{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T15:11:51Z","timestamp":1782745911896,"version":"3.54.5"},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T00:00:00Z","timestamp":1756771200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T00:00:00Z","timestamp":1756771200000},"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":["IJDAR"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s10032-025-00553-7","type":"journal-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T06:11:38Z","timestamp":1756793498000},"page":"319-334","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["From pixels to tables: reconstructing complex tables from document images"],"prefix":"10.1007","volume":"29","author":[{"given":"Sachin","family":"Raja","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ajoy","family":"Mondal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"C. V.","family":"Jawahar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,2]]},"reference":[{"key":"553_CR1","unstructured":"Raja, S., Mondal, A., Jawahar, C.V.: Table structure recognition using top-down and bottom-up cues. In: ECCV (2020)"},{"key":"553_CR2","doi-asserted-by":"crossref","unstructured":"Raja, S., Mondal, A., Jawahar, C.: Visual understanding of complex table structures from document images. In: WACV, pp. 2299\u20132308 (2022)","DOI":"10.1109\/WACV51458.2022.00260"},{"key":"553_CR3","unstructured":"Li, M., Cui, L., Huang, S., Wei, F., Zhou, M., Li, Z.: TableBank: Table benchmark for image-based table detection and recognition. In: ICDAR (2019)"},{"key":"553_CR4","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: ICDAR (2019)","DOI":"10.1109\/ICDAR.2019.00029"},{"key":"553_CR5","doi-asserted-by":"crossref","unstructured":"Zhong, X., ShafieiBavani, E., Yepes, A.J.: Image-based table recognition: data, model, and evaluation. arXiv (2019)","DOI":"10.1007\/978-3-030-58589-1_34"},{"key":"553_CR6","unstructured":"Chi, Z., Huang, H., Xu, H.-D., Yu, H., Yin, W., Mao, X.-L.: Complicated table structure recognition. arXiv (2019)"},{"key":"553_CR7","unstructured":"Xue, W., Li, Q., Tao, D.: ReS2TIM: Reconstruct syntactic structures from table images. In: ICDAR (2019)"},{"key":"553_CR8","doi-asserted-by":"crossref","unstructured":"Qasim, S.R., Mahmood, H., Shafait, F.: Rethinking table parsing using graph neural networks. In: ICDAR (2019)","DOI":"10.1109\/ICDAR.2019.00031"},{"key":"553_CR9","doi-asserted-by":"crossref","unstructured":"Zanibbi, R., Blostein, D., Cordy, J.R.: Recognizing mathematical expressions using tree transformation. IEEE Trans. on PAMI (2002)","DOI":"10.1109\/TPAMI.2002.1046157"},{"key":"553_CR10","doi-asserted-by":"crossref","unstructured":"Zhang, J., Du, J., Dai, L.: Multi-scale attention with dense encoder for handwritten mathematical expression recognition. In: ICDAR (2018)","DOI":"10.1109\/ICPR.2018.8546031"},{"key":"553_CR11","doi-asserted-by":"crossref","unstructured":"Siegel, N., Horvitz, Z., Levin, R., Divvala, S., Farhadi, A.: FigureSeer: Parsing result-figures in research papers. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46478-7_41"},{"key":"553_CR12","doi-asserted-by":"crossref","unstructured":"Tang, B., Liu, X., Lei, J., Song, M., Tao, D., Sun, S., Dong, F.: DeepChart: Combining deep convolutional networks and deep belief networks in chart classification. Signal Processing (2015)","DOI":"10.1016\/j.sigpro.2015.09.027"},{"key":"553_CR13","doi-asserted-by":"crossref","unstructured":"Nishida, K., Sadamitsu, K., Higashinaka, R., Matsuo, Y.: Understanding the semantic structures of tables with a hybrid deep neural network architecture. In: AAAI (2017)","DOI":"10.1609\/aaai.v31i1.10484"},{"key":"553_CR14","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: ICDAR (2017)","DOI":"10.1109\/ICDAR.2017.192"},{"key":"553_CR15","doi-asserted-by":"crossref","unstructured":"Bao, J., Tang, D., Duan, N., Yan, Z., Lv, Y., Zhou, M., Zhao, T.: Table-to-text: Describing table region with natural language. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.11944"},{"key":"553_CR16","doi-asserted-by":"crossref","unstructured":"Tensmeyer, C., Morariu, V., Price, B., Cohen, S., Martinezp, T.: Deep splitting and merging for table structure decomposition. In: ICDAR (2019)","DOI":"10.1109\/ICDAR.2019.00027"},{"key":"553_CR17","doi-asserted-by":"crossref","unstructured":"Khan, S.A., Khalid, S.M.D., Shahzad, M.A., Shafait, F.: Table structure extraction with Bi-directional Gated Recurrent Unit networks. In: ICDAR (2019)","DOI":"10.1109\/ICDAR.2019.00220"},{"key":"553_CR18","doi-asserted-by":"crossref","unstructured":"Siddiqui, S.A., Khan, P.I., Dengel, A., Ahmed, S.: Rethinking semantic segmentation for table structure recognition in documents. In: ICDAR (2019)","DOI":"10.1109\/ICDAR.2019.00225"},{"key":"553_CR19","doi-asserted-by":"crossref","unstructured":"Ly, N.T., Takasu, A.: An end-to-end multi-task learning model for image-based table recognition. arXiv preprint arXiv:2303.08648 (2023)","DOI":"10.5220\/0011685000003417"},{"key":"553_CR20","doi-asserted-by":"crossref","unstructured":"Smock, B., Pesala, R., Abraham, R.: Aligning benchmark datasets for table structure recognition. arXiv preprint arXiv:2303.00716 (2023)","DOI":"10.1007\/978-3-031-41734-4_23"},{"issue":"1","key":"553_CR21","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. Scientific Data 10(1), 110 (2023)","journal-title":"Scientific Data"},{"key":"553_CR22","doi-asserted-by":"crossref","unstructured":"Ly, N.T., Takasu, A., Nguyen, P., Takeda, H.: Rethinking image-based table recognition using weakly supervised methods. arXiv preprint arXiv:2303.07641 (2023)","DOI":"10.5220\/0011682600003411"},{"key":"553_CR23","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1016\/j.patrec.2022.12.014","volume":"165","author":"H Wang","year":"2023","unstructured":"Wang, H., Xue, Y., Zhang, J., Jin, L.: Scene table structure recognition with segmentation collaboration and alignment. Pattern Recogn. Lett. 165, 146\u2013153 (2023)","journal-title":"Pattern Recogn. Lett."},{"key":"553_CR24","unstructured":"Itonori, K.: Table structure recognition based on textblock arrangement and ruled line position. In: ICDAR (1993)"},{"key":"553_CR25","unstructured":"Green, E., Krishnamoorthy, M.: Recognition of tables using table grammars. In: Annual Symposium on Document Analysis and Information Retrieval (1995)"},{"key":"553_CR26","doi-asserted-by":"crossref","unstructured":"Kieninger, T.G.: Table structure recognition based on robust block segmentation. In: Document Recognition V (1998)","DOI":"10.1117\/12.304642"},{"key":"553_CR27","volume-title":"Extracting tabular information from text files","author":"S Tupaj","year":"1996","unstructured":"Tupaj, S., Shi, Z., Chang, C.H., Alam, H.: Extracting tabular information from text files. Tufts University, Medford, USA, EECS Department (1996)"},{"key":"553_CR28","doi-asserted-by":"crossref","unstructured":"Harit, G., Bansal, A.: Table detection in document images using header and trailer patterns. In: ICVGIP (2012)","DOI":"10.1145\/2425333.2425395"},{"key":"553_CR29","doi-asserted-by":"crossref","unstructured":"Gatos, B., Danatsas, D., Pratikakis, I., Perantonis, S.J.: Automatic table detection in document images. In: CVPR (2005)","DOI":"10.1007\/11551188_67"},{"key":"553_CR30","doi-asserted-by":"crossref","unstructured":"Ohta, M., Yamada, R., Kanazawa, T., Takasu, A.: A cell-detection-based table-structure recognition method. In: ACM Symposium on Document Engineering (2019)","DOI":"10.1145\/3342558.3345412"},{"key":"553_CR31","unstructured":"Wang, Y., Phillips, I.T., Haralick, R.M.: Table structure understanding and its performance evaluation. Pattern Recognition (2004)"},{"key":"553_CR32","doi-asserted-by":"crossref","unstructured":"Riba, P., Dutta, A., Goldmann, L., Fornes, A., Ramos, O., Llados, J.: Table detection in invoice documents by graph neural networks. In: ICDAR (2019)","DOI":"10.1109\/ICDAR.2019.00028"},{"key":"553_CR33","doi-asserted-by":"crossref","unstructured":"Hole\u010dek, M., Hoskovec, A., Baudi\u0161, P., Klinger, P.: Line-items and table understanding in structured documents. arXiv (2019)","DOI":"10.1109\/ICDARW.2019.40098"},{"key":"553_CR34","doi-asserted-by":"crossref","unstructured":"Ma, C., Lin, W., Sun, L., Huo, Q.: Robust table detection and structure recognition from heterogeneous document images. arXiv preprint arXiv:2203.09056 (2022)","DOI":"10.1016\/j.patcog.2022.109006"},{"key":"553_CR35","doi-asserted-by":"crossref","unstructured":"Shen, X., Kong, L., Bao, Y., Zhou, Y., Liu, W.: Rcanet: A rows and columns aggregated network for table structure recognition. In: 2022 3rd Information Communication Technologies Conference (ICTC), pp. 112\u2013116 (2022). IEEE","DOI":"10.1109\/ICTC55111.2022.9778621"},{"key":"553_CR36","doi-asserted-by":"crossref","unstructured":"Long, R., Wang, W., Xue, N., Gao, F., Yang, Z., Wang, Y., Xia, G.-S.: Parsing table structures in the wild. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 944\u2013952 (2021)","DOI":"10.1109\/ICCV48922.2021.00098"},{"key":"553_CR37","unstructured":"Xue, W., Yu, B., Wang, W., Tao, D., Li, Q.: Tgrnet: A table graph reconstruction network for table structure recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1295\u20131304 (2021)"},{"key":"553_CR38","unstructured":"Kumar, T., Bhatt, H.S.: Evaluating table structure recognition: A new perspective. arXiv preprint arXiv:2208.00385 (2022)"},{"key":"553_CR39","doi-asserted-by":"crossref","unstructured":"Smock, B., Pesala, R., Abraham, R.: Grits: Grid table similarity metric for table structure recognition. arXiv preprint arXiv:2203.12555 (2022)","DOI":"10.1007\/978-3-031-41734-4_33"},{"key":"553_CR40","doi-asserted-by":"crossref","unstructured":"Lin, W., Sun, Z., Ma, C., Li, M., Wang, J., Sun, L., Huo, Q.: Tsrformer: Table structure recognition with transformers. arXiv preprint arXiv:2208.04921 (2022)","DOI":"10.1145\/3503161.3548038"},{"key":"553_CR41","unstructured":"Xiao, B., Simsek, M., Kantarci, B., Alkheir, A.A.: Table structure recognition with conditional attention. arXiv preprint arXiv:2203.03819 (2022)"},{"key":"553_CR42","doi-asserted-by":"crossref","unstructured":"Xing, H., Gao, F., Long, R., Bu, J., Zheng, Q., Li, L., Yao, C., Yu, Z.: Lore: Logical location regression network for table structure recognition. arXiv preprint arXiv:2303.03730 (2023)","DOI":"10.1609\/aaai.v37i3.25402"},{"key":"553_CR43","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, X., Gong, M., Liu, B., Wu, Y., Jiang, D., Liu, Y., Sun, X.: Grab what you need: Rethinking complex table structure recognition with flexible components deliberation. arXiv preprint arXiv:2303.09174 (2023)","DOI":"10.1609\/aaai.v38i4.28149"},{"key":"553_CR44","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11134\u201311143 (2023)","DOI":"10.1109\/CVPR52729.2023.01071"},{"key":"553_CR45","doi-asserted-by":"crossref","unstructured":"Nassar, A., Livathinos, N., Lysak, M., Staar, P.: Tableformer: Table structure understanding with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4614\u20134623 (2022)","DOI":"10.1109\/CVPR52688.2022.00457"},{"key":"553_CR46","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: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 697\u2013706 (2021)","DOI":"10.1109\/WACV48630.2021.00074"},{"key":"553_CR47","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"},{"key":"553_CR48","unstructured":"Vaswani, A.: Attention is all you need. Advances in Neural Information Processing Systems (2017)"},{"key":"553_CR49","doi-asserted-by":"crossref","unstructured":"Pan, X., Ye, T., Xia, Z., Song, S., Huang, G.: Slide-transformer: Hierarchical vision transformer with local self-attention. In: CVPR, pp. 2082\u20132091 (2023)","DOI":"10.1109\/CVPR52729.2023.00207"},{"key":"553_CR50","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229 (2020). Springer"},{"key":"553_CR51","doi-asserted-by":"crossref","unstructured":"Liu, S., Ren, T., Chen, J., Zeng, Z., Zhang, H., Li, F., Li, H., Huang, J., Su, H., Zhu, J., et al.: Detection transformer with stable matching. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6491\u20136500 (2023)","DOI":"10.1109\/ICCV51070.2023.00597"},{"key":"553_CR52","doi-asserted-by":"crossref","unstructured":"Qiao, L., Li, Z., Cheng, Z., Zhang, P., Pu, S., Niu, Y., Ren, W., Tan, W., Wu, F.: Lgpma: Complicated table structure recognition with local and global pyramid mask alignment. arXiv preprint arXiv:2105.06224 (2021)","DOI":"10.1007\/978-3-030-86549-8_7"},{"key":"553_CR53","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":"553_CR54","doi-asserted-by":"crossref","unstructured":"Lyu, P., Ma, W., Wang, H., Yu, Y., Zhang, C., Yao, K., Xue, Y., Wang, J.: Gridformer: Towards accurate table structure recognition via grid prediction. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 7747\u20137757 (2023)","DOI":"10.1145\/3581783.3611961"},{"key":"553_CR55","doi-asserted-by":"crossref","unstructured":"G\u00f6bel, M., Hassan, T., Oro, E., Orsi, G.: ICDAR 2013 table competition. In: ICDAR (2013)","DOI":"10.1109\/ICDAR.2013.292"},{"key":"553_CR56","doi-asserted-by":"crossref","unstructured":"Zhong, X., ShafieiBavani, E., Yepes, A.J.: Image-based table recognition: data, model, and evaluation. arXiv (2019)","DOI":"10.1007\/978-3-030-58589-1_34"},{"key":"553_CR57","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: ICDAR (2019)","DOI":"10.1109\/ICDAR.2019.00243"},{"key":"553_CR58","doi-asserted-by":"crossref","unstructured":"Smith, R.: An overview of the Tesseract OCR engine. In: ICDAR (2007)","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"553_CR59","doi-asserted-by":"crossref","unstructured":"Gao, L., D\u00e9jean, H., Yan, Q., Kleber, F., Huang, Y., Meunier, J.-L., Fang, Y.: ICDAR 2019 competition on table detection and recognition (cTDaR). In: ICDAR (2019)","DOI":"10.1109\/ICDAR.2019.00243"}],"container-title":["International Journal on Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-025-00553-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10032-025-00553-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-025-00553-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T07:08:00Z","timestamp":1781939280000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10032-025-00553-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,2]]},"references-count":59,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["553"],"URL":"https:\/\/doi.org\/10.1007\/s10032-025-00553-7","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"value":"1433-2833","type":"print"},{"value":"1433-2825","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,2]]},"assertion":[{"value":"3 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 August 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 September 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors declare that they have no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest\/Competing interests"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"This particular work does not involve humans or animals.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"The work submitted for publication may not have implications for public health or general welfare.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}