{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T22:03:22Z","timestamp":1787695402293,"version":"build-2784847793"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031705328","type":"print"},{"value":"9783031705335","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-70533-5_23","type":"book-chapter","created":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:02:25Z","timestamp":1725685345000},"page":"389-405","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Multi-cell Decoder and\u00a0Mutual Learning for\u00a0Table Structure and\u00a0Character Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1285-2748","authenticated-orcid":false,"given":"Takaya","family":"Kawakatsu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,8]]},"reference":[{"key":"23_CR1","unstructured":"Beltagy, I., Peters, M.E., Cohan, A.: Longformer: the long-document transformer (2020)"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F., Hu, H.: GCNet: non-local networks meet squeeze-excitation networks and beyond. In: IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW), pp. 1971\u20131980 (2019)","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Deng, Y., Rosenberg, D., Mann, G.: Challenges in end-to-end neural scientific table recognition. In: International Conference on Document Analysis and Recognition (ICDAR), pp. 894\u2013901 (2019)","DOI":"10.1109\/ICDAR.2019.00148"},{"key":"23_CR4","unstructured":"Gehring, J., Auli, M., Grangier, D., Yarats, D., Dauphin, Y.N.: Convolutional sequence to sequence learning. In: International Conference on Machine Learning (ICML), pp. 1243\u20131252 (2017)"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: IEEE International Conference on Computer Vision (ICCV), pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"23_CR7","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network (2015)"},{"key":"23_CR8","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735\u201380 (1997)","journal-title":"Neural Comput."},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Maaten, L.V.D., Weinberger, K.Q.: Densely connected convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2261\u20132269 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Huang, Y., Lu, N., Chen, D., Li, Y., Xie, Z., Zhu, S., Gao, L., Peng, W.: Improving table structure recognition with visual-alignment sequential coordinate modeling. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11134\u201311143 (2023)","DOI":"10.1109\/CVPR52729.2023.01071"},{"key":"23_CR11","unstructured":"Itonori, K.: Table structure recognition based on textblock arrangement and ruled line position. In: International Conference on Document Analysis and Recognition (ICDAR), pp. 765\u2013768 (1993)"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Kayal, P., Anand, M., Desai, H., Singh, M.: ICDAR 2021 competition on scientific table image recognition to LaTeX. In: International Conference on Document Analysis and Recognition (ICDAR), pp. 754\u2013766 (2021)","DOI":"10.1007\/978-3-030-86337-1_50"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Kieninger, T.G.: Table structure recognition based on robust block segmentation. In: Photonics West \u201998. vol.\u00a03305, pp. 22\u201332 (1998)","DOI":"10.1117\/12.304642"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Kullback, S., Leibler, R.A.: On information and sufficiency. Ann. Math. Stat. 22(1) (1951)","DOI":"10.1214\/aoms\/1177729694"},{"key":"23_CR15","unstructured":"Li, M., Cui, L., Huang, S., Wei, F., Zhou, M., Li, Z.: TableBank: table benchmark for image-based table detection and recognition. In: Language Resources and Evaluation Conference (LREC), pp. 1918\u20131925 (2020)"},{"key":"23_CR16","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), pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"23_CR17","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 Recogn. 117, 107980 (2021)","journal-title":"Pattern Recogn."},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Ly, N.T., Takasu, A.: An end-to-end local attention based model for table recognition. In: International Conference on Document Analysis and Recognition (ICDAR), pp. 20\u201336 (2023)","DOI":"10.1007\/978-3-031-41679-8_2"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Ly, N.T., Takasu, A.: An end-to-end multi-task learning model for image-based table recognition. In: International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP), pp. 626\u2013634 (2023)","DOI":"10.5220\/0011685000003417"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Ly, N.T., Takasu, A., Nguyen, P., Takeda, H.: Rethinking image-based table recognition using weakly supervised methods. In: International Conference on Pattern Recognition Applications and Methods (ICPRAM), pp. 872\u2013880 (2023)","DOI":"10.5220\/0011682600003411"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Nassar, A., Livathinos, N., Lysak, M., Staar, P.: TableFormer: table structure understanding with transformers. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4604\u20134613 (2022)","DOI":"10.1109\/CVPR52688.2022.00457"},{"key":"23_CR22","unstructured":"OpenMMLab: MMCV. https:\/\/github.com\/open-mmlab\/mmcv"},{"key":"23_CR23","unstructured":"OpenMMLab: MMDetection. https:\/\/github.com\/open-mmlab\/mmdetection"},{"key":"23_CR24","unstructured":"OpenMMLab: MMOCR. https:\/\/github.com\/open-mmlab\/mmocr"},{"key":"23_CR25","unstructured":"Peng, A., Lee, S., Wang, X., Balasubramaniyan, R., Chau, D.H.: High-performance transformers for table structure recognition need early convolutions. In: Table Representation Learning Workshop (2023)"},{"key":"23_CR26","doi-asserted-by":"crossref","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\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 2439\u20132447 (2020)","DOI":"10.1109\/CVPRW50498.2020.00294"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Qiao, L., et al.: LGPMA: Complicated table structure recognition with local and global pyramid mask alignment. In: International Conference on Document Analysis and Recognition (ICDAR), pp. 99\u2013114 (2021)","DOI":"10.1007\/978-3-030-86549-8_7"},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Raja, S., Mondal, A., Jawahar, C.V.: Table structure recognition using top-down and bottom-up cues. In: Computer Vision \u2013 ECCV, pp. 70\u201386 (2020)","DOI":"10.1007\/978-3-030-58604-1_5"},{"key":"23_CR29","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems. vol.\u00a028 (2015)"},{"key":"23_CR30","doi-asserted-by":"crossref","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: International Conference on Document Analysis and Recognition (ICDAR), pp. 1162\u20131167 (2017)","DOI":"10.1109\/ICDAR.2017.192"},{"key":"23_CR31","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems. vol.\u00a030, pp. 6000\u20136010 (2017)"},{"issue":"7","key":"23_CR32","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 Recogn. 37(7), 1479\u20131497 (2004)","journal-title":"Pattern Recogn."},{"key":"23_CR33","unstructured":"Wright, L.: Ranger - a synergistic optimizer (2019). https:\/\/github.com\/lessw2020\/Ranger-Deep-Learning-Optimizer"},{"key":"23_CR34","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R.B., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5987\u20135995 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"issue":"1","key":"23_CR35","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1038\/s41597-023-01985-8","volume":"10","author":"F Yang","year":"2023","unstructured":"Yang, F., Hu, L., Liu, X., Huang, S., Gu, Z.: A large-scale dataset for end-to-end table recognition in the wild. Sci. Data 10(1), 110 (2023)","journal-title":"Sci. Data"},{"key":"23_CR36","unstructured":"Ye, J., et al.: PingAn-VCGroup\u2019s solution for ICDAR 2021 competition on scientific literature parsing task B: table recognition to HTML (2021)"},{"key":"23_CR37","doi-asserted-by":"crossref","unstructured":"Yepes, A.J., Zhong, P., Burdick, D.: ICDAR 2021 competition on scientific literature parsing. In: International Conference on Document Analysis and Recognition (ICDAR), pp. 605\u2013617 (2021)","DOI":"10.1007\/978-3-030-86337-1_40"},{"key":"23_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Xiang, T., Hospedales, T.M., Lu, H.: Deep mutual learning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4320\u20134328 (2018)","DOI":"10.1109\/CVPR.2018.00454"},{"key":"23_CR39","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 Recogn. 126, 108565 (2022)","journal-title":"Pattern Recogn."},{"key":"23_CR40","doi-asserted-by":"crossref","unstructured":"Zhao, W., Gao, L., Yan, Z., Peng, S., Du, L., Zhang, Z.: Handwritten mathematical expression recognition with bidirectionally trained transformer. In: International Conference on Document Analysis and Recognition (ICDAR), pp. 570\u2013584 (2021)","DOI":"10.1007\/978-3-030-86331-9_37"},{"key":"23_CR41","doi-asserted-by":"crossref","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: IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 697\u2013706 (2021)","DOI":"10.1109\/WACV48630.2021.00074"},{"key":"23_CR42","doi-asserted-by":"crossref","unstructured":"Zhong, X., ShafieiBavani, E., Yepes, A.J.: Image-based table recognition: Data, model, and evaluation. In: Computer Vision \u2013 ECCV, pp. 564\u2013580 (2020)","DOI":"10.1007\/978-3-030-58589-1_34"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70533-5_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:08:27Z","timestamp":1725685707000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70533-5_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705328","9783031705335"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70533-5_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"8 September 2024","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":"Athens","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","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":"30 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2024.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}