{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T04:56:16Z","timestamp":1775710576960,"version":"3.50.1"},"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_2","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:02:59Z","timestamp":1692342179000},"page":"20-36","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["An End-to-End Local Attention Based Model for Table Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0856-3196","authenticated-orcid":false,"given":"Nam Tuan","family":"Ly","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9061-7949","authenticated-orcid":false,"given":"Atsuhiro","family":"Takasu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"key":"2_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1007\/978-3-030-86337-1_40","volume-title":"Document Analysis and Recognition - ICDAR 2021","author":"A Jimeno Yepes","year":"2021","unstructured":"Jimeno Yepes, A., Zhong, P., Burdick, D.: ICDAR 2021 competition on scientific literature parsing. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) Document Analysis and Recognition - ICDAR 2021. Lecture Notes in Computer Science, vol. 12824, pp. 605\u2013617. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86337-1_40"},{"key":"2_CR2","doi-asserted-by":"publisher","unstructured":"Zhong, X., ShafieiBavani, E., Jimeno Yepes, A.: Image-based table recognition: data, model, and evaluation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds.) Computer Vision \u2013 ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol. 12366, pp. 564\u2013580. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_34\/TABLES\/3","DOI":"10.1007\/978-3-030-58589-1_34\/TABLES\/3"},{"key":"2_CR3","doi-asserted-by":"publisher","unstructured":"Li, M., Cui, L., Huang, S., Wei, F., Zhou, M., Li, Z.: TableBank: a benchmark dataset for table detection and recognition (2019). https:\/\/doi.org\/10.48550\/arxiv.1903.01949","DOI":"10.48550\/arxiv.1903.01949"},{"key":"2_CR4","doi-asserted-by":"publisher","unstructured":"Deng, Y., Rosenberg, D., Mann, G.: Challenges in end-to-end neural scientific table recognition. In: Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, pp. 894\u2013901 (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00148","DOI":"10.1109\/ICDAR.2019.00148"},{"key":"2_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"754","DOI":"10.1007\/978-3-030-86337-1_50","volume-title":"Document Analysis and Recognition - ICDAR 2021","author":"P Kayal","year":"2021","unstructured":"Kayal, P., Anand, M., Desai, H., Singh, M.: ICDAR 2021 competition on scientific table image recognition to LaTeX. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) Document Analysis and Recognition - ICDAR 2021. Lecture Notes in Computer Science, vol. 12824, pp. 754\u2013766. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86337-1_50"},{"key":"2_CR6","doi-asserted-by":"publisher","unstructured":"Itonori, K.: Table structure recognition based on textblock arrangement and ruled line position. In: Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR \u201993), pp. 765\u2013768 (1993). https:\/\/doi.org\/10.1109\/ICDAR.1993.395625","DOI":"10.1109\/ICDAR.1993.395625"},{"key":"2_CR7","doi-asserted-by":"publisher","unstructured":"Kieninger, T.G.: Table structure recognition based on robust block segmentation, vol. 3305, pp. 22\u201332 (1998). https:\/\/doi.org\/10.1117\/12.304642","DOI":"10.1117\/12.304642"},{"key":"2_CR8","doi-asserted-by":"publisher","first-page":"1479","DOI":"10.1016\/J.PATCOG.2004.01.012","volume":"37","author":"Y Wang","year":"2004","unstructured":"Wang, Y., Phillips, I.T., Haralick, R.M.: Table structure understanding and its performance evaluation. Pattern Recognit. 37, 1479\u20131497 (2004). https:\/\/doi.org\/10.1016\/J.PATCOG.2004.01.012","journal-title":"Pattern Recognit."},{"key":"2_CR9","doi-asserted-by":"publisher","unstructured":"Prasad, D., Gadpal, A., Kapadni, K., Visave, M., Sultanpure, K.: CascadeTabNet: an approach for end to end table detection and structure recognition from image-based documents. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, June 2020, pp. 2439\u20132447 (2020). https:\/\/doi.org\/10.48550\/arxiv.2004.12629","DOI":"10.48550\/arxiv.2004.12629"},{"key":"2_CR10","doi-asserted-by":"publisher","unstructured":"Raja, S., Mondal, A., Jawahar, C.V.: Table structure recognition using top-down and bottom-Up Cues. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds.) Computer Vision \u2013 ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol. 12373, pp. 70\u201386. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58604-1_5\/FIGURES\/8","DOI":"10.1007\/978-3-030-58604-1_5\/FIGURES\/8"},{"key":"2_CR11","doi-asserted-by":"publisher","unstructured":"Schreiber, S., Agne, S., Wolf, I., Dengel, A., Ahmed, S.: DeepDeSRT: deep learning for detection and structure recognition of tables in document images. In: Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, vol. 1, pp. 1162\u20131167 (2017). https:\/\/doi.org\/10.1109\/ICDAR.2017.192","DOI":"10.1109\/ICDAR.2017.192"},{"key":"2_CR12","doi-asserted-by":"publisher","unstructured":"Qiao, L., et al.: LGPMA: complicated table structure recognition with local and global pyramid mask alignment. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) Document Analysis and Recognition \u2013 ICDAR 2021. ICDAR 2021. Lecture Notes in Computer Science(), vol. 12821, pp. 99\u2013114. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_7\/TABLES\/4","DOI":"10.1007\/978-3-030-86549-8_7\/TABLES\/4"},{"key":"2_CR13","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems. Neural information processing systems foundation, pp. 5999\u20136009 (2017)"},{"key":"2_CR14","doi-asserted-by":"publisher","unstructured":"Nassar, A., Livathinos, N., Lysak, M., Staar, P.: TableFormer: table structure understanding with transformers (2022). https:\/\/doi.org\/10.48550\/arxiv.2203.01017","DOI":"10.48550\/arxiv.2203.01017"},{"key":"2_CR15","doi-asserted-by":"publisher","unstructured":"Ye, J., et al.: PingAn-VCGroup\u2019s solution for ICDAR 2021 competition on scientific literature parsing task B: table recognition to HTML (2021). https:\/\/doi.org\/10.48550\/arxiv.2105.01848","DOI":"10.48550\/arxiv.2105.01848"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Ly, N.T., Takasu, A., Nguyen, P., Takeda, H.: Rethinking image-based table recognition using weakly supervised methods. In: In Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods (ICPRAM 2023), Lisbon, Portugal (2023)","DOI":"10.5220\/0011682600003411"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Ly, N.T., Takasu, A.: An end-to-end multi-task learning model for image-based table recognition. In: In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) (2023)","DOI":"10.5220\/0011685000003417"},{"key":"2_CR18","unstructured":"Beltagy, I., Peters, M.E., Cohan, A.: Longformer: the long-document transformer. arXiv (2020)"},{"key":"2_CR19","doi-asserted-by":"publisher","unstructured":"Kovaleva, O., Romanov, A., Rogers, A., Rumshisky, A.: Revealing the dark secrets of BERT. In: EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference, pp. 4365\u20134374 (2019). https:\/\/doi.org\/10.18653\/V1\/D19-1445","DOI":"10.18653\/V1\/D19-1445"},{"key":"2_CR20","doi-asserted-by":"publisher","unstructured":"Sperber, M., Niehues, J., Neubig, G., St\u00fcker, S., Waibel, A.: Self-attentional acoustic models. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, September 2018, pp. 3723\u20133727 (2018). https:\/\/doi.org\/10.21437\/INTERSPEECH.2018-1910","DOI":"10.21437\/INTERSPEECH.2018-1910"},{"key":"2_CR21","doi-asserted-by":"publisher","unstructured":"Shaw, P., Uszkoreit, J., Vaswani, A.: Self-Attention with relative position representations. In: NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference, vol. 2, pp. 464\u2013468 (2018). https:\/\/doi.org\/10.18653\/V1\/N18-2074","DOI":"10.18653\/V1\/N18-2074"},{"key":"2_CR22","doi-asserted-by":"publisher","first-page":"107980","DOI":"10.1016\/J.PATCOG.2021.107980","volume":"117","author":"N Lu","year":"2021","unstructured":"Lu, N., et al.: MASTER: multi-aspect non-local network for scene text recognition. Pattern Recognit. 117, 107980 (2021). https:\/\/doi.org\/10.1016\/J.PATCOG.2021.107980","journal-title":"Pattern Recognit."},{"key":"2_CR23","doi-asserted-by":"publisher","unstructured":"Ly, N.T., Nguyen, H.T., Nakagawa, M.: 2D self-attention convolutional recurrent network for offline handwritten text recognition. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) Document Analysis and Recognition \u2013 ICDAR 2021. ICDAR 2021. Lecture Notes in Computer Science(), vol. 12821, pp. 191\u2013204. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_13\/COVER","DOI":"10.1007\/978-3-030-86549-8_13\/COVER"},{"key":"2_CR24","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.48550\/arxiv.1506.01497","volume":"39","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1137\u20131149 (2015). https:\/\/doi.org\/10.48550\/arxiv.1506.01497","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR25","doi-asserted-by":"publisher","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 07\u201312 June 2015, pp. 3431\u20133440 (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298965","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"2_CR26","doi-asserted-by":"publisher","first-page":"108565","DOI":"10.1016\/J.PATCOG.2022.108565","volume":"126","author":"Z Zhang","year":"2022","unstructured":"Zhang, Z., Zhang, J., Du, J., Wang, F.: Split, embed and merge: an accurate table structure recognizer. Pattern Recognit. 126, 108565 (2022). https:\/\/doi.org\/10.1016\/J.PATCOG.2022.108565","journal-title":"Pattern Recognit."},{"key":"2_CR27","doi-asserted-by":"publisher","unstructured":"Deng, Y., Kanervisto, A., Ling, J., Rush, A.M.: Image-to-markup generation with coarse-to-fine attention. In: 34th International Conference on Machine Learning, ICML 2017, vol. 3, pp. 1631\u20131640 (2016). https:\/\/doi.org\/10.48550\/arxiv.1609.04938","DOI":"10.48550\/arxiv.1609.04938"},{"key":"2_CR28","doi-asserted-by":"publisher","unstructured":"Zheng, X., Burdick, D., Popa, L., Zhong, X., Wang, N.X.R.: Global table extractor (GTE): a framework for joint table identification and cell structure recognition using visual context. In: 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 697\u2013706 (2021). https:\/\/doi.org\/10.1109\/WACV48630.2021.00074","DOI":"10.1109\/WACV48630.2021.00074"},{"key":"2_CR29","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778. IEEE (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"2_CR30","unstructured":"MMCV Contributors: {MMCV: OpenMMLab} Computer Vision Foundation (2018). https:\/\/github.com\/open-mmlab\/mmcv"}],"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_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:23:01Z","timestamp":1692343381000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41679-8_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031416781","9783031416798"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41679-8_2","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)"}}]}}