{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T22:28:06Z","timestamp":1743114486173,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031476334"},{"type":"electronic","value":"9783031476341"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-47634-1_14","type":"book-chapter","created":{"date-parts":[[2023,11,4]],"date-time":"2023-11-04T20:01:39Z","timestamp":1699128099000},"page":"179-193","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Scene Text Detection with\u00a0Box Supervision and\u00a0Level Set Evolution"],"prefix":"10.1007","author":[{"given":"Mengbiao","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng-Lin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,5]]},"reference":[{"issue":"2","key":"14_CR1","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1109\/83.902291","volume":"10","author":"TF Chan","year":"2001","unstructured":"Chan, T.F., Vese, L.A.: Active contours without edges. IEEE Trans. Image Process. 10(2), 266\u2013277 (2001)","journal-title":"IEEE Trans. Image Process."},{"key":"14_CR2","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 the International Conference on Document Analysis and Recognition, vol. 1, pp. 935\u2013942 (2017)","DOI":"10.1109\/ICDAR.2017.157"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Chng, C.K., et al.: ICDAR2019 robust reading challenge on arbitrary-shaped text-RRC-art. In: Proceedings of the International Conference on Document Analysis and Recognition, pp. 1571\u20131576 (2019)","DOI":"10.1109\/ICDAR.2019.00252"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Dai, P., Zhang, S., Zhang, H., Cao, X.: Progressive contour regression for arbitrary-shape scene text detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7393\u20137402 (2021)","DOI":"10.1109\/CVPR46437.2021.00731"},{"key":"14_CR5","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":"14_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"14_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":"14_CR8","unstructured":"Huang, L., Yang, Y., Deng, Y., Yu, Y.: DenseBox: unifying landmark localization with end to end object detection. arXiv preprint arXiv:1509.04874 (2015)"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR2015 competition on robust reading. In: Proceedings of the International Conference on Document Analysis and Recognition, pp. 1156\u20131160 (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"14_CR10","doi-asserted-by":"publisher","unstructured":"Li, W., Liu, W., Zhu, J., Cui, M., Hua, X.S., Zhang, L.: Box-supervised instance segmentation with level set evolution. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision. ECCV 2022. LNCS, vol. 13689, pp. 1\u201318. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19818-2_1","DOI":"10.1007\/978-3-031-19818-2_1"},{"key":"14_CR11","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, vol. 31 (2017)","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"14_CR13","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., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: 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":"14_CR14","unstructured":"Liu, Y., Jin, L., Zhang, S., Zhang, S.: Detecting curve text in the wild: new dataset and new solution. arXiv preprint arXiv:1712.02170 (2017)"},{"key":"14_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/978-3-030-01216-8_2","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Long","year":"2018","unstructured":"Long, S., Ruan, J., Zhang, W., He, X., Wu, W., Yao, C.: TextSnake: a flexible representation for detecting text of arbitrary shapes. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 19\u201335. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_2"},{"key":"14_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/978-3-030-01264-9_5","volume-title":"Computer Vision \u2013 ECCV 2018","author":"P Lyu","year":"2018","unstructured":"Lyu, P., Liao, M., Yao, C., Wu, W., Bai, X.: Mask TextSpotter: an end-to-end trainable neural network for spotting text with arbitrary shapes. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 71\u201388. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_5"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., Ahmadi, S.A.: V-Net: fully convolutional neural networks for volumetric medical image segmentation. In: Proceedings of the International Conference on 3D Vision, pp. 565\u2013571 (2016)","DOI":"10.1109\/3DV.2016.79"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Mumford, D.B., Shah, J.: Optimal approximations by piecewise smooth functions and associated variational problems. Communications on Pure and Applied Mathematics (1989)","DOI":"10.1002\/cpa.3160420503"},{"issue":"1","key":"14_CR19","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/0021-9991(88)90002-2","volume":"79","author":"S Osher","year":"1988","unstructured":"Osher, S., Sethian, J.A.: Fronts propagating with curvature-dependent speed: algorithms based on Hamilton-Jacobi formulations. J. Comput. Phys. 79(1), 12\u201349 (1988)","journal-title":"J. Comput. Phys."},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Qin, X., Zhou, Y., Yang, D., Wang, W.: Curved text detection in natural scene images with semi-and weakly-supervised learning. In: Proceedings of the International Conference on Document Analysis and Recognition, pp. 559\u2013564 (2019)","DOI":"10.1109\/ICDAR.2019.00095"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Sun, Y., Liu, J., Liu, W., Han, J., Ding, E., Liu, J.: Chinese street view text: large-scale Chinese text reading with partially supervised learning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9086\u20139095 (2019)","DOI":"10.1109\/ICCV.2019.00918"},{"key":"14_CR23","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":"14_CR24","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. LNCS, vol. 9912, pp. 56\u201372. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_4"},{"key":"14_CR25","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 ACM International Conference on Multimedia, pp. 111\u2013119 (2020)","DOI":"10.1145\/3394171.3413819"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Wang, W., E., Li, X., Hou, W., Lu, T., Yu, G., Shao, S.: Shape robust text detection with progressive scale expansion network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9336\u20139345 (2019)","DOI":"10.1109\/CVPR.2019.00956"},{"issue":"9","key":"14_CR27","first-page":"5349","volume":"44","author":"W Wang","year":"2021","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)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xie, H., Zha, Z.J., Xing, M., Fu, Z., Zhang, Y.: 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 (2020)","DOI":"10.1109\/CVPR42600.2020.01177"},{"key":"14_CR29","unstructured":"Wu, W., et al.: SelfText Beyond Polygon: Unconstrained text detection with box supervision and dynamic self-training. arXiv preprint arXiv:2011.13307 (2020)"},{"key":"14_CR30","first-page":"1","volume":"2020","author":"W Wu","year":"2020","unstructured":"Wu, W., Xing, J., Yang, C., Wang, Y., Zhou, H.: Texts as lines: text detection with weak supervision. Math. Probl. Eng. 2020, 1\u201312 (2020)","journal-title":"Math. Probl. Eng."},{"key":"14_CR31","doi-asserted-by":"publisher","unstructured":"Xue, C., Zhang, W., Hao, Y., Lu, S., Torr, P.H., Bai, S.: Language Matters: A weakly supervised vision-language pre-training approach for scene text detection and spotting. In: In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision. ECCV 2022. LNCS, vol. 13688, pp. 284\u2013302 . Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_17","DOI":"10.1007\/978-3-031-19815-1_17"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Yu, F., Wang, D., Shelhamer, E., Darrell, T.: Deep layer aggregation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2403\u20132412 (2018)","DOI":"10.1109\/CVPR.2018.00255"},{"key":"14_CR33","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 International Conference on Computer Vision, pp. 1305\u20131314 (2021)","DOI":"10.1109\/ICCV48922.2021.00134"},{"key":"14_CR34","doi-asserted-by":"publisher","first-page":"5513","DOI":"10.1109\/TIP.2022.3197987","volume":"31","author":"M Zhao","year":"2022","unstructured":"Zhao, M., Feng, W., Yin, F., Zhang, X.Y., Liu, C.L.: Mixed-supervised scene text detection with expectation-maximization algorithm. IEEE Trans. Image Process. 31, 5513\u20135528 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"14_CR35","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)"},{"key":"14_CR36","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","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-47634-1_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T11:27:54Z","timestamp":1730460474000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-47634-1_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031476334","9783031476341"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-47634-1_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"5 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kitakyushu","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"acpr2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ericlab.org\/acpr2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"164","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"93","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"57% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}