{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:50:27Z","timestamp":1742914227375,"version":"3.40.3"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031705489"},{"type":"electronic","value":"9783031705496"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-70549-6_7","type":"book-chapter","created":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T09:02:15Z","timestamp":1725786135000},"page":"111-128","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Progressive Evolution from\u00a0Single-Point to\u00a0Polygon for\u00a0Scene Text"],"prefix":"10.1007","author":[{"given":"Linger","family":"Deng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingxin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xudong","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuliang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lianwen","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,9]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Baek, Y., Lee, B., Han, D., Yun, S., Lee, H.: 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"},{"issue":"6","key":"7_CR2","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1109\/34.24792","volume":"11","author":"FL Bookstein","year":"1989","unstructured":"Bookstein, F.L.: Principal warps: thin-plate splines and the decomposition of deformations. IEEE Trans. Pattern Anal. Mach. Intell. 11(6), 567\u2013585 (1989)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Xu, Y., Bai, F., Niu, Y., Pu, S., Zhou, S.: AON: towards arbitrarily-oriented text recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5571\u20135579 (2018)","DOI":"10.1109\/CVPR.2018.00584"},{"issue":"1","key":"7_CR4","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/s10032-019-00334-z","volume":"23","author":"CK Ch\u2019ng","year":"2020","unstructured":"Ch\u2019ng, C.K., Chan, C.S., Liu, C.L.: Total-text: toward orientation robustness in scene text detection. Int. J. Doc. Anal. Recogn. (IJDAR) 23(1), 31\u201352 (2020)","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"7_CR5","doi-asserted-by":"publisher","unstructured":"Du, Y., et al.: SVTR: scene text recognition with a single visual model. In: Raedt, L.D. (ed.) Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence. IJCAI-22, pp. 884\u2013890. International Joint Conferences on Artificial Intelligence Organization (2022). https:\/\/doi.org\/10.24963\/ijcai.2022\/124, main Track","DOI":"10.24963\/ijcai.2022\/124"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2315\u20132324 (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"He, W., Zhang, X.Y., Yin, F., Liu, C.L.: Deep direct regression for multi-oriented scene text detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 745\u2013753 (2017)","DOI":"10.1109\/ICCV.2017.87"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Hu, H., Zhang, C., Luo, Y., Wang, Y., Han, J., Ding, E.: WordSup: exploiting word annotations for character based text detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4940\u20134949 (2017)","DOI":"10.1109\/ICCV.2017.529"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Huang, M., et al.: 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":"7_CR10","doi-asserted-by":"crossref","unstructured":"Huang, M., et al.: ESTextSpotter: towards better scene text spotting with explicit synergy in transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19495\u201319505 (2023)","DOI":"10.1109\/ICCV51070.2023.01786"},{"key":"7_CR11","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. arXiv preprint arXiv:1406.2227 (2014)"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et\u00a0al.: ICDAR 2015 competition on robust reading. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1156\u20131160. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Kil, T., Kim, S., Seo, S., Kim, Y., Kim, D.: Towards unified scene text spotting based on sequence generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15223\u201315232 (2023)","DOI":"10.1109\/CVPR52729.2023.01461"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Kittenplon, Y., Lavi, I., Fogel, S., Bar, Y., Manmatha, R., Perona, P.: Towards weakly-supervised text spotting using a multi-task transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4604\u20134613 (2022)","DOI":"10.1109\/CVPR52688.2022.00456"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Kuang, Z., et\u00a0al.: MMOCR: a comprehensive toolbox for text detection, recognition and understanding. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 3791\u20133794 (2021)","DOI":"10.1145\/3474085.3478328"},{"issue":"2","key":"7_CR16","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1109\/TPAMI.2019.2937086","volume":"43","author":"M Liao","year":"2021","unstructured":"Liao, M., Lyu, P., He, M., Yao, C., Wu, W., Bai, X.: Mask textspotter: an end-to-end trainable neural network for spotting text with arbitrary shapes. IEEE Trans. Pattern Anal. Mach. Intell. 43(2), 532\u2013548 (2021). https:\/\/doi.org\/10.1109\/TPAMI.2019.2937086","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Liao, M., Shi, B., Bai, X., Wang, X., Liu, W.: Textboxes: a fast text detector with a single deep neural network. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Liao, M., Wan, Z., Yao, C., Chen, K., Bai, X.: Real-time scene text detection with differentiable binarization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 11474\u201311481 (2020)","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"7_CR19","doi-asserted-by":"publisher","first-page":"8760","DOI":"10.1109\/TIP.2020.3018859","volume":"29","author":"C Liu","year":"2020","unstructured":"Liu, C., Liu, Y., Jin, L., Zhang, S., Luo, C., Wang, Y.: Erasenet: end-to-end text removal in the wild. IEEE Trans. Image Process. 29, 8760\u20138775 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Liu, R., Lu, N., Chen, D., Li, C., Yuan, Z., Peng, W.: PBformer: capturing complex scene text shape with polynomial band transformer. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 2112\u20132120 (2023)","DOI":"10.1145\/3581783.3612059"},{"key":"7_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Y., Chen, H., Shen, C., He, T., Jin, L., Wang, L.: 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":"7_CR23","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.: Curved scene text detection via transverse and longitudinal sequence connection. Pattern Recogn. 90, 337\u2013345 (2019)","journal-title":"Pattern Recogn."},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Y., et\u00a0al.: SPTS v2: single-point scene text spotting. arXiv preprint arXiv:2301.01635 (2023)","DOI":"10.1109\/TPAMI.2023.3312285"},{"key":"7_CR25","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.patcog.2019.01.020","volume":"90","author":"C Luo","year":"2019","unstructured":"Luo, C., Jin, L., Sun, Z.: Moran: a multi-object rectified attention network for scene text recognition. Pattern Recogn. 90, 109\u2013118 (2019)","journal-title":"Pattern Recogn."},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Peng, D., et\u00a0al.: SPTS: single-point text spotting. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4272\u20134281 (2022)","DOI":"10.1145\/3503161.3547942"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Qu, Y., Tan, Q., Xie, H., Xu, J., Wang, Y., Zhang, Y.: Exploring stroke-level modifications for scene text editing. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 2119\u20132127 (2023)","DOI":"10.1609\/aaai.v37i2.25305"},{"issue":"9","key":"7_CR28","doi-asserted-by":"publisher","first-page":"2035","DOI":"10.1109\/TPAMI.2018.2848939","volume":"41","author":"B Shi","year":"2018","unstructured":"Shi, B., Yang, M., Wang, X., Lyu, P., Yao, C., Bai, X.: Aster: an attentional scene text recognizer with flexible rectification. IEEE Trans. Pattern Anal. Mach. Intell. 41(9), 2035\u20132048 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Tang, J., Qiao, S., Cui, B., Ma, Y., Zhang, S., Kanoulas, D.: You can even annotate text with voice: transcription-only-supervised text spotting. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4154\u20134163 (2022)","DOI":"10.1145\/3503161.3547787"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Tian, S., Lu, S., Li, C.: Wetext: scene text detection under weak supervision. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1492\u20131500 (2017)","DOI":"10.1109\/ICCV.2017.166"},{"key":"7_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1007\/978-3-319-46484-8_4","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Z Tian","year":"2016","unstructured":"Tian, Z., Huang, W., He, T., He, P., Qiao, Yu.: Detecting text in natural image with connectionist text proposal network. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part VIII. LNCS, vol. 9912, pp. 56\u201372. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_4"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: 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":"7_CR33","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: 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":"7_CR34","unstructured":"Wang, Y., Xie, H., Fang, S., Qu, Y., Zhang, Y.: PERT: a progressively region-based network for scene text removal. arXiv preprint arXiv:2106.13029 (2021)"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Wu, L., et al.: Editing text in the wild. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 1500\u20131508 (2019)","DOI":"10.1145\/3343031.3350929"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Wu, W., Xie, E., Zhang, R., Wang, W., Luo, P., Hong, Z.: Polygon-free: unconstrained scene text detection with box annotations. In: Proceedings of the IEEE International Conference on Image Processing, pp. 1226\u20131230 (2022)","DOI":"10.1109\/ICIP46576.2022.9897699"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Ye, M., et al.: DeepSolo: let transformer decoder with explicit points solo for text spotting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19348\u201319357 (2023)","DOI":"10.1109\/CVPR52729.2023.01854"},{"key":"7_CR38","unstructured":"Zeiler, M.D.: AdaDelta: an adaptive learning rate method. arXiv preprint arXiv:1212.5701 (2012)"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, X., Su, Y., Tripathi, S., Tu, Z.: Text spotting transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9519\u20139528 (2022)","DOI":"10.1109\/CVPR52688.2022.00930"},{"key":"7_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.patrec.2023.04.004","volume":"170","author":"M Zhao","year":"2023","unstructured":"Zhao, M., Feng, W., Yin, F., Liu, C.L.: Texts as points: scene text detection with point supervision. Pattern Recogn. Lett. 170, 1\u20138 (2023)","journal-title":"Pattern Recogn. Lett."},{"key":"7_CR41","doi-asserted-by":"crossref","unstructured":"Zheng, T., Chen, Z., Fang, S., Xie, H., Jiang, Y.G.: CDistnet: perceiving multi-domain character distance for robust text recognition. Int. J. Comput. Vision, 1\u201319 (2023)","DOI":"10.1007\/s11263-023-01880-0"},{"key":"7_CR42","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: 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"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70549-6_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T09:04:29Z","timestamp":1725786269000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70549-6_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705489","9783031705496"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70549-6_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"9 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Athens","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2024.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}