{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:11:03Z","timestamp":1778051463630,"version":"3.51.4"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:00:00Z","timestamp":1778025600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:00:00Z","timestamp":1778025600000},"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":["Multimedia Systems"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1007\/s00530-026-02276-z","type":"journal-article","created":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:11:48Z","timestamp":1778047908000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Tabamba: a Mamba-Transformer hybrid model for table structure recognition"],"prefix":"10.1007","volume":"32","author":[{"given":"Junqi","family":"Xiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingjie","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,5,6]]},"reference":[{"key":"2276_CR1","unstructured":"Itonori, K.: Table structure recognition based on textblock arrangement and ruled line position. In: Proceedings of the 2nd international conference on document analysis and recognition (ICDAR), pp. 765\u2013768. IEEE, Los Alamitos, CA, USA (1993)"},{"key":"2276_CR2","unstructured":"Green, E.A., Krishnamoorthy, M.: Recognition of tables using table grammars. In: Proceedings of the symposium on document analysis and information retrieval (SDAIR), pp. 261\u2013277. University of Nevada, Las Vegas, NV, USA (1995)"},{"issue":"7","key":"2276_CR3","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":"2276_CR4","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 International conference on document analysis and recognition (ICDAR), vol. 01, pp. 1162\u20131167. IEEE, Los Alamitos, CA, USA (2017)","DOI":"10.1109\/ICDAR.2017.192"},{"key":"2276_CR5","doi-asserted-by":"crossref","unstructured":"Paliwal, S., D., V., 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 Computer Society, Los Alamitos, CA, USA (2019)","DOI":"10.1109\/ICDAR.2019.00029"},{"key":"2276_CR6","doi-asserted-by":"crossref","unstructured":"Siddiqui, S.A., Fateh, I.A., Rizvi, S.T.R., Dengel, A.R., Ahmed, S.: Deeptabstr: Deep learning based table structure recognition. In: 2019 International conference on document analysis and recognition (ICDAR), pp. 1403\u20131409. IEEE, Los Alamitos, CA, USA (2019)","DOI":"10.1109\/ICDAR.2019.00226"},{"key":"2276_CR7","doi-asserted-by":"crossref","unstructured":"Khan, S.A., Khalid, S., Shahzad, M.A., Shafait, F.: Table structure extraction with bi-directional gated recurrent unit networks. In: 2019 International conference on document analysis and recognition (ICDAR), pp. 1366\u20131371. IEEE, Los Alamitos, CA, USA (2019)","DOI":"10.1109\/ICDAR.2019.00220"},{"key":"2276_CR8","doi-asserted-by":"crossref","unstructured":"Tensmeyer, C., Morariu, V.I., Price, B.L., Cohen, S.D., Martinez, T.: Deep splitting and merging for table structure decomposition. In: 2019 International conference on document analysis and recognition (ICDAR), pp. 114\u2013121. IEEE, Los Alamitos, CA, USA (2019)","DOI":"10.1109\/ICDAR.2019.00027"},{"key":"2276_CR9","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. In: ACM multimedia (MM \u201922), pp. 6473\u20136482. ACM, New York, NY, USA (2022)","DOI":"10.1145\/3503161.3548038"},{"key":"2276_CR10","doi-asserted-by":"publisher","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":"2276_CR11","doi-asserted-by":"crossref","unstructured":"Ma, C., Lin, W., Sun, L., Huo, Q.: Robust table detection and structure recognition from heterogeneous document images. Pattern Recognit. 133 (2023)","DOI":"10.1016\/j.patcog.2022.109006"},{"key":"2276_CR12","doi-asserted-by":"crossref","unstructured":"Nguyen, N.Q., Le, A.D., Lu, A.K., Mai, X.T., Tran, T.A.: Formerge: Recover spanning cells in complex table structure using transformer network. In: International conference on document analysis and recognition, Cham, Switzerland, pp. 522\u2013534 (2023). Springer","DOI":"10.1007\/978-3-031-41734-4_32"},{"key":"2276_CR13","doi-asserted-by":"crossref","unstructured":"Qasim, S.R., Mahmood, H., Shafait, F.: Rethinking table recognition using graph neural networks. In: 2019 International conference on document analysis and recognition (ICDAR), pp. 142\u2013147. IEEE, New York, NY, USA (2019)","DOI":"10.1109\/ICDAR.2019.00031"},{"key":"2276_CR14","doi-asserted-by":"crossref","unstructured":"Xue, W., Li, Q., Tao, D.: Res2tim: Reconstruct syntactic structures from table images. In: 2019 International conference on document analysis and recognition (ICDAR), pp. 749\u2013755. IEEE, New York, NY, USA (2019)","DOI":"10.1109\/ICDAR.2019.00125"},{"key":"2276_CR15","doi-asserted-by":"crossref","unstructured":"Raja, S., Mondal, A., Jawahar, C.V.: Table structure recognition using top-down and bottom-up cues. In: ECCV 2020, pp. 70\u201386. Springer, Cham, Switzerland (2020)","DOI":"10.1007\/978-3-030-58604-1_5"},{"key":"2276_CR16","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, X., Liu, B., Jiang, D., Liu, Y., Ren, B., Ji, R.: Show, read and reason: Table structure recognition with flexible context aggregator. In: ACM Multimedia, pp. 1084\u20131092. ACM, New York, NY, USA (2021)","DOI":"10.1145\/3474085.3481534"},{"key":"2276_CR17","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: ICCV, pp. 944\u2013952. IEEE, New York, NY, USA (2021)","DOI":"10.1109\/ICCV48922.2021.00098"},{"key":"2276_CR18","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. In: ICDAR, vol. 12821, pp. 99\u2013114. Springer, Cham, Switzerland (2021)","DOI":"10.1007\/978-3-030-86549-8_7"},{"key":"2276_CR19","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: WACV, pp. 697\u2013706. IEEE, New York, NY, USA (2021)","DOI":"10.1109\/WACV48630.2021.00074"},{"key":"2276_CR20","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: CVPR, pp. 4533\u20134542. IEEE, New York, NY, USA (2022)","DOI":"10.1109\/CVPR52688.2022.00449"},{"key":"2276_CR21","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. In: Proceedings of the AAAI Conference on artificial intelligence, vol. 37, pp. 2992\u20133000 (2023)","DOI":"10.1609\/aaai.v37i3.25402"},{"key":"2276_CR22","doi-asserted-by":"crossref","unstructured":"Deng, Y., Rosenberg, D., Mann, G.: Challenges in end-to-end neural scientific table recognition. In: ICDAR, pp. 894\u2013901. IEEE, New York, NY, USA (2019)","DOI":"10.1109\/ICDAR.2019.00148"},{"key":"2276_CR23","doi-asserted-by":"crossref","unstructured":"Zhong, X., ShafieiBavani, E., Yepes, A.J.: Image-based table recognition: Data, model, and evaluation. In: ECCV 2020, pp. 564\u2013580. Springer, Cham, Switzerland (2020)","DOI":"10.1007\/978-3-030-58589-1_34"},{"key":"2276_CR24","unstructured":"Ye, J., Qi, X., He, Y., Chen, Y., Gu, D., Gao, P., Xiao, R.: Pingan-vcgroup\u2019s Solution for ICDAR 2021 competition on scientific literature parsing task B: table recognition to HTML (2021)"},{"key":"2276_CR25","doi-asserted-by":"crossref","unstructured":"Nassar, A., Livathinos, N., Lysak, M., Staar, P.: Tableformer: table structure understanding with transformers. In: CVPR, pp. 4614\u20134623. IEEE, New York, NY, USA (2022)","DOI":"10.1109\/CVPR52688.2022.00457"},{"key":"2276_CR26","doi-asserted-by":"publisher","unstructured":"Ly, N.T., Takasu, A.: An end-to-end multi-task learning model for image-based table recognition. In: VISAPP, pp. 626\u2013634. SciTePress, Set\u00fabal, Portugal (2023). https:\/\/doi.org\/10.5220\/0011685000003417","DOI":"10.5220\/0011685000003417"},{"key":"2276_CR27","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: CVPR, pp. 11134\u201311143. IEEE, New York, NY, USA (2023)","DOI":"10.1109\/CVPR52729.2023.01071"},{"key":"2276_CR28","unstructured":"Khang, M., Hong, T.: Tflop: Table structure recognition framework with layout pointer mechanism. arXiv preprint arXiv:2501.11800 (2025)"},{"key":"2276_CR29","doi-asserted-by":"crossref","unstructured":"Kudale, D., Kasuba, B.V., Subramanian, V., Chaudhuri, P., Ramakrishnan, G.: Sprint: script-agnostic structure recognition in tables. In: International conference on document analysis and recognition, Cham, Switzerland, pp. 350\u2013367 (2024). Springer","DOI":"10.1007\/978-3-031-70549-6_21"},{"key":"2276_CR30","doi-asserted-by":"crossref","unstructured":"Lysak, M., Nassar, A., Livathinos, N., Auer, C., Staar, P.: Optimized table tokenization for table structure recognition. In: International conference on document analysis and recognition, Cham, Switzerland, pp. 37\u201350 (2023). Springer","DOI":"10.1007\/978-3-031-41679-8_3"},{"key":"2276_CR31","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Polosukhin, I.: Attention is all you need. In: NeurIPS, pp. 5998\u20136008 (2017)"},{"key":"2276_CR32","unstructured":"Gu, A., Dao, T.: Mamba: linear-time sequence modeling with selective state spaces (2023)"},{"key":"2276_CR33","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2276_CR34","doi-asserted-by":"crossref","unstructured":"Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., Zettlemoyer, L.: Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp. 7871\u20137880 (2020)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"2276_CR35","doi-asserted-by":"crossref","unstructured":"Smock, B., Pesala, R., Abraham, R.: Pubtables-1m: towards comprehensive table extraction from unstructured documents. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 4634\u20134642 (2022)","DOI":"10.1109\/CVPR52688.2022.00459"},{"key":"2276_CR36","unstructured":"Peng, S., Lee, S., Wang, X., Balasubramaniyan, R., Chau, D.H.: Unitable: Towards a unified framework for table structure recognition via self-supervised pretraining. arXiv preprint arXiv:2403.04822 (2024)"},{"key":"2276_CR37","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., Wang, X.: Vision Mamba: efficient visual representation learning with bidirectional state space model (2024)"},{"key":"2276_CR38","doi-asserted-by":"crossref","unstructured":"Pei, X., Huang, T., Xu, C.: EfficientVMamba: Atrous selective scan for lightweight visual Mamba (2024)","DOI":"10.1609\/aaai.v39i6.32690"},{"key":"2276_CR39","unstructured":"Liu, Y., Tian, Y., Zhao, Y., Yu, H., Xie, L., Wang, Y., Ye, Q., Liu, Y.: VMamba: visual state space model (2024)"},{"key":"2276_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107980","volume":"117","author":"N Lu","year":"2021","unstructured":"Lu, N., Yu, W., Qi, X., Chen, Y., Gong, P., Xiao, R., Bai, X.: Master: multi-aspect non-local network for scene text recognition. Pattern Recogn. 117, 107980 (2021)","journal-title":"Pattern Recogn."},{"key":"2276_CR41","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Hou, W., Lu, T., Yu, G., Shao, S.: Shape robust text detection with progressive scale expansion network. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 9336\u20139345 (2019)","DOI":"10.1109\/CVPR.2019.00956"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02276-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02276-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02276-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:12:35Z","timestamp":1778047955000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02276-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,6]]},"references-count":41,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["2276"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02276-z","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,6]]},"assertion":[{"value":"10 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 May 2026","order":3,"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 no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"290"}}