{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T21:55:24Z","timestamp":1777758924576,"version":"3.51.4"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"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":["Vis Comput"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s00371-026-04459-1","type":"journal-article","created":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:55:36Z","timestamp":1775667336000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A financial table structure recognition method based on transformer with attention enhancement"],"prefix":"10.1007","volume":"42","author":[{"given":"Pengle","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuanzhe","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Ni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoli","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanghang","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,8]]},"reference":[{"key":"4459_CR1","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. IEEE (1993)"},{"issue":"7","key":"4459_CR2","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":"4459_CR3","unstructured":"Ye, J., Qi, X., He, Y., et al.: PingAn-VCGroup\u2019s solution for ICDAR 2021 competition on scientific literature parsing task B: table recognition to HTML. arXiv:2105.01848 (2021)"},{"key":"4459_CR4","doi-asserted-by":"crossref","unstructured":"Nassar, A., Livathinos, N., Lysak, M., et al.: Tableformer: Table structure understanding with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4614\u20134623 (2022)","DOI":"10.1109\/CVPR52688.2022.00457"},{"key":"4459_CR5","doi-asserted-by":"crossref","unstructured":"Xing, H., Gao, F., Long, R., et al.: LORE: logical location regression network for table structure recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence 37(3), 2992\u20133000 (2023)","DOI":"10.1609\/aaai.v37i3.25402"},{"key":"4459_CR6","doi-asserted-by":"crossref","unstructured":"Zheng, X., Burdick, D., Popa, L., et al.: 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":"4459_CR7","unstructured":"Peng, S.Y., Lee, S., Wang, X., et al.: Self-Supervised Pre-Training for Table Structure Recognition Transformer. arXiv:2402.15578 (2024)"},{"key":"4459_CR8","unstructured":"Peng, S.Y., Lee, S., Wang, X., et al.: UniTable: Towards a Unified Framework for Table Structure Recognition via Self-Supervised Pretraining. arXiv:2403.04822 (2024)"},{"key":"4459_CR9","unstructured":"Peng, S.Y., Lee, S., Wang, X., et al.: High-performance transformers for table structure recognition need early convolutions. arXiv:2311.05565 (2023)"},{"key":"4459_CR10","doi-asserted-by":"crossref","unstructured":"Zhu, Q., Li, H., He, L., et al.: SwinMamba: A hybrid local\u2013global mamba framework for enhancing semantic segmentation of remotely sensed images. Digital Signal Process. 106029 (2026)","DOI":"10.1016\/j.dsp.2026.106029"},{"key":"4459_CR11","first-page":"1","volume":"62","author":"T Chen","year":"2024","unstructured":"Chen, T., Ye, Z., Tan, Z., et al.: MiM-ISTD: Mamba-in-mamba for efficient infrared small-target detection. IEEE Trans. Geosci. Remote Sens. 62, 1\u201313 (2024)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"4459_CR12","unstructured":"Gu, A., Dao, T.: Mamba: Linear-time sequence modeling with selective state spaces. arXiv:2312.00752 (2023)"},{"key":"4459_CR13","unstructured":"Li, C., Guo, R., Zhou, J., et al.: Pp-structurev2: a stronger document analysis system. arXiv:2210.05391 (2022)"},{"key":"4459_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110279","volume":"149","author":"Z Zhang","year":"2024","unstructured":"Zhang, Z., Hu, P., Ma, J., et al.: SEMv2: Table separation line detection based on instance segmentation. Pattern Recogn. 149, 110279 (2024)","journal-title":"Pattern Recogn."},{"issue":"4","key":"4459_CR15","doi-asserted-by":"publisher","first-page":"2817","DOI":"10.1007\/s00371-024-03570-5","volume":"41","author":"SG Ali","year":"2024","unstructured":"Ali, S.G., Wang, X., Li, P., Li, H., Yang, P., Jung, Y., Qin, J., Kim, J., Sheng, B.: Egdnet: an efficient glomerular detection network for multiple anomalous pathological feature in glomerulonephritis. Vis. Comput. 41(4), 2817\u201334 (2024)","journal-title":"Vis. Comput."},{"issue":"3","key":"4459_CR16","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1007\/s41666-024-00167-4","volume":"8","author":"R Liu","year":"2024","unstructured":"Liu, R., Li, J., Wen, Y., Li, H., Zhang, P., Sheng, B., Feng, D.D.: DDE: deep dynamic epidemiological modeling for infectious illness development forecasting in multi-level geographic entities. J. Healthcare Inform. Res. 8(3), 478\u2013505 (2024)","journal-title":"J. Healthcare Inform. Res."},{"key":"4459_CR17","doi-asserted-by":"crossref","unstructured":"Qian, B., Chen, H., Wang, X., Guan, Z., Li, T., Jin, Y., Sheng, B.: DRAC 2022: A public benchmark for diabetic retinopathy analysis on ultra-wide optical coherence tomography angiography images. Patterns 5(3) (2024)","DOI":"10.1016\/j.patter.2024.100929"},{"key":"4459_CR18","doi-asserted-by":"crossref","unstructured":"Li, J., Zhang, P., Wang, T., Zhu, L., Liu, R., Yang, X., Sheng, B.: Dsmt-net: Dual self-supervised multi-operator transformation for multi-source endoscopic ultrasound diagnosis. IEEE Trans. Med. Imaging 43(1), 64\u201375 (2023)","DOI":"10.1109\/TMI.2023.3289859"},{"key":"4459_CR19","doi-asserted-by":"crossref","unstructured":"Liu, R., Wang, T., Li, H., Zhang, P., Li, J., Yang, X., Sheng, B.: TMM-Nets: transferred multi-to mono-modal generation for lupus retinopathy diagnosis. IEEE Trans. Med. Imaging 42(4), 1083\u20131094 (2022)","DOI":"10.1109\/TMI.2022.3223683"},{"key":"4459_CR20","doi-asserted-by":"publisher","first-page":"35105","DOI":"10.1007\/s11042-020-09303-9","volume":"80","author":"SG Ali","year":"2021","unstructured":"Ali, S.G., Chen, Y., Sheng, B., et al.: Cost-effective broad learning-based ultrasound biomicroscopy with 3D reconstruction for ocular anterior segmentation. Multimedia Tools Appl. 80, 35105\u201335122 (2021)","journal-title":"Multimedia Tools Appl."},{"key":"4459_CR21","doi-asserted-by":"publisher","first-page":"70969","DOI":"10.1109\/ACCESS.2020.2987177","volume":"8","author":"A Karambakhsh","year":"2020","unstructured":"Karambakhsh, A., Sheng, B., Li, P., et al.: VoxRec: hybrid convolutional neural network for active 3D object recognition. IEEE Access 8, 70969\u201370980 (2020)","journal-title":"IEEE Access"},{"key":"4459_CR22","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":"4459_CR23","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., et al.: End-to-end object detection with transformers. In: European conference on computer vision, pp. 213\u2013229. Springer, Cham (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"4459_CR24","doi-asserted-by":"crossref","unstructured":"Qiao, L., Li, Z., Cheng, Z., et al.: Lgpma: Complicated table structure recognition with local and global pyramid mask alignment. In: International Conference on Document Analysis and Recognition, pp. 99\u2013114. Springer, Cham (2021)","DOI":"10.1007\/978-3-030-86549-8_7"},{"key":"4459_CR25","doi-asserted-by":"crossref","unstructured":"Xue, W., Yu, B., Wang, W., et al.: 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)","DOI":"10.1109\/ICCV48922.2021.00133"},{"key":"4459_CR26","doi-asserted-by":"crossref","unstructured":"Zhong, X., ShafieiBavani, E., Jimeno Yepes, A.: Image-based table recognition: data, model, and evaluation. In: European Conference on Computer Vision, pp. 564\u2013580. Springer, Cham (2020)","DOI":"10.1007\/978-3-030-58589-1_34"},{"key":"4459_CR27","doi-asserted-by":"crossref","unstructured":"Lysak, M., Nassar, A., Livathinos, N., et al.: Optimized table tokenization for table structure recognition. In: International Conference on Document Analysis and Recognition, pp. 37\u201350. Springer, Cham (2023)","DOI":"10.1007\/978-3-031-41679-8_3"},{"key":"4459_CR28","doi-asserted-by":"crossref","unstructured":"Huang, Y., Lu, N., Chen, D., et al.: 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":"4459_CR29","doi-asserted-by":"crossref","unstructured":"Wan, J., Song, S., Yu, W., et al.: OmniParser: a unified framework for text spotting key information extraction and table recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15641\u201315653 (2024)","DOI":"10.1109\/CVPR52733.2024.01481"},{"key":"4459_CR30","doi-asserted-by":"crossref","unstructured":"Ly, N.T., Takasu, A.: An end-to-end multi-task learning model for image-based table recognition. arXiv:2303.08648 (2023)","DOI":"10.5220\/0011685000003417"},{"key":"4459_CR31","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, pp. 20\u201336. Springer, Cham (2023)","DOI":"10.1007\/978-3-031-41679-8_2"},{"key":"4459_CR32","doi-asserted-by":"crossref","unstructured":"Kawakatsu, T.: Multi-cell decoder and mutual learning for table structure and character recognition. In: International Conference on Document Analysis and Recognition, pp. 389\u2013405. Springer, Cham (2024)","DOI":"10.1007\/978-3-031-70533-5_23"},{"issue":"2","key":"4459_CR33","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1007\/s00371-024-03386-3","volume":"41","author":"Y Zhou","year":"2025","unstructured":"Zhou, Y., Chen, X., Li, T., Lin, S., Sheng, B., Liu, R., Dai, R.: GAMNet: a gated attention mechanism network for grading myopic traction maculopathy in OCT images. Vis. Comput. 41(2), 1097\u20131108 (2025)","journal-title":"Vis. Comput."},{"key":"4459_CR34","doi-asserted-by":"crossref","unstructured":"Qian, B., Chen, H., Xu, Y., Wen, Y., Li, H., Xie, Y., Sheng, B.: Deep contour attention learning for scleral deformation from OCT images. Vis. Comput. 41(2), 1155\u20131170 (2025)","DOI":"10.1007\/s00371-024-03401-7"},{"issue":"20","key":"4459_CR35","doi-asserted-by":"publisher","first-page":"12589","DOI":"10.1007\/s00521-024-09785-w","volume":"36","author":"X Yu","year":"2024","unstructured":"Yu, X., Dai, L., Chen, Z., Sheng, B.: AGG: attention-based gated convolutional GAN with prior guidance for image inpainting. Neural Comput. Appl. 36(20), 12589\u201312604 (2024)","journal-title":"Neural Comput. Appl."},{"key":"4459_CR36","doi-asserted-by":"crossref","unstructured":"Li, L., Chen, Z., Dai, L., Li, R., Sheng, B.: Ma-mfcnet: Mixed attention-based multi-scale feature calibration network for image dehazing. IEEE Trans. Emerging Top. Comput. Intell. (2024)","DOI":"10.1109\/TETCI.2024.3382233"},{"issue":"10","key":"4459_CR37","doi-asserted-by":"publisher","first-page":"7719","DOI":"10.1109\/TNNLS.2022.3146004","volume":"34","author":"Y Zhou","year":"2022","unstructured":"Zhou, Y., Chen, Z., Li, P., Song, H., Chen, C.P., Sheng, B.: FSAD-Net: feedback spatial attention dehazing network. IEEE Trans. Neural Netw. Learn. Syst. 34(10), 7719\u20137733 (2022)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"4459_CR38","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. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00148"},{"key":"4459_CR39","unstructured":"Bao, H., Dong, L., Piao, S., et al.: Beit: Bert pre-training of image transformers. arXiv:2106.08254 (2021)"},{"key":"4459_CR40","doi-asserted-by":"publisher","first-page":"1366","DOI":"10.1109\/TMM.2021.3063916","volume":"24","author":"C Mou","year":"2021","unstructured":"Mou, C., Zhang, J., Fan, X., et al.: COLA-Net: Collaborative attention network for image restoration. IEEE Trans. Multimedia 24, 1366\u20131377 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"4459_CR41","doi-asserted-by":"crossref","unstructured":"Tu, Z., Talebi, H., Zhang, H., et al.: Maxvit: Multi-axis vision transformer. In: European Conference on Computer Vision, pp. 459\u2013479. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"4459_CR42","first-page":"9355","volume":"34","author":"X Chu","year":"2021","unstructured":"Chu, X., Tian, Z., Wang, Y., et al.: Twins: Revisiting the design of spatial attention in vision transformers. Adv. Neural. Inf. Process. Syst. 34, 9355\u20139366 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4459_CR43","doi-asserted-by":"crossref","unstructured":"Kalman, R.E.: A new approach to linear filtering and prediction problems (1960)","DOI":"10.1115\/1.3662552"},{"key":"4459_CR44","unstructured":"Gu, A., Goel, K., R\u00e9, C.: Efficiently modeling long sequences with structured state spaces. arXiv:2111.00396 (2021)"},{"key":"4459_CR45","unstructured":"Liu, X., Zhang, C., Zhang, L.: Vision mamba: a comprehensive survey and taxonomy. arXiv:2405.04404 (2024)"},{"key":"4459_CR46","first-page":"103031","volume":"37","author":"Y Liu","year":"2025","unstructured":"Liu, Y., Tian, Y., Zhao, Y., et al.: Vmamba: Visual state space model. Adv. Neural. Inf. Process. Syst. 37, 103031\u2013103063 (2025)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4459_CR47","unstructured":"Lieber, O., Lenz, B., Bata, H., et al.: Jamba: A hybrid transformer-mamba language model. arXiv:2403.19887 (2024)"},{"key":"4459_CR48","unstructured":"Ma, J., Li, F., Wang, B.: U-mamba: Enhancing long-range dependency for biomedical image segmentation. arXiv:2401.04722 (2024)"},{"key":"4459_CR49","doi-asserted-by":"crossref","unstructured":"Lin T.Y., Maire, M., Belongie, S., et al.: Microsoft coco: Common objects in context. In: Computer vision\u2013ECCV 2014: 13th European conference, Zurich, Switzerland, September 6\u201312, 2014, Proceedings, part v 13, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-026-04459-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-026-04459-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-026-04459-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T13:16:11Z","timestamp":1777468571000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-026-04459-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":49,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["4459"],"URL":"https:\/\/doi.org\/10.1007\/s00371-026-04459-1","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"24 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 April 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":"245"}}