{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T15:19:41Z","timestamp":1784387981142,"version":"3.55.0"},"reference-count":65,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2022,5,31]],"date-time":"2022-05-31T00:00:00Z","timestamp":1653955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,5,31]],"date-time":"2022-05-31T00:00:00Z","timestamp":1653955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076186"],"award-info":[{"award-number":["62076186"]}],"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":["61822113"],"award-info":[{"award-number":["61822113"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Major Project of Hubei Province","award":["2019AEA170"],"award-info":[{"award-number":["2019AEA170"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2022,8]]},"DOI":"10.1007\/s11263-022-01616-6","type":"journal-article","created":{"date-parts":[[2022,5,31]],"date-time":"2022-05-31T07:05:35Z","timestamp":1653980735000},"page":"1961-1977","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":44,"title":["I3CL: Intra- and Inter-Instance Collaborative Learning for Arbitrary-Shaped Scene Text Detection"],"prefix":"10.1007","volume":"130","author":[{"given":"Bo","family":"Du","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3907-8820","authenticated-orcid":false,"given":"Juhua","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,5,31]]},"reference":[{"key":"1616_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 the IEEE conference on computer vision and pattern recognition (pp. 9365\u20139374)","DOI":"10.1109\/CVPR.2019.00959"},{"key":"1616_CR2","doi-asserted-by":"crossref","unstructured":"Baek, Y., Shin, S., Baek, J., Park, S., Lee, J., Nam, D., & Lee, H. (2020). Character region attention for text spotting. In: Proceedings of the European conference on computer vision (pp. 504\u2013521). Springer.","DOI":"10.1007\/978-3-030-58526-6_30"},{"key":"1616_CR3","doi-asserted-by":"crossref","unstructured":"Bodla, N., Singh, B., Chellappa, R., Davis, LS. (2017). Soft-NMS\u2014Improving object detection with one line of code. In Proceedings of the IEEE international conference on computer vision (pp. 5561\u20135569).","DOI":"10.1109\/ICCV.2017.593"},{"issue":"1","key":"1616_CR4","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1007\/s11263-020-01370-7","volume":"129","author":"Z Chen","year":"2021","unstructured":"Chen, Z., Zhang, J., & Tao, D. (2021). Recursive context routing for object detection. International Journal of Computer Vision, 129(1), 142\u2013160.","journal-title":"International Journal of Computer Vision"},{"key":"1616_CR5","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 international conference on document analysis and recognition (pp. 935\u2013942).","DOI":"10.1109\/ICDAR.2017.157"},{"key":"1616_CR6","doi-asserted-by":"crossref","unstructured":"Chng, C. K., Liu, Y., Sun, Y., Ng, C. C., Luo, C., Ni, Z., et\u00a0al. (2019). Icdar2019 robust reading challenge on arbitrary-shaped text-RRC-art. In Proceedings of international conference on document analysis and recognition (ICDAR) (pp. 1571\u20131576). IEEE.","DOI":"10.1109\/ICDAR.2019.00252"},{"issue":"8","key":"1616_CR7","doi-asserted-by":"publisher","first-page":"1969","DOI":"10.1109\/TMM.2019.2952978","volume":"22","author":"P Dai","year":"2019","unstructured":"Dai, P., Zhang, H., & Cao, X. (2019). Deep multi-scale context aware feature aggregation for curved scene text detection. IEEE Transactions on Multimedia, 22(8), 1969\u20131984.","journal-title":"IEEE Transactions on Multimedia"},{"key":"1616_CR8","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 the IEEE\/CVF conference on computer vision and pattern recognition (pp. 7393\u20137402).","DOI":"10.1109\/CVPR46437.2021.00731"},{"key":"1616_CR9","doi-asserted-by":"crossref","unstructured":"Feng, W., He, W., Yin, F., Zhang, X. Y., & Liu, C. L. (2019) Textdragon: An end-to-end framework for arbitrary shaped text spotting. In Proceedings of the IEEE international conference on computer vision (pp. 9076\u20139085).","DOI":"10.1109\/ICCV.2019.00917"},{"key":"1616_CR10","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., & Zisserman, A. (2016) Synthetic data for text localisation in natural images. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2315\u20132324).","DOI":"10.1109\/CVPR.2016.254"},{"key":"1616_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"1616_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. (2017) Mask r-CNN. In Proceedings of the IEEE international conference on computer vision (pp. 2961\u20132969).","DOI":"10.1109\/ICCV.2017.322"},{"issue":"8","key":"1616_CR13","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":"1616_CR14","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 of the AAAI conference on artificial intelligence (pp. 4161\u20134167). AAAI Press.","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"1616_CR15","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 the AAAI conference on artificial intelligence (Vol. 34, pp. 11474\u201311481).","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"1616_CR16","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2117\u20132125).","DOI":"10.1109\/CVPR.2017.106"},{"key":"1616_CR17","doi-asserted-by":"publisher","first-page":"5924","DOI":"10.1109\/TIP.2020.2984082","volume":"29","author":"J Liu","year":"2020","unstructured":"Liu, J., Chen, Z., Du, B., & Tao, D. (2020). Asts: A unified framework for arbitrary shape text spotting. IEEE Transactions on Image Processing, 29, 5924\u20135936.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1616_CR18","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 European conference on computer vision (pp. 21\u201337). Springer.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1616_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Y., Chen, H., Shen, C., He, T., Jin, L., & Wang, L. (2020b). 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).","DOI":"10.1109\/CVPR42600.2020.00983"},{"key":"1616_CR20","doi-asserted-by":"publisher","first-page":"2918","DOI":"10.1109\/TIP.2019.2954218","volume":"29","author":"Y Liu","year":"2019","unstructured":"Liu, Y., Jin, L., & Fang, C. (2019). Arbitrarily shaped scene text detection with a mask tightness text detector. IEEE Transactions on Image Processing, 29, 2918\u20132930.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1616_CR21","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1016\/j.patcog.2019.02.002","volume":"90","author":"Y Liu","year":"2019","unstructured":"Liu, Y., Jin, L., Zhang, S., Luo, C., & Zhang, S. (2019). Curved scene text detection via transverse and longitudinal sequence connection. Pattern Recognition, 90, 337\u2013345.","journal-title":"Pattern Recognition"},{"key":"1616_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, G., Yang, S., Liu, F., Lin, W., & Goh, WL. (2019c). Towards robust curve text detection with conditional spatial expansion. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7269\u20137278).","DOI":"10.1109\/CVPR.2019.00744"},{"key":"1616_CR23","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. arXiv preprint arXiv:2103.14030.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1616_CR24","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 European conference on computer vision (pp. 20\u201336).","DOI":"10.1007\/978-3-030-01216-8_2"},{"key":"1616_CR25","doi-asserted-by":"crossref","unstructured":"Nayef, N., Patel, Y., Busta, M., Chowdhury, P. N., Karatzas, D., et\u00a0al.(2019) Icdar2019 robust reading challenge on multi-lingual scene text detection and recognition-rrc-mlt-2019. In Proceedings of the international conference on document analysis and recognition (pp. 1582\u20131587). IEEE.","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"1616_CR26","doi-asserted-by":"crossref","unstructured":"Qiao, L., Tang, S., Cheng, Z., Xu, Y., Niu, Y., Pu, S., & Wu, F. (2020). Text perceptron: Towards end-to-end arbitrary-shaped text spotting. In Proceedings of the AAAI conference on artificial intelligence (Vol. 34, pp. 11899\u201311907).","DOI":"10.1609\/aaai.v34i07.6864"},{"key":"1616_CR27","doi-asserted-by":"crossref","unstructured":"Shi, B., Bai, X., & Belongie, S. (2017) Detecting oriented text in natural images by linking segments. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2550\u20132558).","DOI":"10.1109\/CVPR.2017.371"},{"key":"1616_CR28","unstructured":"Song, G., & Chai, W. (2018) Collaborative learning for deep neural networks. arXiv preprint arXiv:1805.11761."},{"key":"1616_CR29","doi-asserted-by":"crossref","unstructured":"Sun, Y., Ni, Z., Chng, CK., Liu, Y., Luo, C., Ng, CC., et\u00a0al.(2019) Icdar 2019 competition on large-scale street view text with partial labeling-rrc-lsvt. In Proceedings of the international conference on document analysis and recognition (pp. 1557\u20131562). IEEE.","DOI":"10.1109\/ICDAR.2019.00250"},{"key":"1616_CR30","doi-asserted-by":"publisher","first-page":"106954","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":"1616_CR31","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shu, M., Lyu, P., Li, R., Zhou, C., Shen, X., et al. (2019). Learning shape-aware embedding for scene text detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4234\u20134243).","DOI":"10.1109\/CVPR.2019.00436"},{"key":"1616_CR32","doi-asserted-by":"crossref","unstructured":"Wang, F., Chen, Y., Wu, F., & Li, X. (2020a) Textray: Contour-based geometric modeling for arbitrary-shaped scene text detection. In Proceedings of the 28th ACM international conference on multimedia (pp. 111\u2013119).","DOI":"10.1145\/3394171.3413819"},{"key":"1616_CR33","doi-asserted-by":"crossref","unstructured":"Wang, H., Lu, P., Zhang, H., Yang, M., Bai, X., Xu, Y., et al. (2020). All you need is boundary: Toward arbitrary-shaped text spotting. In Proceedings of the AAAI conference on artificial intelligence (Vol. 34, pp. 12160\u201312167).","DOI":"10.1609\/aaai.v34i07.6896"},{"key":"1616_CR34","doi-asserted-by":"crossref","unstructured":"Wang, J., Yao, J., Zhang, Y., & Zhang, R. (2018) Collaborative learning for weakly supervised object detection. arXiv preprint arXiv:1802.03531.","DOI":"10.24963\/ijcai.2018\/135"},{"key":"1616_CR35","unstructured":"Wang, L., Li, D., Zhu, Y., Tian, L., & Shan, Y. (2021) Cross-dataset collaborative learning for semantic segmentation. arXiv preprint arXiv:2103.11351."},{"key":"1616_CR36","doi-asserted-by":"crossref","unstructured":"Wang, P., Zhang, C., Qi, F., Huang, Z., En, M., et al. (2019a). A single-shot arbitrarily-shaped text detector based on context attended multi-task learning. In Proceedings of the 27th ACM international conference on multimedia (pp. 1277\u20131285).","DOI":"10.1145\/3343031.3350988"},{"key":"1616_CR37","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 the IEEE conference on computer vision and pattern recognition (pp. 9336\u20139345).","DOI":"10.1109\/CVPR.2019.00956"},{"key":"1616_CR38","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Song, X., Zang, Y., Wang, W., Lu, T., et al. (2019c). 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).","DOI":"10.1109\/ICCV.2019.00853"},{"key":"1616_CR39","doi-asserted-by":"crossref","unstructured":"Wang, X., Jiang, Y., Luo, Z., Liu, CL., Choi, H., & Kim, S. (2019d) Arbitrary shape scene text detection with adaptive text region representation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 6449\u20136458).","DOI":"10.1109\/CVPR.2019.00661"},{"key":"1616_CR40","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xie, H., Zha, Z. J., Xing, M., Fu, Z., & Zhang, Y. (2020c). Contournet: Taking a further step toward accurate arbitrary-shaped scene text detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 11753\u201311762).","DOI":"10.1109\/CVPR42600.2020.01177"},{"key":"1616_CR41","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 the AAAI conference on artificial intelligence (Vol. 33, pp. 9038\u20139045).","DOI":"10.1609\/aaai.v33i01.33019038"},{"key":"1616_CR42","doi-asserted-by":"crossref","unstructured":"Xie, Q., Luong, M. T., Hovy, E., & Le, QV. (2020). Self-training with noisy student improves imagenet classification. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10687\u201310698).","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"1616_CR43","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., & He, K. (2017). Aggregated residual transformations for deep neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1492\u20131500).","DOI":"10.1109\/CVPR.2017.634"},{"issue":"11","key":"1616_CR44","doi-asserted-by":"publisher","first-page":"5566","DOI":"10.1109\/TIP.2019.2900589","volume":"28","author":"Y Xu","year":"2019","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(11), 5566\u20135579.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1616_CR45","first-page":"28522","volume":"34","author":"Y Xu","year":"2021","unstructured":"Xu, Y., Zhang, Q., Zhang, J., & Tao, D. (2021). Vitae: Vision transformer advanced by exploring intrinsic inductive bias. Advances in Neural Information Processing Systems, 34, 28522\u201328535.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"1616_CR46","doi-asserted-by":"crossref","unstructured":"Xue, C., Lu, S., & Zhang, W. (2019) MSR: Multi-scale shape regression for scene text detection. In Proceedings of the twenty-eighth international joint conference on artificial intelligence, ijcai.org (pp. 989\u2013995).","DOI":"10.24963\/ijcai.2019\/139"},{"key":"1616_CR47","doi-asserted-by":"crossref","unstructured":"Yang, Q., Cheng, M., Zhou, W., Chen, Y., Qiu, M., & Lin, W. (2018). Inceptext: A new inception-text module with deformable PSROI pooling for multi-oriented scene text detection. In Proceedings of the twenty-seventh international joint conference on artificial intelligence (pp. 1071\u20131077).","DOI":"10.24963\/ijcai.2018\/149"},{"key":"1616_CR48","doi-asserted-by":"crossref","unstructured":"Yang, Q., Wei, X., Wang, B., Hua, XS., & Zhang, L. (2021) Interactive self-training with mean teachers for semi-supervised object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 5941\u20135950).","DOI":"10.1109\/CVPR46437.2021.00588"},{"key":"1616_CR49","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 the twenty-ninth international joint conference on artificial intelligence (pp. 516\u2013522).","DOI":"10.24963\/ijcai.2020\/72"},{"key":"1616_CR50","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":"1616_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, C., Liang, B., Huang, Z., En, M., Han, J., Ding, E., & Ding, X. (2019a) Look more than once: An accurate detector for text of arbitrary shapes. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 10552\u201310561).","DOI":"10.1109\/CVPR.2019.01080"},{"key":"1616_CR52","unstructured":"Zhang, H., Cisse, M., Dauphin, Y. N., Lopez-Paz, D. (2017) mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412."},{"key":"1616_CR53","unstructured":"Zhang, H., Wu, C., Zhang, Z., Zhu, Y., Lin, H., Zhang, Z., et\u00a0al.(2020a) Resnest: Split-attention networks. arXiv preprint arXiv:2004.08955."},{"issue":"10","key":"1616_CR54","doi-asserted-by":"publisher","first-page":"7789","DOI":"10.1109\/JIOT.2020.3039359","volume":"8","author":"J Zhang","year":"2020","unstructured":"Zhang, J., & Tao, D. (2020). Empowering things with intelligence: A survey of the progress, challenges, and opportunities in artificial intelligence of things. IEEE Internet of Things Journal, 8(10), 7789\u20137817.","journal-title":"IEEE Internet of Things Journal"},{"issue":"9","key":"1616_CR55","doi-asserted-by":"publisher","first-page":"2639","DOI":"10.1007\/s11263-021-01482-8","volume":"129","author":"J Zhang","year":"2021","unstructured":"Zhang, J., Chen, Z., & Tao, D. (2021). Towards high performance human keypoint detection. International Journal of Computer Vision, 129(9), 2639\u20132662.","journal-title":"International Journal of Computer Vision"},{"key":"1616_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, P., Zhang, B., Zhang, T., Chen, D., Wang, Y., & Wen, F. (2021b). Prototypical pseudo label denoising and target structure learning for domain adaptive semantic segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 12414\u201312424).","DOI":"10.1109\/CVPR46437.2021.01223"},{"key":"1616_CR57","unstructured":"Zhang, Q., Zhang, J., Liu, W., & Tao, D. (2019b) Category anchor-guided unsupervised domain adaptation for semantic segmentation. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8\u201314, 2019, Vancouver, BC, Canada, pp. 433\u2013443."},{"key":"1616_CR58","unstructured":"Zhang, Q., Xu, Y., Zhang, J., & Tao, D. (2022). Vitaev2: Vision transformer advanced by exploring inductive bias for image recognition and beyond. arXiv preprint arXiv:2202.10108."},{"key":"1616_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, S. X., Zhu, X., Hou, J. B., Liu, C., Yang, C., Wang, H., et al. (2020b) Deep relational reasoning graph network for arbitrary shape text detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 9699\u20139708).","DOI":"10.1109\/CVPR42600.2020.00972"},{"key":"1616_CR60","doi-asserted-by":"crossref","unstructured":"Zhang, X., Yue, Y., Yang, Y., Zhang, X., Wang, W., & Zou, Q. (2020c). Collaborative learning network for scene text detection. In 2020 Chinese automation congress (CAC) (pp .6788\u20136793). IEEE.","DOI":"10.1109\/CAC51589.2020.9327576"},{"key":"1616_CR61","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 the IEEE conference on computer vision and pattern recognition (pp. 5551\u20135560).","DOI":"10.1109\/CVPR.2017.283"},{"key":"1616_CR62","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 the 28th ACM international conference on multimedia (pp. 2571\u20132580).","DOI":"10.1145\/3394171.3413565"},{"key":"1616_CR63","doi-asserted-by":"publisher","first-page":"107336","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"},{"key":"1616_CR64","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 the IEEE\/CVF conference on computer vision and pattern recognition (pp. 3123\u20133131).","DOI":"10.1109\/CVPR46437.2021.00314"},{"key":"1616_CR65","doi-asserted-by":"crossref","unstructured":"Zou, Y., Yu, Z., Liu, X., Kumar, BVKV., & Wang, J. (2019) Confidence regularized self-training. In 2019 IEEE\/CVF international conference on computer vision, ICCV 2019, Seoul, Korea (South), October 27\u2013November 2, 2019 (pp. 5981\u20135990). IEEE.","DOI":"10.1109\/ICCV.2019.00608"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-022-01616-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-022-01616-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-022-01616-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,14]],"date-time":"2022-07-14T09:14:37Z","timestamp":1657790077000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-022-01616-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,31]]},"references-count":65,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2022,8]]}},"alternative-id":["1616"],"URL":"https:\/\/doi.org\/10.1007\/s11263-022-01616-6","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,31]]},"assertion":[{"value":"23 August 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 April 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 May 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}