/CVPR.2016.254"},{"key":"2022_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. (2017). Mask R-CNN. In Proceedings of CVPR (pp. 2961\u20132969).","DOI":"10.1109\/ICCV.2017.322"},{"key":"2022_CR10","doi-asserted-by":"crossref","unstructured":"He, M., Liao, M., Yang, Z., Zhong, H., Tang, J., Cheng, W., Yao, C., Wang, Y., & Bai, X. (2021). Most: A multi-oriented scene text detector with localization refinement. In Proceedings of CVPR (pp. 8813\u20138822).","DOI":"10.1109\/CVPR46437.2021.00870"},{"key":"2022_CR11","doi-asserted-by":"crossref","unstructured":"He, M., Liu, Y., Yang, Z., Zhang, S., Luo, C., Gao, F., Zheng, Q., Wang, Y., Zhang, X., & Jin, L. (2018). Icpr2018 contest on robust reading for multi-type web images. In Proceedings of ICPR (pp. 7\u201312).","DOI":"10.1109\/ICPR.2018.8546143"},{"key":"2022_CR12","doi-asserted-by":"crossref","unstructured":"Howard, A., Sandler, M., Chu, G., Chen, L.-C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., & Vasudevan, V. (2019). Searching for mobilenetv3. In Proceedings of ICCV (pp. 1314\u20131324).","DOI":"10.1109\/ICCV.2019.00140"},{"key":"2022_CR13","unstructured":"Kingma, D. P., Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980"},{"key":"2022_CR14","doi-asserted-by":"crossref","unstructured":"Liao, M., Pang, G., Huang, J., Hassner, T., & Bai, X. (2020). Mask textspotter v3: Segmentation proposal network for robust scene text spotting. In Proceedings of ECCV (pp. 706\u2013722). Springer.","DOI":"10.1007\/978-3-030-58621-8_41"},{"key":"2022_CR15","doi-asserted-by":"crossref","unstructured":"Liao, M., Shi, B., Bai, X., Wang, X., & Liu, W. (2017) Textboxes: A fast text detector with a single deep neural network. In Proceedings AAAI (pp. 4161\u20134167).","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"2022_CR16","doi-asserted-by":"crossref","unstructured":"Liao, M., Wan, Z., Yao, C., Chen, K., & Bai, X. (2020). Real-time scene text detection with differentiable binarization. In: Proceedings of AAAI (pp. 11474\u201311481).","DOI":"10.1609\/aaai.v34i07.6812"},{"issue":"8","key":"2022_CR17","doi-asserted-by":"publisher","first-page":"3676","DOI":"10.1109\/TIP.2018.2825107","volume":"27","author":"M Liao","year":"2018","unstructured":"Liao, M., Shi, B., & Bai, X. (2018). Textboxes++: A single-shot oriented scene text detector. IEEE Transactions on Image Processing, 27(8), 3676\u20133690.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2022_CR18","doi-asserted-by":"publisher","first-page":"919","DOI":"10.1109\/TPAMI.2022.3155612","volume":"45","author":"M Liao","year":"2022","unstructured":"Liao, M., Zou, Z., Wan, Z., Yao, C., & Bai, X. (2022). Real-time scene text detection with differentiable binarization and adaptive scale fusion. IEEE Transactions on Pattern Analysis and Machine Intelligence., 45, 919.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence."},{"key":"2022_CR19","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A.C. (2016) SSD: Single shot multibox detector. In Proceedings of ECCV (pp. 21\u201337).","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2022_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Y., Chen, H., Shen, C., He, T., Jin, L., Wang, L. (2020). Abcnet: Real-time scene text spotting with adaptive bezier-curve network. In Proceedings of CVPR (pp. 9809\u20139818).","DOI":"10.1109\/CVPR42600.2020.00983"},{"key":"2022_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Y., Jin, L. (2017) Deep matching prior network: Toward tighter multi-oriented text detection. In Proceedings CVPR (pp. 1962\u20131969).","DOI":"10.1109\/CVPR.2017.368"},{"key":"2022_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of ICCV (pp. 10012\u201310022).","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2022_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Y., Shen, C., Jin, L., He, T., Chen, P., Liu, C., & Chen, H. (2021). Abcnet v2: Adaptive Bezier-curve network for real-time end-to-end text spotting. arXiv preprint arXiv:2105.03620","DOI":"10.1109\/TPAMI.2021.3107437"},{"key":"2022_CR24","doi-asserted-by":"crossref","unstructured":"Liu, S.-A., Xie, H., Xu, H., Zhang, Y., & Tian, Q. (2022). Partial class activation attention for semantic segmentation. In Proceedings of CVPR (pp. 16836\u201316845).","DOI":"10.1109\/CVPR52688.2022.01633"},{"key":"2022_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhang, S., Jin, L., Xie, L., Wu, Y., & Wang, Z. (2019). Omnidirectional scene text detection with sequential-free box discretization. arXiv preprint arXiv:1906.02371","DOI":"10.24963\/ijcai.2019\/423"},{"issue":"6","key":"2022_CR26","doi-asserted-by":"publisher","first-page":"1786","DOI":"10.1007\/s11263-020-01298-y","volume":"128","author":"Z Liu","year":"2020","unstructured":"Liu, Z., Lin, G., & Goh, W. L. (2020). Bottom-up scene text detection with Markov clustering networks. International Journal of Computer Vision, 128(6), 1786\u20131809.","journal-title":"International Journal of Computer Vision"},{"key":"2022_CR27","doi-asserted-by":"crossref","unstructured":"Long, S., Qin, S., Panteleev, D., Bissacco, A., Fujii, Y., Raptis, M. (2022). Towards end-to-end unified scene text detection and layout analysis. In Proceedings of CVPR (pp. 1049\u20131059).","DOI":"10.1109\/CVPR52688.2022.00112"},{"key":"2022_CR28","doi-asserted-by":"crossref","unstructured":"Long, S., Ruan, J., Zhang, W., He, X., Wu, W., & Yao, C. (2018). Textsnake: A flexible representation for detecting text of arbitrary shapes. In Proceedings of ECCV (pp. 20\u201336).","DOI":"10.1007\/978-3-030-01216-8_2"},{"key":"2022_CR29","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In Proceedings of CVPR (pp. 3431\u20133440).","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"2022_CR30","doi-asserted-by":"crossref","unstructured":"Lyu, P., Liao, M., Yao, C., Wu, W., & Bai, X. (2018) Mask textspotter: An end-to-end trainable neural network for spotting text with arbitrary shapes. In Proceedings of ECCV (pp. 67\u201383).","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"2022_CR31","doi-asserted-by":"crossref","unstructured":"Lyu, P., Yao, C., Wu, W., Yan, S., & Bai, X. (2018). 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).","DOI":"10.1109\/CVPR.2018.00788"},{"key":"2022_CR32","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., Wang, L., Wang, H., Zheng, Y., & Xue, X. (2018). Arbitrary-oriented scene text detection via rotation proposals. IEEE Transactions on Multimedia, 20, 3111\u20133122.","journal-title":"IEEE Transactions on Multimedia"},{"key":"2022_CR33","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., & Ahmadi, S.-A. (2016). V-net: Fully convolutional neural networks for volumetric medical image segmentation. In Proceedings of 3DV (pp. 565\u2013571).","DOI":"10.1109\/3DV.2016.79"},{"key":"2022_CR34","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. (2019). Icdar2019 robust reading challenge on multi-lingual scene text detection and recognition-RRC-MLT-2019. In Proceedings of ICDAR (pp. 1582\u20131587).","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"2022_CR35","unstructured":"Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., & Lerer, A. (2017). Automatic differentiation in pytorch."},{"key":"2022_CR36","doi-asserted-by":"crossref","unstructured":"Qin, X., Zhou, Y., Guo, Y., Wu, D., & Wang, W. (2021). Fc$$^2$$RN: A fully convolutional corner refinement network for accurate multi-oriented scene text detection. In Proceedings of ICASSP (pp. 4350\u20134354). IEEE.","DOI":"10.1109\/ICASSP39728.2021.9413821"},{"key":"2022_CR37","doi-asserted-by":"crossref","unstructured":"Raisi, Z., Younes, G., & Zelek, J. (2022). Arbitrary shape text detection using transformers. In Proceedings of ICPR (pp. 3238\u20133245). IEEE.","DOI":"10.1109\/ICPR56361.2022.9956488"},{"key":"2022_CR38","doi-asserted-by":"crossref","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2017). Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 1137\u20131149.","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"2022_CR39","first-page":"335","volume":"34","author":"T Sheng","year":"2021","unstructured":"Sheng, T., Chen, J., & Lian, Z. (2021). Centripetaltext: An efficient text instance representation for scene text detection. Advances in Neural Information Processing Systems, 34, 335\u2013346.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2022_CR40","doi-asserted-by":"crossref","unstructured":"Shi, B., Bai, X., & Belongie, S. (2017). Detecting oriented text in natural images by linking segments. In Proceedings of CVPR (pp. 2550\u20132558).","DOI":"10.1109\/CVPR.2017.371"},{"key":"2022_CR41","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Gupta, A., & Girshick, R. (2016). Training region-based object detectors with online hard example mining. In Proceedings of CVPR (pp. 761\u2013769).","DOI":"10.1109\/CVPR.2016.89"},{"key":"2022_CR42","doi-asserted-by":"crossref","unstructured":"Tang, J., Zhang, W., Liu, H., Yang, M., Jiang, B., Hu, G., & Bai, X. (2022) Few could be better than all: Feature sampling and grouping for scene text detection. In Proceedings CVPR (pp. 4563\u20134572).","DOI":"10.1109\/CVPR52688.2022.00452"},{"key":"2022_CR43","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., Zheng, Q., Xu, Y., & Bai, X. (2019). Seglink++: Detecting dense and arbitrary-shaped scene text by instance-aware component grouping. Pattern Recognition, 96, 106954.","journal-title":"Pattern Recognition"},{"key":"2022_CR44","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shu, M., Lyu, P., Li, R., Zhou, C., Shen, X., & Jia, J. (2019). Learning shape-aware embedding for scene text detection. In Proceedings of CVPR (pp. 4234\u20134243).","DOI":"10.1109\/CVPR.2019.00436"},{"key":"2022_CR45","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1145\/129902.129906","volume":"35","author":"BR Vatti","year":"1992","unstructured":"Vatti, B. R. (1992). A generic solution to polygon clipping. Communications of the ACM, 35, 56\u201363.","journal-title":"Communications of the ACM"},{"key":"2022_CR46","unstructured":"Veit, A., Matera, T., Neumann, L., Matas, J., & Belongie, S. (2016). Coco-text: Dataset and benchmark for text detection and recognition in natural images. arXiv preprint arXiv:1601.07140"},{"key":"2022_CR47","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., & He, K. (2018). Non-local neural networks. In Proceedings of CVPR (pp. 7794\u20137803).","DOI":"10.1109\/CVPR.2018.00813"},{"key":"2022_CR48","doi-asserted-by":"crossref","unstructured":"Wang, X., Jiang, Y., Luo, Z., Liu, C.L., Kim, S. (2019a). Arbitrary shape scene text detection with adaptive text region representation. In Proceedings of CVPR (pp. 6449\u20136458).","DOI":"10.1109\/CVPR.2019.00661"},{"key":"2022_CR49","doi-asserted-by":"crossref","unstructured":"Wang, H., Lu, P., Zhang, H., Yang, M., Bai, X., Xu, Y., He, M., Wang, Y., & Liu, W. (2020a). All you need is boundary: Toward arbitrary-shaped text spotting. In Proceedings of AAAI (vol. 34, pp. 12160\u201312167).","DOI":"10.1609\/aaai.v34i07.6896"},{"key":"2022_CR50","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Hou, W., Lu, T., Yu, G., & Shao, S. (2019b). Shape robust text detection with progressive scale expansion network. In Proceedings of CVPR (pp. 9336\u20139345).","DOI":"10.1109\/CVPR.2019.00956"},{"key":"2022_CR51","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Song, X., Zang, Y., Wang, W., Lu, T., Yu, G., & Shen, C. (2019c). Efficient and accurate arbitrary-shaped text detection with pixel aggregation network. In: Proceedings of ICCV (pp. 8440\u20138449).","DOI":"10.1109\/ICCV.2019.00853"},{"key":"2022_CR52","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xie, H., Zha, Z.-J., Xing, M., Fu, Z., & Zhang, Y. (2020b). Contournet: Taking a further step toward accurate arbitrary-shaped scene text detection. In Proceedings of CVPR (pp. 11753\u201311762).","DOI":"10.1109\/CVPR42600.2020.01177"},{"key":"2022_CR53","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zheng, Y., & Betke, M. (2020c). A method for detecting text of arbitrary shapes in natural scenes that improves text spotting. In Proceedings of CVPRW (pp. 540\u2013541).","DOI":"10.1109\/CVPRW50498.2020.00278"},{"issue":"9","key":"2022_CR54","first-page":"5349","volume":"44","author":"W Wang","year":"2021","unstructured":"Wang, W., Xie, E., Li, X., Liu, X., Liang, D., Yang, Z., Lu, T., & Shen, C. (2021). Pan++: Towards efficient and accurate end-to-end spotting of arbitrarily-shaped text. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(9), 5349\u20135367.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2022_CR55","doi-asserted-by":"crossref","unstructured":"Xie, E., Zang, Y., Shao, S., Yu, G., Yao, C., Li, G. (2019). Scene text detection with supervised pyramid context network. In Proceedings of AAAI (pp. 9038\u20139045).","DOI":"10.1609\/aaai.v33i01.33019038"},{"key":"2022_CR56","doi-asserted-by":"crossref","unstructured":"Xue, C., Lu, S., & Zhang, W. (2019). MSR: Multi-scale shape regression for scene text detection. In Proceedings of IJCAI (pp. 989\u2013995).","DOI":"10.24963\/ijcai.2019\/139"},{"key":"2022_CR57","doi-asserted-by":"crossref","unstructured":"Xu, Y., Wang, Y., Zhou, W., Wang, Y., Yang, Z., & Bai, X. (2019). Textfield: Learning a deep direction field for irregular scene text detection. IEEE Transactions on Image Processing, 28, 5566\u20135579.","DOI":"10.1109\/TIP.2019.2900589"},{"key":"2022_CR58","unstructured":"Yao, C., Bai, X., Liu, W., Ma, Y., & Tu, Z. (2012). Detecting texts of arbitrary orientations in natural images. In Proceedings of CVPR (pp. 1083\u20131090)."},{"key":"2022_CR59","unstructured":"Yao, C., Bai, X., Sang, N., Zhou, X., Zhou, S., & Cao, Z. (2016). Scene text detection via holistic, multi-channel prediction. arXiv preprint arXiv:1606.09002"},{"issue":"11","key":"2022_CR60","doi-asserted-by":"publisher","first-page":"4737","DOI":"10.1109\/TIP.2014.2353813","volume":"23","author":"C Yao","year":"2014","unstructured":"Yao, C., Bai, X., & Liu, W. (2014). A unified framework for multioriented text detection and recognition. IEEE Transactions on Image Processing, 23(11), 4737\u20134749.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2022_CR61","doi-asserted-by":"crossref","unstructured":"Ye, J., Chen, Z., Liu, J., & Du, B. (2020). Textfusenet: Scene text detection with richer fused features. In Proceedings of IJCAI (vol. 20, pp. 516\u2013522).","DOI":"10.24963\/ijcai.2020\/72"},{"key":"2022_CR62","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Chen, X., Wang, J. (2020). Object-contextual representations for semantic segmentation. In Proceedings of ECCV (pp. 173\u2013190).","DOI":"10.1007\/978-3-030-58539-6_11"},{"key":"2022_CR63","unstructured":"Yuliang, L., Lianwen, J., Shuaitao, Z., & Sheng, Z. (2017). Detecting curve text in the wild: New dataset and new solution. arXiv preprint arXiv:1712.02170"},{"key":"2022_CR64","doi-asserted-by":"crossref","unstructured":"Zhang, F., Chen, Y., Li, Z., Hong, Z., Ding, E. (2019). Acfnet: Attentional class feature network for semantic segmentation. In Proceedings of ICCV (pp. 6798\u20136807).","DOI":"10.1109\/ICCV.2019.00690"},{"key":"2022_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, C., Liang, B., Huang, Z., En, M., Han, J., Ding, E., & Ding, X. (2019). Look more than once: An accurate detector for text of arbitrary shapes. In Proceedings of CVPR (pp. 10552\u201310561).","DOI":"10.1109\/CVPR.2019.01080"},{"key":"2022_CR66","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhang, C., Shen, W., Yao, C., Liu, W., Bai, X. (2016) Multi-oriented text detection with fully convolutional networks. In Proceedings of CVPR (pp. 4159\u20134167).","DOI":"10.1109\/CVPR.2016.451"},{"key":"2022_CR67","doi-asserted-by":"crossref","unstructured":"Zhang, S.-X., Zhu, X., Hou, J.-B., Liu, C., Yang, C., Wang, H., & Yin, X.-C. (2020). Deep relational reasoning graph network for arbitrary shape text detection. In Proceedings of CVPR (pp. 9699\u20139708).","DOI":"10.1109\/CVPR42600.2020.00972"},{"key":"2022_CR68","doi-asserted-by":"crossref","unstructured":"Zhang, S.-X., Zhu, X., Yang, C., Wang, H., & Yin, X.-C. (2021). Adaptive boundary proposal network for arbitrary shape text detection. In Proceedings of ICCV (pp. 1305\u20131314).","DOI":"10.1109\/ICCV48922.2021.00134"},{"key":"2022_CR69","unstructured":"Zhang, S.-X., Zhu, X., Yang, C., Yin, X.-C. (2022). Arbitrary shape text detection via boundary transformer. arXiv preprint arXiv:2205.05320"},{"key":"2022_CR70","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Xie, H., Fang, S., Li, Y., & Zhang, Y. (2020). Crnet: A center-aware representation for detecting text of arbitrary shapes. In Proceedings of ACM-MM (pp. 2571\u20132580).","DOI":"10.1145\/3394171.3413565"},{"key":"2022_CR71","doi-asserted-by":"crossref","unstructured":"Zhou, X., Yao, C., Wen, H., Wang, Y., Zhou, S., He, W., & Liang, J. (2017). East: An efficient and accurate scene text detector. In Proceedings of CVPR (pp. 5551\u20135560).","DOI":"10.1109\/CVPR.2017.283"},{"key":"2022_CR72","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Chen, J., Liang, L., Kuang, Z., Jin, L., & Zhang, W. (2021). Fourier contour embedding for arbitrary-shaped text detection. In Proceedings of CVPR (pp. 3123\u20133131).","DOI":"10.1109\/CVPR46437.2021.00314"},{"key":"2022_CR73","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107336","volume":"110","author":"Y Zhu","year":"2021","unstructured":"Zhu, Y., & Du, J. (2021). Textmountain: Accurate scene text detection via instance segmentation. Pattern Recognition, 110, 107336.","journal-title":"Pattern Recognition"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02022-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02022-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02022-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T14:29:46Z","timestamp":1720708186000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02022-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,5]]},"references-count":73,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["2022"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02022-w","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,5]]},"assertion":[{"value":"9 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 January 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 March 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}