{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:17:52Z","timestamp":1771949872568,"version":"3.50.1"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031417306","type":"print"},{"value":"9783031417313","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\/978-3-031-41731-3_1","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T06:02:26Z","timestamp":1692338546000},"page":"3-21","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Text Reading Order in\u00a0Uncontrolled Conditions by\u00a0Sparse Graph Segmentation"],"prefix":"10.1007","author":[{"given":"Renshen","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasuhisa","family":"Fujii","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessandro","family":"Bissacco","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"key":"1_CR1","unstructured":"Aiello, M., Smeulders, A.M.W.: Bidimensional relations for reading order detection. In: EPRINTS-BOOK-TITLE. University of Groningen, Johann Bernoulli Institute for Mathematics and Computer Science (2003)"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Antonacopoulos, A., Bridson, D., Papadopoulos, C., Pletschacher, S.: A realistic dataset for performance evaluation of document layout analysis. In: 10th International Conference on Document Analysis and Recognition, ICDAR 2009, Barcelona, Spain, 26\u201329 July 2009, pp. 296\u2013300. IEEE Computer Society (2009). https:\/\/doi.org\/10.1109\/ICDAR.2009.271","DOI":"10.1109\/ICDAR.2009.271"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Appalaraju, S., Jasani, B., Kota, B.U., Xie, Y., Manmatha, R.: Docformer: end-to-end transformer for document understanding. In: 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, 10\u201317 October 2021, pp. 973\u2013983. IEEE (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00103","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Bissacco, A., Cummins, M., Netzer, Y., Neven, H.: Photoocr: reading text in uncontrolled conditions. In: IEEE International Conference on Computer Vision, ICCV 2013, Sydney, Australia, 1\u20138 December 2013, pp. 785\u2013792. IEEE Computer Society (2013). https:\/\/doi.org\/10.1109\/ICCV.2013.102","DOI":"10.1109\/ICCV.2013.102"},{"key":"1_CR5","unstructured":"Breuel, T.M.: High performance document layout analysis. In: Symposium on Document Image Understanding Technology, Greenbelt, MD, USA (2003)"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Ceci, M., Berardi, M., Porcelli, G., Malerba, D.: A data mining approach to reading order detection. In: 9th International Conference on Document Analysis and Recognition (ICDAR 2007), 23\u201326 September, Curitiba, Paran\u00e1, Brazil, pp. 924\u2013928. IEEE Computer Society (2007). https:\/\/doi.org\/10.1109\/ICDAR.2007.4377050","DOI":"10.1109\/ICDAR.2007.4377050"},{"key":"1_CR7","doi-asserted-by":"publisher","unstructured":"Chen, X., et al.: Pali: a jointly-scaled multilingual language-image model (2022). https:\/\/doi.org\/10.48550\/ARXIV.2209.06794. https:\/\/arxiv.org\/abs\/2209.06794","DOI":"10.48550\/ARXIV.2209.06794"},{"key":"1_CR8","unstructured":"Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: Lee, D.D., Sugiyama, M., von Luxburg, U., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 5\u201310 December 2016, Barcelona, Spain, pp. 379\u2013387 (2016)"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Ferilli, S., Grieco, D., Redavid, D., Esposito, F.: Abstract argumentation for reading order detection. In: Simske, S.J., R\u00f6nnau, S. (eds.) ACM Symposium on Document Engineering 2014, DocEng 2014, Fort Collins, CO, USA, 16\u201319 September 2014, pp. 45\u201348. ACM (2014). https:\/\/doi.org\/10.1145\/2644866.2644883","DOI":"10.1145\/2644866.2644883"},{"key":"1_CR10","doi-asserted-by":"publisher","unstructured":"Ferludin, O., et al.: TF-GNN: graph neural networks in tensorflow (2022). https:\/\/doi.org\/10.48550\/ARXIV.2207.03522. https:\/\/arxiv.org\/abs\/2207.03522","DOI":"10.48550\/ARXIV.2207.03522"},{"key":"1_CR11","unstructured":"Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. In: Proceedings of the 34th International Conference on Machine Learning, ICML 2017, vol. 70, pp. 1263\u20131272. JMLR.org (2017)"},{"key":"1_CR12","unstructured":"Gu, J., et al.: Unidoc: unified pretraining framework for document understanding. In: Ranzato, M., Beygelzimer, A., Dauphin, Y.N., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, 6\u201314 December 2021, Virtual, pp. 39\u201350 (2021)"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Gu, Z., et al.: Xylayoutlm: towards layout-aware multimodal networks for visually-rich document understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4583\u20134592 (2022)","DOI":"10.1109\/CVPR52688.2022.00454"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Howard, A., et al.: Searching for mobilenetv3. In: 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), 27 October\u20132 November 2019, pp. 1314\u20131324. IEEE (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00140","DOI":"10.1109\/ICCV.2019.00140"},{"key":"1_CR15","doi-asserted-by":"publisher","unstructured":"Huang, Y., Lv, T., Cui, L., Lu, Y., Wei, F.: Layoutlmv3: pre-training for document AI with unified text and image masking. CoRR abs\/2204.08387 (2022). https:\/\/doi.org\/10.48550\/ARXIV.2204.08387. https:\/\/arxiv.org\/abs\/2204.08387","DOI":"10.48550\/ARXIV.2204.08387"},{"key":"1_CR16","doi-asserted-by":"publisher","unstructured":"Kirillov, A., He, K., Girshick, R.B., Rother, C., Doll\u00e1r, P.: Panoptic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, 16\u201320 June 2019, pp. 9404\u20139413. Computer Vision Foundation\/IEEE (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00963","DOI":"10.1109\/CVPR.2019.00963"},{"key":"1_CR17","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1016\/B978-0-444-87806-9.50013-X","volume":"2","author":"DG Kirkpatrick","year":"1985","unstructured":"Kirkpatrick, D.G., Radke, J.D.: A framework for computational morphology. Mach. Intell. Pattern Recognit. 2, 217\u2013248 (1985). https:\/\/doi.org\/10.1016\/B978-0-444-87806-9.50013-X","journal-title":"Mach. Intell. Pattern Recognit."},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Lee, C., et al.: Formnet: structural encoding beyond sequential modeling in form document information extraction. In: Muresan, S., Nakov, P., Villavicencio, A. (eds.) Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022, Dublin, Ireland, 22\u201327 May 2022, pp. 3735\u20133754. Association for Computational Linguistics (2022). https:\/\/aclanthology.org\/2022.acl-long.260","DOI":"10.18653\/v1\/2022.acl-long.260"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Lee, C., et al.: ROPE: reading order equivariant positional encoding for graph-based document information extraction. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL\/IJCNLP 2021, (Volume 2: Short Papers), Virtual Event, 1\u20136 August 2021, pp. 314\u2013321. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/v1\/2021.acl-short.41","DOI":"10.18653\/v1\/2021.acl-short.41"},{"key":"1_CR20","unstructured":"Levenshtein, V.I.: Binary codes capable of correcting deletions, insertions and reversals. Soviet Physics Doklady 10, 707 (1966)"},{"key":"1_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1007\/978-3-030-58595-2_6","volume-title":"Computer Vision \u2013 ECCV 2020","author":"L Li","year":"2020","unstructured":"Li, L., Gao, F., Bu, J., Wang, Y., Yu, Z., Zheng, Q.: An end-to-end OCR text re-organization sequence learning for rich-text detail image comprehension. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12370, pp. 85\u2013100. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58595-2_6"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Li, P., et al.: Selfdoc: self-supervised document representation learning. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, virtual, 19\u201325 June 2021, pp. 5652\u20135660. Computer Vision Foundation\/IEEE (2021)","DOI":"10.1109\/CVPR46437.2021.00560"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Structext: structured text understanding with multi-modal transformers. In: Shen, H.T., et al. (eds.) MM 2021: ACM Multimedia Conference, Virtual Event, China, 20\u201324 October 2021, pp. 1912\u20131920. ACM (2021). https:\/\/doi.org\/10.1145\/3474085.3475345","DOI":"10.1145\/3474085.3475345"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, X., Liu, B., Jiang, D., Liu, Y., Ren, B.: Neural collaborative graph machines for table structure recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4533\u20134542 (2022)","DOI":"10.1109\/CVPR52688.2022.00449"},{"key":"1_CR25","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/978-3-031-06555-2_3","volume-title":"DAS 2022","author":"S Liu","year":"2022","unstructured":"Liu, S., Wang, R., Raptis, M., Fujii, Y.: Unified line and paragraph detection by graph convolutional networks. In: Uchida, S., Barney, E., Eglin, V. (eds.) DAS 2022. LNCS, vol. 13237, pp. 33\u201347. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-06555-2_3"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, 7\u201312 June 2015, pp. 3431\u20133440. IEEE Computer Society (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298965","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Meunier, J.: Optimized XY-cut for determining a page reading order. In: Eighth International Conference on Document Analysis and Recognition (ICDAR 2005), 29 August\u20131 September 2005, Seoul, Korea, pp. 347\u2013351. IEEE Computer Society (2005). https:\/\/doi.org\/10.1109\/ICDAR.2005.182","DOI":"10.1109\/ICDAR.2005.182"},{"key":"1_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"732","DOI":"10.1007\/978-3-030-86331-9_47","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"R Powalski","year":"2021","unstructured":"Powalski, R., Borchmann, \u0141, Jurkiewicz, D., Dwojak, T., Pietruszka, M., Pa\u0142ka, G.: Going full-TILT boogie on document understanding with text-image-layout transformer. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12822, pp. 732\u2013747. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86331-9_47"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Quir\u00f3s, L., Vidal, E.: Reading order detection on handwritten documents. Neural Comput. Appl. 34(12), 9593\u20139611 (2022). https:\/\/doi.org\/10.1007\/s00521-022-06948-5","DOI":"10.1007\/s00521-022-06948-5"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Wang, J., Jin, L., Ding, K.: Lilt: A simple yet effective language-independent layout transformer for structured document understanding. In: Muresan, S., Nakov, P., Villavicencio, A. (eds.) Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022, Dublin, Ireland, 22\u201327 May 2022, pp. 7747\u20137757. Association for Computational Linguistics (2022). https:\/\/aclanthology.org\/2022.acl-long.534","DOI":"10.18653\/v1\/2022.acl-long.534"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Wang, R., Fujii, Y., Popat, A.C.: Post-OCR paragraph recognition by graph convolutional networks. In: IEEE\/CVF Winter Conference on Applications of Computer Vision, WACV 2022, Waikoloa, HI, USA, 3\u20138 January 2022, pp. 2533\u20132542. IEEE (2022). https:\/\/doi.org\/10.1109\/WACV51458.2022.00259","DOI":"10.1109\/WACV51458.2022.00259"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Wang, Z., Xu, Y., Cui, L., Shang, J., Wei, F.: Layoutreader: pre-training of text and layout for reading order detection. In: Moens, M., Huang, X., Specia, L., Yih, S.W. (eds.) Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event\/Punta Cana, Dominican Republic, 7\u201311 November 2021, pp. 4735\u20134744. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.389","DOI":"10.18653\/v1\/2021.emnlp-main.389"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: Layoutlmv2: multi-modal pre-training for visually-rich document understanding. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL\/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, 1\u20136 August 2021, pp. 2579\u20132591. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.201","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Xu, Y., Li, M., Cui, L., Huang, S., Wei, F., Zhou, M.: Layoutlm: pre-training of text and layout for document image understanding. In: Gupta, R., Liu, Y., Tang, J., Prakash, B.A. (eds.) KDD 2020: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Virtual Event, CA, USA, 23\u201327 August 2020, pp. 1192\u20131200. ACM (2020). https:\/\/doi.org\/10.1145\/3394486.3403172","DOI":"10.1145\/3394486.3403172"},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"Zhong, X., Tang, J., Jimeno-Yepes, A.: Publaynet: largest dataset ever for document layout analysis. In: 2019 International Conference on Document Analysis and Recognition, ICDAR 2019, Sydney, Australia, 20\u201325 September 2019, pp. 1015\u20131022. IEEE (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00166","DOI":"10.1109\/ICDAR.2019.00166"}],"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\/978-3-031-41731-3_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T06:02:48Z","timestamp":1692338568000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41731-3_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031417306","9783031417313"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41731-3_1","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)"}}]}}