{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T19:48:28Z","timestamp":1778615308555,"version":"3.51.4"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,10,27]],"date-time":"2022-10-27T00:00:00Z","timestamp":1666828800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,10,27]],"date-time":"2022-10-27T00:00:00Z","timestamp":1666828800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001843","name":"Science and Engineering Research Board","doi-asserted-by":"publisher","award":["ECR\/2018\/000087"],"award-info":[{"award-number":["ECR\/2018\/000087"]}],"id":[{"id":"10.13039\/501100001843","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["IJDAR"],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1007\/s10032-022-00420-9","type":"journal-article","created":{"date-parts":[[2022,10,27]],"date-time":"2022-10-27T10:03:36Z","timestamp":1666865016000},"page":"121-130","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Tables to LaTeX: structure and content extraction from scientific tables"],"prefix":"10.1007","volume":"26","author":[{"given":"Pratik","family":"Kayal","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mrinal","family":"Anand","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harsh","family":"Desai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mayank","family":"Singh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,27]]},"reference":[{"key":"420_CR1","unstructured":"Ba, L.J., Kiros, J.R., Hinton, G.E.: Layer normalization. CoRR (2016). http:\/\/arxiv.org\/abs\/1607.06450"},{"key":"420_CR2","unstructured":"Brischoux, F., Legagneux, P.: Don\u2019t format manuscripts. Scientist 23(7), 24 (2009)"},{"key":"420_CR3","unstructured":"Chi, Z., Huang, H., Xu, H., Yu, H., Yin, W., Mao, X.: Complicated table structure recognition. CoRR (2019). http:\/\/arxiv.org\/abs\/1908.04729"},{"key":"420_CR4","unstructured":"Deng, Y., Kanervisto, A., Ling, J., Rush, A.M.: Image-to-markup generation with coarse-to-fine attention. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 980\u2013989. JMLR. org (2017)"},{"key":"420_CR5","doi-asserted-by":"crossref","unstructured":"Deng, Y., Rosenberg, D., Mann, G.: Challenges in end-to-end neural scientific table recognition. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 894\u2013901 (2019)","DOI":"10.1109\/ICDAR.2019.00148"},{"key":"420_CR6","unstructured":"Douglas, S., Hurst, M., Quinn, D., et al.: Using natural language processing for identifying and interpreting tables in plain text. In: Proceedings of the Fourth Annual Symposium on Document Analysis and Information Retrieval, pp. 535\u2013546 (1995)"},{"issue":"2\u20133","key":"420_CR7","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1007\/s10032-006-0017-x","volume":"8","author":"DW Embley","year":"2006","unstructured":"Embley, D.W., Hurst, M., Lopresti, D., Nagy, G.: Table-processing paradigms: a research survey. IJDAR 8(2\u20133), 66\u201386 (2006)","journal-title":"IJDAR"},{"key":"420_CR8","doi-asserted-by":"crossref","unstructured":"Fang, J., Tao, X., Tang, Z., Qiu, R., Liu, Y.: Dataset, ground-truth and performance metrics for table detection evaluation. In: 2012 10th IAPR International Workshop on Document Analysis Systems, pp. 445\u2013449. IEEE (2012)","DOI":"10.1109\/DAS.2012.29"},{"key":"420_CR9","unstructured":"Feng, X., Yao, H., Yi, Y., Zhang, J., Zhang, S.: Scene text recognition via transformer. arXiv preprint (2020). arXiv:2003.08077"},{"key":"420_CR10","doi-asserted-by":"crossref","unstructured":"Gao, L., Huang, Y., D\u00e9jean, H., Meunier, J.L., Yan, Q., Fang, Y., Kleber, F., Lang, E.: Icdar 2019 competition on table detection and recognition (ctdar). In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1510\u20131515. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00243"},{"key":"420_CR11","doi-asserted-by":"crossref","unstructured":"G\u00f6bel, M., Hassan, T., Oro, E., Orsi, G.: Icdar 2013 table competition. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 1449\u20131453. IEEE (2013)","DOI":"10.1109\/ICDAR.2013.292"},{"key":"420_CR12","doi-asserted-by":"publisher","first-page":"87663","DOI":"10.1109\/ACCESS.2021.3087865","volume":"9","author":"KA Hashmi","year":"2021","unstructured":"Hashmi, K.A., Liwicki, M., Stricker, D., Afzal, M.A., Afzal, M.A., Afzal, M.Z.: Current status and performance analysis of table recognition in document images with deep neural networks. IEEE Access 9, 87663\u201387685 (2021)","journal-title":"IEEE Access"},{"key":"420_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"420_CR14","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, W., Chen, J., Wei, X.Y.: Attention on attention for image captioning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4634\u20134643 (2019)","DOI":"10.1109\/ICCV.2019.00473"},{"key":"420_CR15","doi-asserted-by":"crossref","unstructured":"Klein, G., Kim, Y., Deng, Y., Senellart, J., Rush, A.: OpenNMT: open-source toolkit for neural machine translation. In: Proceedings of ACL 2017, System Demonstrations, pp. 67\u201372. Association for Computational Linguistics, Vancouver (2017). https:\/\/www.aclweb.org\/anthology\/P17-4012","DOI":"10.18653\/v1\/P17-4012"},{"key":"420_CR16","unstructured":"Levenshtein, V.I., et al.: Binary codes capable of correcting deletions, insertions, and reversals. In: Soviet Physics Doklady, vol.\u00a010, pp. 707\u2013710. Soviet Union (1966)"},{"key":"420_CR17","unstructured":"Li, M., Cui, L., Huang, S., Wei, F., Zhou, M., Li, Z.: Tablebank: table benchmark for image-based table detection and recognition. In: LREC 2020 (2020). https:\/\/www.microsoft.com\/en-us\/research\/publication\/tablebank-table-benchmark-for-image-based-table-detection-and-recognition\/"},{"key":"420_CR18","unstructured":"Lyu, P., Yang, Z., Leng, X., Wu, X., Li, R., Shen, X.: 2d attentional irregular scene text recognizer. arXiv preprint (2019). arXiv:1906.05708"},{"key":"420_CR19","unstructured":"Niklaus, C., Cetto, M., Freitas, A., Handschuh, S.: A survey on open information extraction. In: Proceedings of the 27th International Conference on Computational Linguistics, pp. 3866\u20133878 (2018)"},{"key":"420_CR20","doi-asserted-by":"crossref","unstructured":"Paliwal, S.S., Vishwanath, D., Rahul, R., Sharma, M., Vig, L.: Tablenet: deep learning model for end-to-end table detection and tabular data extraction from scanned document images. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 128\u2013133. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00029"},{"key":"420_CR21","doi-asserted-by":"crossref","unstructured":"Raja, S., Mondal, A., Jawahar, C.V.: Table structure recognition using top-down and bottom-up cues. CoRR (2020). https:\/\/arxiv.org\/abs\/2010.04565","DOI":"10.1007\/978-3-030-58604-1_5"},{"key":"420_CR22","doi-asserted-by":"crossref","unstructured":"Ramel, J.Y., Crucianu, M., Vincent, N., Faure, C.: Detection, extraction and representation of tables. In: 7th International Conference on Document Analysis and Recognition. Proceedings, pp. 374\u2013378. IEEE (2003)","DOI":"10.1109\/ICDAR.2003.1227692"},{"issue":"3","key":"420_CR23","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1561\/1900000003","volume":"1","author":"S Sarawagi","year":"2008","unstructured":"Sarawagi, S.: Information extraction. Found. Trends Databases 1(3), 261\u2013377 (2008)","journal-title":"Found. Trends Databases"},{"key":"420_CR24","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: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol.\u00a01, pp. 1162\u20131167. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.192"},{"key":"420_CR25","doi-asserted-by":"crossref","unstructured":"Siegel, N., Lourie, N., Power, R., Ammar, W.: Extracting scientific figures with distantly supervised neural networks. In: Proceedings of the 18th ACM\/IEEE On Joint Conference on Digital Libraries, pp. 223\u2013232 (2018)","DOI":"10.1145\/3197026.3197040"},{"issue":"2\u20133","key":"420_CR26","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1007\/s10032-005-0001-x","volume":"8","author":"AC Silva","year":"2006","unstructured":"Silva, A.C., Jorge, A.M., Torgo, L.: Design of an end-to-end method to extract information from tables. Int. J. Doc. Anal. Recogn. (IJDAR) 8(2\u20133), 144\u2013171 (2006)","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"420_CR27","doi-asserted-by":"crossref","unstructured":"Singh, M., Sarkar, R., Vyas, A., Goyal, P., Mukherjee, A., Chakrabarti, S.: Automated early leaderboard generation from comparative tables. In: European Conference on Information Retrieval, pp. 244\u2013257. Springer (2019)","DOI":"10.1007\/978-3-030-15712-8_16"},{"key":"420_CR28","doi-asserted-by":"crossref","unstructured":"Smith, R.: An overview of the tesseract OCR engine. In: 9th International Conference on Document Analysis and Recognition (ICDAR 2007), vol. 2, pp. 629\u2013633. IEEE (2007)","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"420_CR29","doi-asserted-by":"publisher","unstructured":"pandas development team, T.: pandas-dev\/pandas: Pandas (2020). https:\/\/doi.org\/10.5281\/zenodo.3509134","DOI":"10.5281\/zenodo.3509134"},{"key":"420_CR30","doi-asserted-by":"publisher","unstructured":"Tenopir, C., King, D.W.: 6\u2014The growth of journals publishing. In: B. Cope, A. Phillips (eds.) The Future of the Academic Journal, 2nd edn., pp. 159 \u2013 178. Chandos Publishing (2014). https:\/\/doi.org\/10.1533\/9781780634647.159. http:\/\/www.sciencedirect.com\/science\/article\/pii\/B9781843347835500069","DOI":"10.1533\/9781780634647.159"},{"key":"420_CR31","doi-asserted-by":"publisher","unstructured":"Tensmeyer, C., Morariu, V.I., Price, B., Cohen, S., Martinez, T.: Deep splitting and merging for table structure decomposition. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 114\u2013121 (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00027","DOI":"10.1109\/ICDAR.2019.00027"},{"key":"420_CR32","doi-asserted-by":"crossref","unstructured":"Vasileiadis, M., Kaklanis, N., Votis, K., Tzovaras, D.: Extraction of tabular data from document images. In: Proceedings of the 14th Web for all Conference on the Future of Accessible Work, pp. 1\u20132 (2017)","DOI":"10.1145\/3058555.3058581"},{"key":"420_CR33","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"420_CR34","unstructured":"Yang, L., Wang, P., Li, H., Gao, Y., Zhang, L., Shen, C., Zhang, Y.: A simple and strong convolutional-attention network for irregular text recognition. arXiv preprint (2019). arXiv:1904.01375"},{"key":"420_CR35","unstructured":"Yildiz, B., Kaiser, K., Miksch, S.: pdf2table: a method to extract table information from pdf files. In: IICAI, pp. 1773\u20131785 (2005)"},{"key":"420_CR36","doi-asserted-by":"crossref","unstructured":"Zhong, X., ShafieiBavani E., Jimeno Yepes, A.: Image-based table recognition: data, model, and evaluation. European Conference on Computer Vision. Springer, Cham (2020)","DOI":"10.1007\/978-3-030-58589-1_34"},{"key":"420_CR37","doi-asserted-by":"publisher","unstructured":"Zhong, X., Tang, J., Yepes, A.J.: Publaynet: largest dataset ever for document layout analysis. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1015\u20131022. IEEE (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00166","DOI":"10.1109\/ICDAR.2019.00166"}],"container-title":["International Journal on Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-022-00420-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10032-022-00420-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-022-00420-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T17:14:43Z","timestamp":1728234883000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10032-022-00420-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,27]]},"references-count":37,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,6]]}},"alternative-id":["420"],"URL":"https:\/\/doi.org\/10.1007\/s10032-022-00420-9","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"value":"1433-2833","type":"print"},{"value":"1433-2825","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,27]]},"assertion":[{"value":"12 May 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 June 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 September 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 October 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}