{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T18:22:39Z","timestamp":1767982959765,"version":"3.49.0"},"reference-count":84,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2021,4,19]],"date-time":"2021-04-19T00:00:00Z","timestamp":1618790400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,4,19]],"date-time":"2021-04-19T00:00:00Z","timestamp":1618790400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1007\/s11263-021-01459-7","type":"journal-article","created":{"date-parts":[[2021,4,19]],"date-time":"2021-04-19T06:02:40Z","timestamp":1618812160000},"page":"1972-1992","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection"],"prefix":"10.1007","volume":"129","author":[{"given":"Yuliang","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Canjie","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuaitao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunhua","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lianwen","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,4,19]]},"reference":[{"key":"1459_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 IEEE conference on computer vision and pattern recognition (pp.\u00a09365\u20139374).","DOI":"10.1109\/CVPR.2019.00959"},{"issue":"4","key":"1459_CR2","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2017","unstructured":"Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2017). Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(4), 834\u2013848.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1459_CR3","doi-asserted-by":"crossref","unstructured":"Chng, 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.\u00a0935\u2013942).","DOI":"10.1109\/ICDAR.2017.157"},{"key":"1459_CR4","doi-asserted-by":"crossref","unstructured":"Ch\u2019ng, C.-K., Chan, C. S., & Liu, C.-L. (2019). Total-text: Toward orientation robustness in scene text detection. International Journal on Document Analysis and Recognition, 1\u201322.","DOI":"10.1007\/s10032-019-00334-z"},{"key":"1459_CR5","doi-asserted-by":"crossref","unstructured":"Chng, C.-K., Liu, Y., Sun, Y., Ng, C. C., Luo, C., & Ni, Z., et al. (2019). ICDAR2019 robust reading challenge on arbitrary-shaped text (RRC-ArT). In Proceedings of international conference on document analysis and recognition.","DOI":"10.1109\/ICDAR.2019.00252"},{"key":"1459_CR6","unstructured":"Dai, J., Li, Y., He, K., & Sun, J. (2016). R-FCN: Object detection via region-based fully convolutional networks. In Proceedings of advances in neural information processing System (pp.\u00a0379\u2013387)."},{"key":"1459_CR7","doi-asserted-by":"crossref","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., & Wei, Y. (2017). Deformable convolutional networks. In Proceedings of IEEE international conference on computer vision (pp. 764\u2013773).","DOI":"10.1109\/ICCV.2017.89"},{"key":"1459_CR8","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 conference on artificial intelligence.","DOI":"10.1609\/aaai.v32i1.12269"},{"key":"1459_CR9","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015). Fast R-CNN. In Proceedings of IEEE international conference on computer vision (pp. 1440\u20131448).","DOI":"10.1109\/ICCV.2015.169"},{"key":"1459_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. (2017c). Mask R-CNN. In Proceedings of IEEE international conference on computer vision (pp. 2980\u20132988).","DOI":"10.1109\/ICCV.2017.322"},{"key":"1459_CR11","doi-asserted-by":"crossref","unstructured":"He, P., Huang, W., He, T., Zhu, Q., Qiao, Y., & Li, X. (2017a). Single shot text detector with regional attention. In Proceedings of IEEE international conference on computer vision, (pp. 3047\u20133055).","DOI":"10.1109\/ICCV.2017.331"},{"issue":"6","key":"1459_CR12","doi-asserted-by":"publisher","first-page":"2529","DOI":"10.1109\/TIP.2016.2547588","volume":"25","author":"T He","year":"2016","unstructured":"He, T., Huang, W., Qiao, Y., & Yao, J. (2016). Text-attentional convolutional neural network for scene text detection. IEEE Transactions on Image Processing, 25(6), 2529\u20132541.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1459_CR13","doi-asserted-by":"crossref","unstructured":"He, T., Tian, Z., Huang, W., Shen, C., Qiao, Y., & Sun, C. (2018b). An end-to-end textspotter with explicit alignment and attention. In Proceedings of IEEE conference on computer vision and pattern recognition (pp.\u00a05020\u20135029).","DOI":"10.1109\/CVPR.2018.00527"},{"key":"1459_CR14","doi-asserted-by":"crossref","unstructured":"He, W., Zhang, X.-Y., Yin, F., & Liu, C.-L. (2017b). Deep direct regression for multi-oriented scene text detection. In Proceedings of IEEE international conference on computer vision.","DOI":"10.1109\/ICCV.2017.87"},{"key":"1459_CR15","doi-asserted-by":"publisher","first-page":"107026","DOI":"10.1016\/j.patcog.2019.107026","volume":"98","author":"W He","year":"2020","unstructured":"He, W., Zhang, X.-Y., Yin, F., Luo, Z., Ogier, J.-M., & Liu, C.-L. (2020). Realtime multi-scale scene text detection with scale-based region proposal network. Pattern Recognition, 98, 107026.","journal-title":"Pattern Recognition"},{"key":"1459_CR16","doi-asserted-by":"crossref","unstructured":"He, Z., Zhou, Y., Wang, Y., Wang, S., Lu, X., Tang, Z., & Cai, L. (2018a). An end-to-end quadrilateral regression network for comic panel extraction. In Proceedings of ACM international conference on multimedia (pp.\u00a0887\u2013895). ACM.","DOI":"10.1145\/3240508.3240555"},{"key":"1459_CR17","doi-asserted-by":"crossref","unstructured":"Hu, H., Zhang, C., Luo, Y., Wang, Y., Han, J., & Ding, E. (2017). Wordsup: Exploiting word annotations for character based text detection. In Proceedings of IEEE international conference on computer vision.","DOI":"10.1109\/ICCV.2017.529"},{"key":"1459_CR18","doi-asserted-by":"crossref","unstructured":"Huang, Z., Huang, L., Gong, Y., Huang, C., & Wang, X. (2019a). Mask scoring r-CNN. In Proceedings of IEEE conference on computer vision and pattern recognition (pp.\u00a06409\u20136418).","DOI":"10.1109\/CVPR.2019.00657"},{"key":"1459_CR19","doi-asserted-by":"crossref","unstructured":"Huang, Z., Zhong, Z., Sun, L., & Huo, Q. (2019b). Mask R-CNN with pyramid attention network for scene text detection. In Proceedings of Winter conference on applications of computer vision (pp.\u00a0764\u2013772), IEEE.","DOI":"10.1109\/WACV.2019.00086"},{"issue":"1","key":"1459_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-015-0823-z","volume":"116","author":"M Jaderberg","year":"2016","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., & Zisserman, A. (2016). Reading text in the wild with convolutional neural networks. International Journal of Computer Vision, 116(1), 1\u201320.","journal-title":"International Journal of Computer Vision"},{"key":"1459_CR21","doi-asserted-by":"crossref","unstructured":"Karatzas, D., & Gomez-Bigorda, L. et\u00a0al. (2015). ICDAR 2015 competition on robust reading. In Proceedings of international conference on document analysis and recognition (pp.\u00a01156\u20131160).","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"1459_CR22","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Shafait, F., Uchida, S., Iwamura, M., Bigorda, L.\u00a0G.\u00a0I., Mestre, S.\u00a0R., Mas, J., Mota, D.\u00a0F., Almaz\u00e0n, J.\u00a0A., & Heras, L.\u00a0P. D.\u00a0L. (2013). ICDAR 2013 robust reading competition. In Proceedings of international conference on document analysis and recognition (pp.\u00a01484\u20131493).","DOI":"10.1109\/ICDAR.2013.221"},{"key":"1459_CR23","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Girshick, R., He, K., & Doll\u00e1r, P. (2019). Panoptic feature pyramid networks. In Proceedings of IEEE conference on computer vision and pattern recognition (pp.\u00a06399\u20136408).","DOI":"10.1109\/CVPR.2019.00656"},{"key":"1459_CR24","doi-asserted-by":"crossref","unstructured":"Li, H., Wang, P., Shen, C., & Zhang, G. (2019b). Show, attend and read: A simple and strong baseline for irregular text recognition. In Proceedings of AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"1459_CR25","doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, Y., Wang, N., & Zhang, Z. (2019a). Scale-aware trident networks for object detection. In Proceedings of IEEE international conference on computer vision.","DOI":"10.1109\/ICCV.2019.00615"},{"key":"1459_CR26","doi-asserted-by":"crossref","unstructured":"Liao, M., Lyu, P., He, M., Yao, C., Wu, W., & Bai, X. (2019). Mask textspotter: An end-to-end trainable neural network for spotting text with arbitrary shapes. IEEE Transactions of Pattern Analysis and Machine Intelligence.","DOI":"10.1109\/TPAMI.2019.2937086"},{"issue":"8","key":"1459_CR27","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. (2018a). 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":"1459_CR28","doi-asserted-by":"crossref","unstructured":"Liao, M., Shi, B., Bai, X., Wang, X., & Liu, W. (2017). \u201cTextboxes: A fast text detector with a single deep neural network. In Proceedings of AAAI conference on artificial intelligence (pp.\u00a04161\u20134167).","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"1459_CR29","doi-asserted-by":"crossref","unstructured":"Liao, M., Zhu, Z., Shi, B., Xia, G.-s., & Bai, X. (2018b). Rotation-sensitive regression for oriented scene text detection. In Proceedings of IEEE conference on computer vision and pattern recognition, (pp.\u00a05909\u20135918).","DOI":"10.1109\/CVPR.2018.00619"},{"key":"1459_CR30","doi-asserted-by":"crossref","unstructured":"Liu, X., Liang, D., Yan, S., Chen, D., Qiao, Y., & Yan, J. (2018). Fots: Fast oriented text spotting with a unified network. In Proceedings of IEEE conference on computer vision and pattern recognition, (pp.\u00a05676\u20135685).","DOI":"10.1109\/CVPR.2018.00595"},{"key":"1459_CR31","doi-asserted-by":"crossref","unstructured":"Liu, Y., & Jin, L. (2017). Deep matching prior network: Toward tighter multi-oriented text detection. In Proceedings of IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2017.368"},{"key":"1459_CR32","doi-asserted-by":"crossref","unstructured":"Liu, Y., Jin, L., & Fang, C. (2019c). Arbitrarily shaped scene text detection with a mask tightness text detector. IEEE Transactions Image Processing.","DOI":"10.1109\/TIP.2019.2954218"},{"key":"1459_CR33","doi-asserted-by":"crossref","unstructured":"Liu, Y., Jin, L., Xie, Z., Luo, C., Zhang, S., & Xie, L. (2019d). Tightness-aware evaluation protocol for scene text detection. In Proceedings of IEEE conference on computer vision and pattern recognition (pp.\u00a09612\u20139620).","DOI":"10.1109\/CVPR.2019.00984"},{"key":"1459_CR34","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. (2019b). Curved scene text detection via transverse and longitudinal sequence connection. Pattern Recognition, 90, 337\u2013345.","journal-title":"Pattern Recognition"},{"key":"1459_CR35","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhang, S., Jin, L., Xie, L., Wu, Y., & Wang, Z. (2019a). Omnidirectional scene text detection with sequential-free box discretization. In Proceedings of international joint conference on artificial intelligence.","DOI":"10.24963\/ijcai.2019\/423"},{"key":"1459_CR36","doi-asserted-by":"crossref","unstructured":"Liu, Z., Hu, J., Weng, L., & Yang, Y. (2017). Rotated region based cnn for ship detection. In Proceedings of IEEE international conference on image processing (pp.\u00a0900\u2013904). IEEE.","DOI":"10.1109\/ICIP.2017.8296411"},{"key":"1459_CR37","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 3431\u20133440).","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"1459_CR38","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":"1459_CR39","doi-asserted-by":"crossref","unstructured":"Lyu, P., Liao, M., Yao, C., Wu, W., & Bai, X. (2018b). Mask textspotter: An end-to-end trainable neural network for spotting text with arbitrary shapes. In: Proceedings of European conference on computer vision (pp. 67\u201383).","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"1459_CR40","doi-asserted-by":"crossref","unstructured":"Lyu, P., Yao, C., Wu, W., Yan, S., & Bai, X. (2018aa). Multi-oriented scene text detection via corner localization and region segmentation. In Proceedings of IEEE conference on computer vision and pattern recognition, (pp.\u00a07553\u20137563).","DOI":"10.1109\/CVPR.2018.00788"},{"key":"1459_CR41","doi-asserted-by":"crossref","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.","DOI":"10.1109\/TMM.2018.2818020"},{"key":"1459_CR42","doi-asserted-by":"crossref","unstructured":"Nayef, N., Patel, Y., Busta, M., Chowdhury, P. N., Karatzas, D., & Khlif, W., et al. (2019). ICDAR2019 robust reading challenge on multi-lingual scene text detection and recognition-RRC-MLT-2019. In Proceedings of international conference on document analysis and recognition","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"1459_CR43","doi-asserted-by":"crossref","unstructured":"Nayef, N., Yin, F., Bizid, I., Choi, H., Feng, Y., Karatzas, D., Luo, Z., Pal, U., Rigaud, C., & Chazalon, J. et\u00a0al. (2017). ICDAR2017 robust reading challenge on multi-lingual scene text detection and script identification-RRC-MLT. In Proceedings of international conference on document analysis and recognition, vol.\u00a01 (pp.\u00a01454\u20131459). IEEE.","DOI":"10.1109\/ICDAR.2017.237"},{"key":"1459_CR44","doi-asserted-by":"crossref","unstructured":"Neumann, L., & Matas, J. (2012). Real-time scene text localization and recognition. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 3538\u20133545). IEEE.","DOI":"10.1109\/CVPR.2012.6248097"},{"issue":"9","key":"1459_CR45","doi-asserted-by":"publisher","first-page":"1872","DOI":"10.1109\/TPAMI.2015.2496234","volume":"38","author":"L Neumann","year":"2015","unstructured":"Neumann, L., & Matas, J. (2015a). Real-time lexicon-free scene text localization and recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(9), 1872\u20131885.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1459_CR46","doi-asserted-by":"crossref","unstructured":"Neumann, L., & Matas, J. (2015b). Efficient scene text localization and recognition with local character refinement. In Proceedings of international conference on document analysis and recognition (pp.\u00a0746\u2013750). IEEE.","DOI":"10.1109\/ICDAR.2015.7333861"},{"key":"1459_CR47","doi-asserted-by":"crossref","unstructured":"Qin, S., Bissacco, A., Raptis, M., Fujii, Y., & Xiao, Y. (2019). Towards unconstrained end-to-end text spotting. In Proceedings of IEEE international conference on computer vision.","DOI":"10.1109\/ICCV.2019.00480"},{"key":"1459_CR48","doi-asserted-by":"crossref","unstructured":"Redmon, J., & Farhadi, A. (2017). Yolo9000: better, faster, stronger. In Proceedings of IEEE conference on computer vision and pattern recognition (pp.\u00a07263\u20137271).","DOI":"10.1109\/CVPR.2017.690"},{"key":"1459_CR49","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-CNN: Towards real-time object detection with region proposal networks. In Proceedings of advances in neural information processing systems (pp.\u00a091\u201399)."},{"key":"1459_CR50","doi-asserted-by":"crossref","unstructured":"Shi, B., Bai, X., & Belongie, S. (2017a). Detecting oriented text in natural images by linking segments. In Proceedings of IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2017.371"},{"issue":"11","key":"1459_CR51","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2017","unstructured":"Shi, B., Bai, X., & Yao, C. (2017c). An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(11), 2298\u20132304.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1459_CR52","doi-asserted-by":"crossref","unstructured":"Shi, B., Yao, C., Liao, M., Yang, M., Xu, P., Cui, L., Belongie, S., Lu, S., & Bai, X. (2017b). ICDAR2017 competition on reading chinese text in the wild (RCTW-17). In Proceedings of international conference on document analysis and recognition, vol.\u00a01 (pp.\u00a01429\u20131434).","DOI":"10.1109\/ICDAR.2017.233"},{"key":"1459_CR53","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 IEEE conference on computer vision and pattern recognition. (pp.\u00a0761\u2013769).","DOI":"10.1109\/CVPR.2016.89"},{"key":"1459_CR54","doi-asserted-by":"crossref","unstructured":"Sun, Y., Ni, Z., Chng, C.-K., Liu, Y., Luo, C., & Ng, C. C., et al. (2019). ICDAR 2019 competition on large-scale street view text with partial labeling-RRC-LSVT. In Proceedings of international conference on document analysis and recognition.","DOI":"10.1109\/ICDAR.2019.00250"},{"key":"1459_CR55","doi-asserted-by":"crossref","unstructured":"Tang, J., Yang, Z., Wang, Y., Zheng, Q., Xu, Y., & Bai, X. (2019). Detecting dense and arbitrary-shaped scene text by instance-aware component grouping. Pattern Recognition.","DOI":"10.1016\/j.patcog.2019.06.020"},{"key":"1459_CR56","doi-asserted-by":"crossref","unstructured":"Tian, S., Pan, Y., Huang, C., Lu, S., Yu, K., & Lim T. C. (2015). Text flow: A unified text detection system in natural scene images. Proceedings of IEEE international conference on computer vision (pp. 4651\u20134659).","DOI":"10.1109\/ICCV.2015.528"},{"key":"1459_CR57","doi-asserted-by":"crossref","unstructured":"Tian, Z., Huang, W., He, T., He, P., & Qiao, Y. (2016). Detecting text in natural image with connectionist text proposal network. In Proceedings of European conference on computer vision (pp.\u00a056\u201372). Springer.","DOI":"10.1007\/978-3-319-46484-8_4"},{"key":"1459_CR58","unstructured":"Tianwei, W., Yuanzhi, Z., Lianwen, J., Luo, C., Chen, X., & Wu, Y., et al. (2020). Decoupled attention network for text recognition. In Proceedings of AAAI conference on artificial intelligence."},{"key":"1459_CR59","unstructured":"Veit, A., & Matera, T. et\u00a0al. (2016). Coco-text: Dataset and benchmark for text detection and recognition in natural images. arXiv preprint arXiv:1601.07140."},{"key":"1459_CR60","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, K., Yang, S., Loy, C.\u00a0C., & Lin, D. (2019b). Region proposal by guided anchoring. In Proceedings of IEEE conference on computer vision and pattern recognition (pp.\u00a02965\u20132974).","DOI":"10.1109\/CVPR.2019.00308"},{"key":"1459_CR61","unstructured":"Wang, P., Yang, L., Li, H., Deng, Y., Shen, C., & Zhang, Y. (2019e). A simple and robust convolutional-attention network for irregular text recognition. arXiv:1904.01375."},{"key":"1459_CR62","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Hou, W., Lu, T., Yu, G., & Shao, S. (2019a). Shape Robust text detection with progressive scale expansion network. In Proceedings of IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00956"},{"key":"1459_CR63","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. Proceedings of IEEE international conference on computer vision.","DOI":"10.1109\/ICCV.2019.00853"},{"key":"1459_CR64","doi-asserted-by":"crossref","unstructured":"Wang, X., Jiang, Y., Luo, Z., Liu, C.-L., Choi, H., & Kim, S. (2019). Arbitrary shape scene text detection with adaptive text region representation. In Proceedings of IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00661"},{"key":"1459_CR65","unstructured":"Wei, F., Wenhao, H., Fei, Y., Xu-Yao, Z., & Liu, C.-L. (2019). TextDragon: An end-to-end framework for arbitrary shaped text spotting. In Proceedings of IEEE international conference on computer vision."},{"key":"1459_CR66","doi-asserted-by":"crossref","unstructured":"Wu, Y., & Natarajan, P. (2017). Self-organized text detection with minimal post-processing via border learning. In Proceedings of IEEE conference on computer vision and pattern recognition (pp.\u00a05000\u20135009).","DOI":"10.1109\/ICCV.2017.535"},{"key":"1459_CR67","doi-asserted-by":"crossref","unstructured":"Xie, E., Zang, Y., Shao, S., Yu, G., Yao, C., & Li, G. (2019a). Scene text detection with supervised pyramid context network. In Proceedings of AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v33i01.33019038"},{"issue":"1","key":"1459_CR68","first-page":"1","volume":"15","author":"H Xie","year":"2019","unstructured":"Xie, H., Fang, S., Zha, Z.-J., Yang, Y., Li, Y., & Zhang, Y. (2019c). Convolutional attention networks for scene text recognition. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 15(1), 1\u201317.","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)"},{"key":"1459_CR69","doi-asserted-by":"crossref","unstructured":"Xie, L., Liu, Y., Jin, L., & Xie, Z. (2019b). DeRPN: Taking a further step toward more general object detection. In Proceedings of AAAI conference on artificial intelligence, vol.\u00a033 (pp.\u00a09046\u20139053).","DOI":"10.1609\/aaai.v33i01.33019046"},{"key":"1459_CR70","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.","DOI":"10.1109\/TIP.2019.2900589"},{"key":"1459_CR71","doi-asserted-by":"crossref","unstructured":"Xue, C., Lu, S., & Zhan, F. (2018). Accurate scene text detection through border semantics awareness and bootstrapping. In Proceedings of European conference on computer vision, (pp. 355\u2013372).","DOI":"10.1007\/978-3-030-01270-0_22"},{"key":"1459_CR72","doi-asserted-by":"crossref","unstructured":"Xue, C., Lu, S., & Zhang, W. (2019). Msr: Multi-scale shape regression for scene text detection. In Proceedings of international joint conference on artificial intelligence.","DOI":"10.24963\/ijcai.2019\/139"},{"key":"1459_CR73","doi-asserted-by":"crossref","unstructured":"Yang, Q., Cheng, M., Zhou, W., Chen, Y., Qiu, M., Lin, W., & Chu, W. (2018). Inceptext: A new inception-text module with deformable psroi pooling for multi-oriented scene text detection. In Proceedings of joint international conference on artificial intelligence.","DOI":"10.24963\/ijcai.2018\/149"},{"key":"1459_CR74","unstructured":"Yao, C., Bai, X., Liu, W., & Ma, Y. (2012). Detecting texts of arbitrary orientations in natural images. In Proceedings of IEEE conference on computer vision and pattern recognition (pp.\u00a01083\u20131090)."},{"key":"1459_CR75","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1109\/TPAMI.2014.2388210","volume":"37","author":"X-C Yin","year":"2015","unstructured":"Yin, X.-C., Pei, W. Y., Zhang, J., & Hao, H. W. (2015). Multi-orientation scene text detection with adaptive clustering. IEEE Transaction on Pattern Analysis and Machine Intelligence, 37, 1930.","journal-title":"IEEE Transaction on Pattern Analysis and Machine Intelligence"},{"key":"1459_CR76","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 IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.01080"},{"key":"1459_CR77","doi-asserted-by":"crossref","unstructured":"Zhang, H., Dana, K., Shi, J., Zhang, Z., Wang, X., Tyagi, A., & Agrawal, A. (2018). Context encoding for semantic segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7151\u20137160).","DOI":"10.1109\/CVPR.2018.00747"},{"key":"1459_CR78","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 IEEE conference on computer vision and pattern recognition, (pp.\u00a04159\u20134167).","DOI":"10.1109\/CVPR.2016.451"},{"key":"1459_CR79","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Jin, L., Zhang, S., & Feng, Z. (2016). \u201cDeeptext: A unified framework for text proposal generation and text detection in natural images. arXiv preprint arXiv:1605.07314.","DOI":"10.1109\/ICASSP.2017.7952348"},{"key":"1459_CR80","doi-asserted-by":"publisher","first-page":"106986","DOI":"10.1016\/j.patcog.2019.106986","volume":"96","author":"Z Zhong","year":"2019","unstructured":"Zhong, Z., Sun, L., & Huo, Q. (2019a). Improved localization accuracy by locnet for faster R-CNN based text detection in natural scene images. Pattern Recognition, 96, 106986.","journal-title":"Pattern Recognition"},{"issue":"3","key":"1459_CR81","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1007\/s10032-019-00335-y","volume":"22","author":"Z Zhong","year":"2019","unstructured":"Zhong, Z., Sun, L., & Huo, Q. (2019b). An anchor-free region proposal network for faster R-CNN-based text detection approaches. International Journal of Document Analysis & Recognition, 22(3), 315\u2013327.","journal-title":"International Journal of Document Analysis & Recognition"},{"key":"1459_CR82","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. Proceedings of IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2017.283"},{"key":"1459_CR83","doi-asserted-by":"crossref","unstructured":"Zhu, Y., & Du, J. (2018). Sliding line point regression for shape robust scene text detection. In Proceedings of international conference on pattern recognition.","DOI":"10.1109\/ICPR.2018.8545067"},{"key":"1459_CR84","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Du, J., & Wu, X. (2020). Adaptive period embedding for representing oriented objects in aerial images. IEEE Transactions on Geoscience & Remote Sensing.","DOI":"10.1109\/TGRS.2020.2981203"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01459-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-021-01459-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01459-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,24]],"date-time":"2022-12-24T17:02:49Z","timestamp":1671901369000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-021-01459-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,19]]},"references-count":84,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,6]]}},"alternative-id":["1459"],"URL":"https:\/\/doi.org\/10.1007\/s11263-021-01459-7","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,19]]},"assertion":[{"value":"19 December 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 March 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 April 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}