{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:52:43Z","timestamp":1777654363472,"version":"3.51.4"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031416781","type":"print"},{"value":"9783031416798","type":"electronic"}],"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\/978-3-031-41679-8_28","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:02:59Z","timestamp":1692342179000},"page":"483-497","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["ICDAR 2023 Competition on\u00a0Hierarchical Text Detection and\u00a0Recognition"],"prefix":"10.1007","author":[{"given":"Shangbang","family":"Long","sequence":"first","affiliation":[]},{"given":"Siyang","family":"Qin","sequence":"additional","affiliation":[]},{"given":"Dmitry","family":"Panteleev","sequence":"additional","affiliation":[]},{"given":"Alessandro","family":"Bissacco","sequence":"additional","affiliation":[]},{"given":"Yasuhisa","family":"Fujii","sequence":"additional","affiliation":[]},{"given":"Michalis","family":"Raptis","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"key":"28_CR1","doi-asserted-by":"publisher","unstructured":"Bautista, D., Atienza, R.: Scene text recognition with permuted autoregressive sequence models. In: Computer Vision-ECCV,: 17th European Conference, Tel Aviv, Israel, 23\u201327 October 2022, Proceedings, Part XXVIII, p. 2022. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_11","DOI":"10.1007\/978-3-031-19815-1_11"},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Ye, M., et al.: DeepSolo: let transformer decoder with explicit points solo for text spotting. arXiv preprint arXiv:2211.10772 (2022)","DOI":"10.1109\/CVPR52729.2023.01854"},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer v2: scaling up capacity and resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"28_CR5","doi-asserted-by":"publisher","unstructured":"Xue, C.: Language matters: a weakly supervised vision-language pre-training approach for scene text detection and spotting. In: Computer Vision-ECCV, et al.: 17th European Conference, Tel Aviv, Israel, 23\u201327 October 2022, Proceedings, Part XXVIII, p. 2022. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_17","DOI":"10.1007\/978-3-031-19815-1_17"},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Liao, M., et al.: Real-time scene text detection with differentiable binarization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 07 (2020)","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"28_CR7","unstructured":"Xie, E., et al.: SegFormer: simple and efficient design for semantic segmentation with transformers. Adv. Neural Inf. Process. Syst. 34, 12077\u201312090 (2021)"},{"key":"28_CR8","unstructured":"Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, PMLR (2019)"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Berman, M., Amal, R.T., Matthew, B.B.: The lov\u00e1sz-softmax loss: a tractable surrogate for the optimization of the intersection-over-union measure in neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00464"},{"issue":"1","key":"28_CR10","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. Vis. 129(1), 161\u2013184 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"Lee, J., et al.: Page segmentation using a convolutional neural network with trainable co-occurrence features. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00167"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Yang, X., et al.: Learning to extract semantic structure from documents using multimodal fully convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.462"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Ronen, R., et al.: GLASS: global to local attention for scene-text spotting. arXiv preprint arXiv:2208.03364 (2022)","DOI":"10.1007\/978-3-031-19815-1_15"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Long, S., et al.: Textsnake: a flexible representation for detecting text of arbitrary shapes. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01216-8_2"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Qin, S., et al.: Towards unconstrained end-to-end text spotting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00480"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Kittenplon, Y., et al.: Towards weakly-supervised text spotting using a multi-task transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00456"},{"key":"28_CR17","doi-asserted-by":"publisher","unstructured":"Liu, S., et al.: Unified line and paragraph detection by graph convolutional networks. In: Uchida, S., Barney, E., Eglin, V. (eds.) Document Analysis Systems. DAS 2022. LNCS, vol. 13237, pp. 33\u201347. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-06555-2_3","DOI":"10.1007\/978-3-031-06555-2_3"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Wang, R., Yasuhisa, F., Ashok, C.P.: Post-ocr paragraph recognition by graph convolutional networks. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (2022)","DOI":"10.1109\/WACV51458.2022.00259"},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Long, S., et al.: Towards end-to-end unified scene text detection and layout analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00112"},{"key":"28_CR20","unstructured":"Li, C., et al.: StructuralLM: structural pre-training for form understanding. arXiv preprint arXiv:2105.11210 (2021)"},{"key":"28_CR21","unstructured":"Long, S., Cong, Y.: Unrealtext: synthesizing realistic scene text images from the unreal world. arXiv preprint arXiv:2003.10608 (2020)"},{"key":"28_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11432-019-2737-0","volume":"63","author":"M Liao","year":"2020","unstructured":"Liao, M., et al.: SynthText3D: synthesizing scene text images from 3D virtual worlds. Sci. China Inf. Sci. 63, 1\u201314 (2020)","journal-title":"Sci. China Inf. Sci."},{"key":"28_CR23","unstructured":"Jaderberg, M., et al.: Synthetic data and artificial neural networks for natural scene text recognition. arXiv preprint arXiv:1406.2227 (2014)"},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Gupta, A., Andrea, V., Andrew, Z.: Synthetic data for text localisation in natural images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"28_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/978-3-030-86337-1_8","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"M Yim","year":"2021","unstructured":"Yim, M., Kim, Y., Cho, H.-C., Park, S.: SynthTIGER: synthetic text image GEneratoR towards better text recognition models. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021, Part IV. LNCS, vol. 12824, pp. 109\u2013124. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86337-1_8"},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"Huang, Y., et al.: LayoutLMv3: pre-training for document AI with unified text and image masking. arXiv preprint arXiv:2204.08387 (2022)","DOI":"10.1145\/3503161.3548112"},{"issue":"7","key":"28_CR27","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova, A., et al.: The open images dataset v4. Int. J. Comput. Vis. 128(7), 1956\u20131981 (2020)","journal-title":"Int. J. Comput. Vis."},{"key":"28_CR28","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: TextOCR: towards large-scale end-to-end reasoning for arbitrary-shaped scene text. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00869"},{"key":"28_CR29","unstructured":"Krylov, I., Sergei, N., Vladislav, S.: Open images v5 text annotation and yet another mask text spotter. In: Asian Conference on Machine Learning, PMLR (2021)"},{"key":"28_CR30","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Panoptic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00963"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-41679-8_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T07:13:27Z","timestamp":1702970007000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41679-8_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031416781","9783031416798"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41679-8_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"19 August 2023","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":"San Jos\u00e9, CA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","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":"21 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-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":"316","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":"154","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":"49% - 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":"2.89","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":"1.50","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)"}},{"value":"Number and type of other papers accepted : IJDAR track papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}