{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T21:41:06Z","timestamp":1761946866449,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":54,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819787012"},{"type":"electronic","value":"9789819787029"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-97-8702-9_34","type":"book-chapter","created":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T14:46:14Z","timestamp":1738939574000},"page":"505-519","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Arbitrary-Shape Text Spotting Based on\u00a0Global, Pixel and\u00a0Sequence Semantics"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2564-0998","authenticated-orcid":false,"given":"Chunhu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8766-0647","authenticated-orcid":false,"given":"Mayire","family":"Ibrayim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2321-308X","authenticated-orcid":false,"given":"Askar","family":"Hamdulla","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5232-0176","authenticated-orcid":false,"given":"Qilin","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,8]]},"reference":[{"key":"34_CR1","doi-asserted-by":"crossref","unstructured":"Wang, P., Zhang, C., et al.: Pgnet: real-time arbitrarily-shaped text spotting with point gathering network. In: Proceedings of the AAAI, vol. 35, no. 4, pp. 2782\u20132790 (2021)","DOI":"10.1609\/aaai.v35i4.16383"},{"key":"34_CR2","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhang, J., et al.: SPTS v2: single-point scene text spotting (2023)","DOI":"10.1109\/TPAMI.2023.3312285"},{"key":"34_CR3","doi-asserted-by":"publisher","unstructured":"Wang, W., et al.: PAN++: towards efficient and accurate end-to-end spotting of arbitrarily-shaped text. In: IEEE TPAMI, vol. 44, no. 9, pp. 5349\u20135367, 1 September 2022. https:\/\/doi.org\/10.1109\/TPAMI.2021.3077555","DOI":"10.1109\/TPAMI.2021.3077555"},{"key":"34_CR4","doi-asserted-by":"publisher","unstructured":"Xu, Y., Xu, W., Cheung, D., Tu, Z.: Line segment detection using transformers without edges. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, pp. 4255\u20134264 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00424","DOI":"10.1109\/CVPR46437.2021.00424"},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"Liu, Y., Shen, L.C., et al.: ABCNet v2: adaptive bezier-curve network for real-time end-to end text spotting. IEEE Trans. Pattern Anal. Mach. Intell. 44(11), 8048\u20138064 (2022)","DOI":"10.1109\/TPAMI.2021.3107437"},{"key":"34_CR6","volume-title":"CBAM: Convolutional Block Attention Module","author":"S Woo","year":"2018","unstructured":"Woo, S., Park, J., Lee, J.Y., et al.: CBAM: Convolutional Block Attention Module. Springer, Cham (2018)"},{"key":"34_CR7","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xie, H.Z.-J., et al.: Contournet: taking a further step toward accurate arbitrary-shaped scene text detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11 753\u201311 762 (2020)","DOI":"10.1109\/CVPR42600.2020.01177"},{"key":"34_CR8","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 (2022)","DOI":"10.1109\/CVPR52688.2022.00456"},{"key":"34_CR9","doi-asserted-by":"publisher","unstructured":"Zhang, S. -X., Zhu, X.L., et al.: Arbitrary shape text detection via segmentation with probability maps. In: IEEE TPAMI, vol. 45, no. 3, pp. 2736\u20132750, 1 March 2023. https:\/\/doi.org\/10.1109\/TPAMI.2022.3176122","DOI":"10.1109\/TPAMI.2022.3176122"},{"key":"34_CR10","unstructured":"Yang, L., Zhang, R., et al.: SimAM: a simple, parameter-free attention module for convolutional neural networks. In: Proceedings of the 38th International Conference on Machine Learning, in Proceedings of Machine Learning Research, vol. 139, pp. 11863\u201311874 (2021)"},{"key":"34_CR11","doi-asserted-by":"publisher","unstructured":"Dai, W., et al.: An end-to-end chinese text normalization model based on rule-guided flat-lattice transformer. In: ICASSP 2022, Singapore, pp. 7122\u20137126 (2022). https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9747316","DOI":"10.1109\/ICASSP43922.2022.9747316"},{"key":"34_CR12","doi-asserted-by":"publisher","unstructured":"Xing, L., Tian, Z., Huang, W., Scott, M.: Convolutional character networks. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South), pp. 9125\u20139135 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00922","DOI":"10.1109\/ICCV.2019.00922"},{"key":"34_CR13","doi-asserted-by":"crossref","unstructured":"Peng, D., Wang, X.Y., et al.: 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":"34_CR14","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Song, X., 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":"34_CR15","doi-asserted-by":"crossref","unstructured":"Nayef, N., et al.: ICDAR2017 robust reading challenge on multilingual scene text detection and script identification-RRC-MLT. In: Proceedings of International Conference on Document Analysis and Recognition, pp. 1454\u20131459 (2017)","DOI":"10.1109\/ICDAR.2017.237"},{"key":"34_CR16","doi-asserted-by":"crossref","unstructured":"Baek, Y., Lee, B., Han, D., et al.: Character region awareness for text detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9365\u20139374 (2019)","DOI":"10.1109\/CVPR.2019.00959"},{"key":"34_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"34_CR18","doi-asserted-by":"crossref","unstructured":"Liao, M., Zou, Z.Z., et al.: Real-time scene text detection with differentiable binarization and adaptive scale fusion. In: IEEE TPAMI (2022)","DOI":"10.1109\/TPAMI.2022.3155612"},{"key":"34_CR19","doi-asserted-by":"publisher","unstructured":"Liu, X., Liang, D.S., et al.: FOTS: fast oriented text spotting with a unified network. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, pp. 5676\u20135685 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00595","DOI":"10.1109\/CVPR.2018.00595"},{"key":"34_CR20","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., 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":"34_CR21","doi-asserted-by":"publisher","unstructured":"Huang, M., et al.: SwinTextSpotter: scene text spotting via better synergy between text detection and text recognition. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, pp. 4583\u20134593 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00455","DOI":"10.1109\/CVPR52688.2022.00455"},{"key":"34_CR22","first-page":"6200","volume":"31","author":"P Lu","year":"2022","unstructured":"Lu, P., Wang, H., Zhu, S., et al.: Boundary TextSpotter: toward arbitrary-shaped scene text spotting. IEEE TIP 31, 6200\u20136212 (2022)","journal-title":"IEEE TIP"},{"key":"34_CR23","doi-asserted-by":"crossref","unstructured":"Qin, S., Bissacco, A.M., et al.: Towards unconstrained end-to-end text spotting. In: Proceedings of IEEE International Conference on Computer Vision, pp. 4703\u20134713 (2019)","DOI":"10.1109\/ICCV.2019.00480"},{"key":"34_CR24","doi-asserted-by":"crossref","unstructured":"Zhang, S.-X., Zhu, X., et al.: Adaptive boundary proposal network for arbitrary shape text detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1305\u20131314, October 2021","DOI":"10.1109\/ICCV48922.2021.00134"},{"key":"34_CR25","unstructured":"Chen, Z., Wang, W., Xie, E., et al.: FAST: Searching for a faster arbitrarily-shaped text detector with minimalist kernel representation (2021)"},{"key":"34_CR26","unstructured":"Yuliang, L., Lianwen, J.Z., et al.: Detecting curve text in the wild: new dataset and new solution (2017) arXiv:1712.02170"},{"key":"34_CR27","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2015 competition on robust reading. In: Proceedings of International conference on Document Analysis Recognition, pp. 1156\u20131160 (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"34_CR28","doi-asserted-by":"crossref","unstructured":"Fang, S., Mao, Z., Xie, H., et al.: Abinet++: autonomous, bidirectional and iterative language modeling for scene text spotting. In: IEEE TPAMI (2022)","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"34_CR29","doi-asserted-by":"publisher","unstructured":"Liao, M., Pang, G., et al.: Mask TextSpotter v3: segmentation proposal network for robust scene text spotting. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds.) Computer Vision \u2013 ECCV 2020, LNCS, vol. 12356. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8-41","DOI":"10.1007\/978-3-030-58621-8-41"},{"key":"34_CR30","doi-asserted-by":"crossref","unstructured":"Ch\u2019ng, C.K., Chan, C.S.: Total-text: a comprehensive dataset for scene text detection and recognition. In: Proceedings of International Conference on Document Analysis Recognition, pp. 935\u2013942 (2017)","DOI":"10.1109\/ICDAR.2017.157"},{"key":"34_CR31","doi-asserted-by":"crossref","unstructured":"Yu, W., Liu, Y., Hua, W., et al.: Turning a CLIP model into a scene text detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6978\u20136988 (2023)","DOI":"10.1109\/CVPR52729.2023.00674"},{"issue":"11","key":"34_CR32","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2016","unstructured":"Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE TPAMI 39(11), 2298\u20132304 (2016)","journal-title":"IEEE TPAMI"},{"key":"34_CR33","unstructured":"Jaderberg, S.-N.M., et al. Spatial transformer networks. In: Advances in Neural Information Processing Systems, pp. 2017\u20132025 (2015)"},{"key":"34_CR34","doi-asserted-by":"crossref","unstructured":"Liao, M., Wan, Z., Yao, C., et al.: Real-time scene text detection with differentiable binarization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11474\u201311481 (2020)","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"34_CR35","doi-asserted-by":"crossref","unstructured":"Shi, B, Wang, X, et al.: Robust scene text recognition with automatic rectification. In: Proceedings of the CVPR, pp. 4168\u20134176 (2016)","DOI":"10.1109\/CVPR.2016.452"},{"key":"34_CR36","doi-asserted-by":"crossref","unstructured":"Li, H., Wang, P., et al.: Show, attend and read: a simple and strong baseline for irregular text recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, no. 01, pp. 8610\u20138617, July 2019","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"34_CR37","doi-asserted-by":"crossref","unstructured":"Liao, M., Zhang, J., et al.: Scene text recognition from two-dimensional perspective. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, no. 01, pp. 8714\u20138721, July 2019","DOI":"10.1609\/aaai.v33i01.33018714"},{"key":"34_CR38","doi-asserted-by":"crossref","unstructured":"Dai, P., Zhang, S., et al.: Progressive contour regression for arbitrary-shape scene text detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7393\u20137402, June 2021","DOI":"10.1109\/CVPR46437.2021.00731"},{"key":"34_CR39","doi-asserted-by":"publisher","unstructured":"Lu, P., Wang, H., S., et al.: Boundary TextSpotter: toward arbitrary-shaped scene text spotting. In: IEEE TIP, vol. 31, pp. 6200\u20136212 (2022). https:\/\/doi.org\/10.1109\/TIP.2022.3206615","DOI":"10.1109\/TIP.2022.3206615"},{"key":"34_CR40","unstructured":"Li, M., et al.: TrOCR: transformer-based optical character recognition with pre-trained models (2021)"},{"key":"34_CR41","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Chen, J., et al.: Fourier contour embedding for arbitrary-shaped text detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3123\u20133131, June 2021","DOI":"10.1109\/CVPR46437.2021.00314"},{"key":"34_CR42","unstructured":"Sheng, T., Chen, J., et al.: Centripetaltext: an efficient text instance representation for scene text detection. In: Advances in Neural Information Processing Systems, vol. 34 (2021)"},{"key":"34_CR43","unstructured":"Yao, C., et al.: Detecting texts of arbitrary orientations in natural images. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1083\u20131090 (2012)"},{"key":"34_CR44","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: All you need is boundary: toward arbitrary-shaped text spotting. In: AAAI, vol. 34, pp. 12160\u201312167 (2020)","DOI":"10.1609\/aaai.v34i07.6896"},{"key":"34_CR45","doi-asserted-by":"crossref","unstructured":"Long, S., Qin, S., Panteleev, D., et al.: Towards end-to-end unified scene text detection and layout analysis (2022)","DOI":"10.1109\/CVPR52688.2022.00112"},{"key":"34_CR46","doi-asserted-by":"crossref","unstructured":"Qiao, L., et al.: Mango: a mask at tention guided one-stage scene text spotter. In: AAAI, vol. 35, pp. 2467\u20132476 (2021)","DOI":"10.1609\/aaai.v35i3.16348"},{"key":"34_CR47","doi-asserted-by":"publisher","unstructured":"Tang., J., Few could be better than all: feature sampling and grouping for scene text detection (2022). https:\/\/doi.org\/10.48550\/arXiv.2203.15221","DOI":"10.48550\/arXiv.2203.15221"},{"key":"34_CR48","doi-asserted-by":"crossref","unstructured":"Peng, D., et al.: 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":"34_CR49","doi-asserted-by":"crossref","unstructured":"Qin, S., et al.: Towards unconstrained end-to-end text spotting. In: CVPR, pp. 4704\u20134714 (2019)","DOI":"10.1109\/ICCV.2019.00480"},{"issue":"10","key":"34_CR50","doi-asserted-by":"publisher","first-page":"7266","DOI":"10.1109\/TPAMI.2021.3095916","volume":"44","author":"P Wang","year":"2021","unstructured":"Wang, P., Li, H., Shen, C.: Towards end to-end text spotting in natural scenes. IEEE TPAMI 44(10), 7266\u20137281 (2021)","journal-title":"IEEE TPAMI"},{"key":"34_CR51","doi-asserted-by":"crossref","unstructured":"Lyu, P., etal.: Mask textspotter: an end-to-end trainable neural network for spotting text with arbitrary shapes. In: ECCV, pp. 67\u201383 (2018)","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"34_CR52","doi-asserted-by":"crossref","unstructured":"Qiao, L., et al.: Text perceptron: Towards end-to end arbitrary-shaped text spotting. In: AAAI, vol. 34, pp. 11899\u201311907 (2020)","DOI":"10.1609\/aaai.v34i07.6864"},{"key":"34_CR53","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Abcnet: real-time scene text spotting with adaptive bezier-curve network. In: CVPR, pp. 9809\u20139818 (2020)","DOI":"10.1109\/CVPR42600.2020.00983"},{"key":"34_CR54","doi-asserted-by":"crossref","unstructured":"Liao, M., et al.: Mask textspotter: an end-to-end trainable neural network for spotting text with arbitrary shapes. In: IEEE TPAMI, vol. 43, no. 2, pp. 532\u2013548 (2021)","DOI":"10.1109\/TPAMI.2019.2937086"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8702-9_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T14:46:41Z","timestamp":1738939601000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8702-9_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819787012","9789819787029"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8702-9_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"8 February 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ICPRAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition and Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Jeju Island","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","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":"18 June 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 June 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icprai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/brain.korea.ac.kr\/icprai2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}