{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T18:39:59Z","timestamp":1742927999668,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819785100"},{"type":"electronic","value":"9789819785117"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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\/978-981-97-8511-7_2","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T05:02:28Z","timestamp":1730523748000},"page":"16-29","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Real-Time Text Detection with Multi-level Feature Fusion and Pixel Clustering"],"prefix":"10.1007","author":[{"given":"Lu","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhufeng","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingyu","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zizhu","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"2_CR1","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/s11263-020-01369-0","volume":"129","author":"S Long","year":"2021","unstructured":"Long, S., He, X., Yao, C.: Scene text detection and recognition: the deep learning era. Int. J. Comput. Vision 129, 161\u2013184 (2021)","journal-title":"Int. J. Comput. Vision"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: PAN++: towards efficient and accurate end-to-end spotting of arbitrarily-shaped text. IEEE Trans. Pattern Anal. Mach. Intell. 44(9), 5349\u20135367 (2021)","DOI":"10.1109\/TPAMI.2021.3077555"},{"key":"2_CR3","doi-asserted-by":"publisher","first-page":"6983","DOI":"10.1109\/TMM.2022.3216729","volume":"25","author":"Y Qu","year":"2022","unstructured":"Qu, Y., Xie, H., Fang, S., Wang, Y., Zhang, Y.: ADNet: rethinking the shrunk polygon-based approach in scene text detection. IEEE Trans. Multimed. 25, 6983\u20136996 (2022)","journal-title":"IEEE Trans. Multimed."},{"issue":"3","key":"2_CR4","first-page":"2736","volume":"45","author":"SX Zhang","year":"2022","unstructured":"Zhang, S.X., Zhu, X., Chen, L., Hou, J.B., Yin, X.C.: Arbitrary shape text detection via segmentation with probability maps. IEEE Trans. Pattern Anal. Mach. Intell. 45(3), 2736\u20132750 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"11","key":"2_CR5","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.: Textfield: learning a deep direction field for irregular scene text detection. IEEE Trans. Image Process. 28(11), 5566\u20135579 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"2_CR6","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."},{"issue":"8","key":"2_CR7","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.: Textboxes++: a single-shot oriented scene text detector. IEEE Trans. Image Process. 27(8), 3676\u20133690 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Su, Y., et al.: Textdct: arbitrary-shaped text detection via discrete cosine transform mask. IEEE Trans. Multimed. (2022)","DOI":"10.1109\/TMM.2022.3186431"},{"issue":"1","key":"2_CR9","doi-asserted-by":"publisher","first-page":"919","DOI":"10.1109\/TPAMI.2022.3155612","volume":"45","author":"M Liao","year":"2022","unstructured":"Liao, M., Zou, Z., Wan, Z., Yao, C., Bai, X.: Real-time scene text detection with differentiable binarization and adaptive scale fusion. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 919\u2013931 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Zhang, S.X., Yang, C., Zhu, X., Yin, X.C.: Arbitrary shape text detection via boundary transformer. IEEE Trans. Multimed. (2023)","DOI":"10.1109\/TMM.2023.3286657"},{"key":"2_CR11","unstructured":"Chen, Z., et al.: Fast: faster arbitrarily-shaped text detector with minimalist kernel representation (2021). arXiv:2111.02394"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Wang, F., Xu, X., Chen, Y., Li, X.: Fuzzy semantics for arbitrary shaped scene text detection. IEEE Trans. Image Process. 32, 1\u201312 (2023)","DOI":"10.1109\/TIP.2022.3201467"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Zhang, S.X., Zhu, X., Hou, J.B., Yang, C., Yin, X.C.: Kernel proposal network for arbitrary shape text detection. IEEE Trans. Neural Netw. Learn. Syst. (2022)","DOI":"10.1109\/TNNLS.2022.3152596"},{"issue":"9","key":"2_CR14","doi-asserted-by":"publisher","first-page":"6073","DOI":"10.1109\/TCSVT.2022.3156390","volume":"32","author":"T Guan","year":"2022","unstructured":"Guan, T., Gu, C., Lu, C.: Industrial scene text detection with refined feature-attentive network. IEEE Trans. Circuits Syst. Video Technol. 32(9), 6073\u20136085 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2_CR15","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 (CVPR), pp. 9334\u20139345 (2019)","DOI":"10.1109\/CVPR.2019.00956"},{"key":"2_CR16","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, pp. 11474\u201311481 (2020)","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"2_CR17","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 (ICCV), pp. 8440\u20138449 (2019)","DOI":"10.1109\/ICCV.2019.00853"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Ye, J., Chen, Z., Liu, J., Du, B.: Textfusenet: scene text detection with richer fused features. In: Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), pp. 516\u2013522 (2020)","DOI":"10.24963\/ijcai.2020\/72"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Ch\u2019ng, C.K., Chan, C.S.: Total-text: a comprehensive dataset for scene text detection and recognition. In: International Conference on Document Analysis and Recognition (ICDAR), pp. 935\u2013942. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.157"},{"key":"2_CR21","unstructured":"Yao, C., Bai, X., Liu, W., Ma, Y., Tu, Z.: Detecting texts of arbitrary orientations in natural images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1083\u20131090 (2012)"},{"key":"2_CR22","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: Proceedings of the AAAI Conference on Artificial Intelligence, 31(1) (2017)","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Zhao Y., Ma, J., Qi Z.: VTLayout: a multi-modal approach for video text layout. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 2775\u20132784 (2023)","DOI":"10.1145\/3581783.3611870"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Wang, F., Chen, Y., Wu, F., Li, X.: Textray: contour-based geometric modeling for arbitrary-shaped scene text detection. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 111\u2013119 (2020)","DOI":"10.1145\/3394171.3413819"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Long, S., Ruan, J., Zhang, W., He, X., Wu, W., Yao, C.: Textsnake: a flexible representation for detecting text of arbitrary shapes. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 20\u201336 (2018)","DOI":"10.1007\/978-3-030-01216-8_2"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Tian, Z., et al.: Learning shape-aware embedding for scene text detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4234\u20134243 (2019)","DOI":"10.1109\/CVPR.2019.00436"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2315\u20132324 (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Su, Y., et al.: LRANet: towards accurate and efficient scene text detection with low-rank approximation network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 5, pp. 4979\u20134987 (2024)","DOI":"10.1609\/aaai.v38i5.28302"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, S.X., Zhu, X., Yang, C., Wang, H., Yin, X.C.: Adaptive boundary proposal network for arbitrary shape text detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1305\u20131314 (2021)","DOI":"10.1109\/ICCV48922.2021.00134"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8511-7_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T05:02:42Z","timestamp":1730523762000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8511-7_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9789819785100","9789819785117"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8511-7_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}