Elamur Research
☰
home / papers / 2021 / OCR-free Document Understanding Transformer

OCR-free Document Understanding Transformer

Written for the Research library (claude-opus-5-5) from the paper text, in our own words: the license "arXiv — non-exclusive license to distribute" does not allow redistributing the text itself. Original — arxiv.org/pdf/2111.15664

Summary

Most Visual Document Understanding (VDU) systems for document classification, field extraction from receipts or invoices, and question answering over pages first run an external OCR engine and then model the recognized text. The authors identify three problems with this design: OCR is expensive at inference, it adapts poorly to new languages and document types, and its recognition mistakes carry into later steps. They propose Donut, an end-to-end Transformer that works directly on pixels. A Swin Transformer encoder turns the image into embeddings, and a BART decoder, initialized from a multilingual checkpoint, emits tokens that convert losslessly into JSON. Pre-training is a pseudo-OCR task: the model predicts page text in reading order under a cross-entropy loss. The training data combine real scans from IIT-CDIP with synthetic pages from the authors' generator, SynthDoG. During fine-tuning, task-specific prompt tokens switch the decoder to the target task. Donut matches or beats OCR-dependent models while running faster with less memory, and it stays strong with few labeled examples. Its synthetic-data approach is especially useful for languages that lack good OCR.

Key points

  • Architecture: a Swin Transformer visual encoder feeds a BART text decoder initialized from a multilingual BART model (asian-bart-ecjk). No OCR component is used anywhere in the pipeline.
  • Pre-training data:
    • About 11M English scans from IIT-CDIP, with pseudo text labels produced by the commercial CLOVA OCR API.
    • 0.5M SynthDoG images per language, rendered from Chinese, Japanese, Korean and English Wikipedia.
  • Output format: every target field is enclosed in its own start and end tokens, so simple regular expressions can turn the output into JSON. A field with malformed tags is treated as missing.
  • Low-resource results on CORD: trained on only 80 samples (about 10% of the training set), Donut already surpassed LayoutLMv2. The larger 2560×1920 input resolution was more robust in this setting. The OCR-based baselines' speed and accuracy changed substantially depending on which of four engines was used (EasyOCR, PaddleOCR, MS Azure, CLOVA OCR).
  • Additional findings and release: decoder cross-attention maps locate text regions even though the model was never trained for localization. Code, trained models and synthetic data are available at github.com/clovaai/donut.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Other

Cited by

149 papers of our library cite it (of the 140673 whose bibliographies we read); 7 of them have a page here, 142 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2111.15664 · arXiv 2111.15664

@misc{kim2021ocr,
  title = {{OCR-free Document Understanding Transformer}},
  author = {Kim, Geewook and Hong, Teakgyu and Yim, Moonbin and Nam, Jeongyeon and Park, Jinyoung and Yim, Jinyeong and Hwang, Wonseok and Yun, Sangdoo and Han, Dongyoon and Park, Seunghyun},
  year = {2021},
  doi = {10.48550/arxiv.2111.15664},
  eprint = {2111.15664},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2111.15664}
}

References

70 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Afzal, M.Z., Capobianco, S., Malik, M.I., Marinai, S., Breuel, T.M., Dengel, A., Liwicki, M.: Deepdocclassifier: Document classification with deep convolutional neural network. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR). pp. 1111–1115 (2015). https://doi.org/… — [doi:10.1109/icdar.2015.7333933](https://doi.org/10.1109/icdar.2015.7333933) find
  2. Appalaraju, S., Jasani, B., Kota, B.U., Xie, Y., Manmatha, R.: Docformer: End-to-end transformer for document understanding. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). pp. 993–1003 (October 2021) 14 find
  3. Baek, J., Kim, G., Lee, J., Park, S., Han, D., Yun, S., Oh, S.J., Lee, H.: What is wrong with scene text recognition model comparisons? dataset and model analysis. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (October 2019) 2, 4, 9, 13, 22 find
  4. Baek, Y., Lee, B., Han, D., Yun, S., Lee, H.: Character region awareness for text detection. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 9357–9366 (2019). https://doi.org/10.1109/CVPR.2019.00959 2, 4, 9, 13, 22 — [doi:10.1109/cvpr.2019.00959](https://doi.org/10.1109/cvpr.2019.00959) ↗
  5. Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D., Wu, J., Winter, C., Hesse, C., Chen, M., Sigler, E., Litwin, M., Gray, S., Chess,… find
  6. Davis, B., Morse, B., Cohen, S., Price, B., Tensmeyer, C.: Deep visual template-free form parsing. In: 2019 International Conference on Document Analysis and Recognition (ICDAR). pp. 134–141 (2019). https://doi.org/10.1109/ICDAR.2019.00030 3 — [doi:10.1109/icdar.2019.00030](https://doi.org/10.1109/icdar.2019.00030) ↗
  7. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. pp. 248–255. Ieee (2009) 6, 12, 23 find
  8. Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Sh… find
  9. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: Transformers for image recognition at scale. In: 9th International Conference on Learning Representat… find
  10. Duong, Q., Hämäläinen, M., Hengchen, S.: An unsupervised method for OCR post-correction and spelling normalisation for Finnish. In: Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa). pp. 240–248. Linköping University Electronic Press, Sweden, Reykjavik, Iceland (O… find
  11. Friedl, J.E.F.: Mastering Regular Expressions. O’Reilly, Beijing, 3 edn. (2006), https://www.safaribooksonline.com/library/view/mastering-regular-expressions/0596528124/ 5 ↗
  12. Guo, H., Qin, X., Liu, J., Han, J., Liu, J., Ding, E.: Eaten: Entity-aware attention for single shot visual text extraction. In: 2019 International Conference on Document Analysis and Recognition (ICDAR). pp. 254–259 (2019). https://doi.org/10.1109/ICDAR.2019.00049 4, 8, 10, 22, 24, 25, 26 — [doi:10.1109/icdar.2019.00049](https://doi.org/10.1109/icdar.2019.00049) ↗
  13. Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (June 2016) 6, 13 find
  14. Hammami, M., Héroux, P., Adam, S., d’Andecy, V.P.: One-shot field spotting on colored forms using subgraph isomorphism. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR). pp. 586–590 (2015). https://doi.org/10.1109/ICDAR.2015.7333829 3 — [doi:10.1109/icdar.2015.7333829](https://doi.org/10.1109/icdar.2015.7333829) ↗
  15. Harley, A.W., Ufkes, A., Derpanis, K.G.: Evaluation of deep convolutional nets for document image classification and retrieval. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR). pp. 991–995 (2015). https://doi.org/10.1109/ICDAR.2015.7333910 4, 14 — [doi:10.1109/icdar.2015.7333910](https://doi.org/10.1109/icdar.2015.7333910) ↗
  16. Harley, A.W., Ufkes, A., Derpanis, K.G.: Evaluation of deep convolutional nets for document image classification and retrieval. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR). pp. 991–995 (2015). https://doi.org/10.1109/ICDAR.2015.7333910 6 — [doi:10.1109/icdar.2015.7333910](https://doi.org/10.1109/icdar.2015.7333910) ↗
  17. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 770–778 (2016). https://doi.org/10.1109/CVPR.2016.90 4 ↗
  18. Hong, T., Kim, D., Ji, M., Hwang, W., Nam, D., Park, S.: Bros: A pre-trained language model focusing on text and layout for better key information extraction from documents. Proceedings of the AAAI Conference on Artificial Intelligence 36(10), 10767–10775 (Jun 2022). https://doi.org/10.1609/aaai.v36… — [doi:10.1609/aaai.v36i10.21322](https://doi.org/10.1609/aaai.v36i10.21322) ↗
  19. Huang, W., Qiao, Y., Tang, X.: Robust scene text detection with convolution neural network induced mser trees. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) Computer Vision – ECCV 2014. pp. 497–511. Springer International Publishing, Cham (2014) 13 find
  20. Huang, Z., Chen, K., He, J., Bai, X., Karatzas, D., Lu, S., Jawahar, C.V.: Icdar2019 competition on scanned receipt ocr and information extraction. In: 2019 International Conference on Document Analysis and Recognition (ICDAR). pp. 1516–1520 (2019). https://doi.org/10.1109/ICDAR.2019.00244 3 — [doi:10.1109/icdar.2019.00244](https://doi.org/10.1109/icdar.2019.00244) ↗
  21. Hwang, A., Frey, W.R., McKeown, K.: Towards augmenting lexical resources for slang and African American English. In: Proceedings of the 7th Workshop on NLP for Similar Languages, Varieties and Dialects. pp. 160–172. International Committee on Computational Linguistics (ICCL), Barcelona, Spain (Onlin… find
  22. Hwang, W., Kim, S., Yim, J., Seo, M., Park, S., Park, S., Lee, J., Lee, B., Lee, H.: Post-ocr parsing: building simple and robust parser via bio tagging. In: Workshop on Document Intelligence at NeurIPS 2019 (2019) 1, 2, 4, 7, 9, 10, 14, 28, 29 find
  23. Hwang, W., Lee, H., Yim, J., Kim, G., Seo, M.: Cost-effective end-to-end information extraction for semi-structured document images. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. pp. 3375– 3383. Association for Computational Linguistics, Online and Punta… find
  24. Hwang, W., Yim, J., Park, S., Yang, S., Seo, M.: Spatial dependency parsing for semi-structured document information extraction. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. pp. 330–343. Association for Computational Linguistics, Online (Aug 2021). https://doi.org/… find
  25. Hwang, W., Yim, J., Park, S., Yang, S., Seo, M.: Spatial dependency parsing for semi-structured document information extraction. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. pp. 330–343. Association for Computational Linguistics, Online (Aug 2021). https://doi.org/… find
  26. Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. In: Workshop on Deep Learning, NIPS (2014) 13 find
  27. Kang, L., Kumar, J., Ye, P., Li, Y., Doermann, D.S.: Convolutional neural networks for document image classification. 2014 22nd International Conference on Pattern Recognition pp. 3168–3172 (2014) 1, 4, 14 find
  28. Karatzas, D., Gomez-Bigorda, L., Nicolaou, A., Ghosh, S., Bagdanov, A., Iwamura, M., Matas, J., Neumann, L., Chandrasekhar, V.R., Lu, S., Shafait, F., Uchida, S., Valveny, E.: Icdar 2015 competition on robust reading. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR… — [doi:10.1109/icdar.2015.7333942](https://doi.org/10.1109/icdar.2015.7333942) find
  29. Kim, W., Son, B., Kim, I.: Vilt: Vision-and-language transformer without convolution or region supervision. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 139, pp. 5583–5594. PMLR (18–24 Jul 2021),… find our card
  30. Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings (2015), http://arxiv.org/abs/1412.6980 8, 25 ↗
  31. Klaiman, S., Lehne, M.: Docreader: Bounding-box free training of a document information extraction model. In: Document Analysis and Recognition – IC-DAR 2021: 16th International Conference, Lausanne, Switzerland, September 5–10, 2021, Proceedings, Part I. p. 451–465. Springer-Verlag, Berlin, Heidelb… — [doi:10.1007/978-3-030-86549-8](https://doi.org/10.1007/978-3-030-86549-8) find
  32. Lewis, D., Agam, G., Argamon, S., Frieder, O., Grossman, D., Heard, J.: Building a test collection for complex document information processing. In: Proceedings of the 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. p. 665–666. SIGIR ’06, Associati… — [doi:10.1145/1148170.1148307](https://doi.org/10.1145/1148170.1148307) find
  33. 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 L… find our card
  34. Li, C., Bi, B., Yan, M., Wang, W., Huang, S., Huang, F., Si, L.: StructuralLM: Structural pre-training for form understanding. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volum… find
  35. Li, P., Gu, J., Kuen, J., Morariu, V.I., Zhao, H., Jain, R., Manjunatha, V., Liu, H.: Selfdoc: Self-supervised document representation learning. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 5648–5656 (2021). https://doi.org/10.1109/CVPR46437.2021.00560 14 — [doi:10.1109/cvpr46437.2021.00560](https://doi.org/10.1109/cvpr46437.2021.00560) ↗
  36. Liao, M., Shi, B., Bai, X., Wang, X., Liu, W.: Textboxes: A fast text detector with a single deep neural network. Proceedings of the AAAI Conference on Artificial Intelligence 31(1) (Feb 2017). https://doi.org/10.1609/aaai.v31i1.11196, https: //ojs.aaai.org/index.php/AAAI/article/view/11196 13 — [doi:10.1609/aaai.v31i1.11196](https://doi.org/10.1609/aaai.v31i1.11196) ↗
  37. Liu, W., Chen, C., Wong, K.Y.K., Su, Z., Han, J.: Star-net: A spatial attention residue network for scene text recognition. In: Richard C. Wilson, E.R.H., Smith, W.A.P. (eds.) Proceedings of the British Machine Vision Conference (BMVC). pp. 43.1–43.13. BMVA Press (September 2016). https://doi.org/10… — [doi:10.5244/c.30.43](https://doi.org/10.5244/c.30.43) find
  38. Liu, Y., Gu, J., Goyal, N., Li, X., Edunov, S., Ghazvininejad, M., Lewis, M., Zettlemoyer, L.: Multilingual denoising pre-training for neural machine translation. Transactions of the Association for Computational Linguistics 8, 726–742 (2020), https://aclanthology.org/2020.tacl-1.47 5 ↗
  39. Liu, Y., Chen, H., Shen, C., He, T., Jin, L., Wang, L.: Abcnet: Real-time scene text spotting with adaptive bezier-curve network. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (June 2020) 2 find
  40. 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 (ICCV). pp. 10012– 10022 (October 2021) 4, 8, 12 find our card
  41. Long, S., Yao, C.: Unrealtext: Synthesizing realistic scene text images from the unreal world. arXiv preprint arXiv:2003.10608 (2020) 6 — [arXiv:2003.10608](https://arxiv.org/abs/2003.10608) find
  42. Majumder, B.P., Potti, N., Tata, S., Wendt, J.B., Zhao, Q., Najork, M.: Representation learning for information extraction from form-like documents. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. pp. 6495–6504. Association for Computational Linguistics,… find
  43. Majumder, B.P., Potti, N., Tata, S., Wendt, J.B., Zhao, Q., Najork, M.: Representation learning for information extraction from form-like documents. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. pp. 6495–6504. Association for Computational Linguistics,… find
  44. Mathew, M., Karatzas, D., Jawahar, C.: Docvqa: A dataset for vqa on document images. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. pp. 2200–2209 (2021) 1, 8, 12, 14 find our card
  45. Park, S., Shin, S., Lee, B., Lee, J., Surh, J., Seo, M., Lee, H.: Cord: A consolidated receipt dataset for post-ocr parsing. In: Workshop on Document Intelligence at NeurIPS 2019 (2019) 2, 7, 10, 12, 13, 22, 24, 26 find
  46. Peng, D., Wang, X., Liu, Y., Zhang, J., Huang, M., Lai, S., Zhu, S., Li, J., Lin, D., Shen, C., Jin, L.: SPTS: Single-Point Text Spotting. CoRR abs/2112.07917 (2021), https://arxiv.org/abs/2112.07917 2 — [arXiv:2112.07917](https://arxiv.org/abs/2112.07917) ↗
  47. Phan, T.Q., Shivakumara, P., Tian, S., Tan, C.L.: Recognizing text with perspective distortion in natural scenes. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (December 2013) 13 find
  48. Powalski, R., Borchmann, L., Jurkiewicz, D., Dwojak, T., Pietruszka, M., Pa lka, G.: Going full-tilt boogie on document understanding with text-image-layout transformer. In: Lladós, J., Lopresti, D., Uchida, S. (eds.) Document Analysis and Recognition – ICDAR 2021. pp. 732–747. Springer Internation… find
  49. Riba, P., Dutta, A., Goldmann, L., Fornés, A., Ramos, O., Lladós, J.: Table detection in invoice documents by graph neural networks. In: 2019 International Conference on Document Analysis and Recognition (ICDAR). pp. 122–127 (2019). https://doi.org/10.1109/ICDAR.2019.00028 3 — [doi:10.1109/icdar.2019.00028](https://doi.org/10.1109/icdar.2019.00028) ↗
  50. Rijhwani, S., Anastasopoulos, A., Neubig, G.: OCR Post Correction for Endangered Language Texts. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). pp. 5931–5942. Association for Computational Linguistics, Online (Nov 2020). https://doi.org/10.18653/v… find
  51. Schaefer, R., Neudecker, C.: A two-step approach for automatic OCR post-correction. In: Proceedings of the The 4th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature. pp. 52–57. International Committee on Computational Linguistics, On… find
  52. Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 39, 2298–2304 (2017) 13 find
  53. Shi, B., Wang, X., Lyu, P., Yao, C., Bai, X.: Robust scene text recognition with automatic rectification. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 4168–4176 (2016). https://doi.org/10.1109/CVPR.2016.452 13 — [doi:10.1109/cvpr.2016.452](https://doi.org/10.1109/cvpr.2016.452) ↗
  54. Taghva, K., Beckley, R., Coombs, J.: The effects of ocr error on the extraction of private information. In: Bunke, H., Spitz, A.L. (eds.) Document Analysis Systems VII. pp. 348–357. Springer Berlin Heidelberg, Berlin, Heidelberg (2006) 2 find
  55. Tan, M., Le, Q.: Efficientnetv2: Smaller models and faster training. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 139, pp. 10096–10106. PMLR (18–24 Jul 2021), https://proceedings.mlr.press/v139/ta… ↗
  56. Tian, Z., Huang, W., He, T., He, P., Qiao, Y.: Detecting text in natural image with connectionist text proposal network. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) Computer Vision – ECCV 2016. pp. 56–72. Springer International Publishing, Cham (2016) 13 find
  57. Tito, R., Mathew, M., Jawahar, C.V., Valveny, E., Karatzas, D.: Icdar 2021 competition on document visual question answering. In: Lladós, J., Lopresti, D., Uchida, S. (eds.) Document Analysis and Recognition – ICDAR 2021. pp. 635–649. Springer International Publishing, Cham (2021) 1, 14 find
  58. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L.u., Polosukhin, I.: Attention is all you need. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) Advances in Neural Information Processing Systems. vol. 30. Cu… find
  59. Wang, J., Hu, X.: Gated recurrent convolution neural network for ocr. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) Advances in Neural Information Processing Systems. vol. 30. Curran Associates, Inc. (2017), https://proceedings.neurips.cc/pap… ↗
  60. Wang, S., Li, B., Khabsa, M., Fang, H., Ma, H.: Linformer: Self-attention with linear complexity. arXiv preprint arXiv:2006.04768 (2020) 12, 27 find
  61. Wightman, R.: Pytorch image models. https://github.com/rwightman/pytorch-image-models (2019). https://doi.org/10.5281/zenodo.4414861 25 — [doi:10.5281/zenodo.4414861](https://doi.org/10.5281/zenodo.4414861) ↗
  62. Williams, R.J., Zipser, D.: A learning algorithm for continually running fully recurrent neural networks. Neural computation 1(2), 270–280 (1989) 5 find
  63. Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., Davison, J., Shleifer, S., von Platen, P., Ma, C., Jernite, Y., Plu, J., Xu, C., Le Scao, T., Gugger, S., Drame, M., Lhoest, Q., Rush, A.: Transformers: State-of-the-art natural langua… find our card
  64. Xu, Y., Xu, Y., Lv, T., Cui, L., Wei, F., Wang, G., Lu, Y., Florencio, D., Zhang, C., Che, W., Zhang, M., Zhou, L.: LayoutLMv2: Multi-modal pre-training for visually-rich document understanding. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th… find our card
  65. Xu, Y., Li, M., Cui, L., Huang, S., Wei, F., Zhou, M.: Layoutlm: Pre-training of text and layout for document image understanding. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. p. 1192–1200. KDD ’20, Association for Computing Machinery, New Yor… find our card
  66. Xu, Y., Lv, T., Cui, L., Wang, G., Lu, Y., Florencio, D., Zhang, C., Wei, F.: Layoutxlm: Multimodal pre-training for multilingual visually-rich document understanding. arXiv preprint arXiv:2104.08836 (2021) 10, 27 — [arXiv:2104.08836](https://arxiv.org/abs/2104.08836) find
  67. Yim, M., Kim, Y., Cho, H.C., Park, S.: Synthtiger: Synthetic text image generator towards better text recognition models. In: Lladós, J., Lopresti, D., Uchida, S. (eds.) Document Analysis and Recognition – ICDAR 2021. pp. 109–124. Springer International Publishing, Cham (2021) 5, 6, 23 find
  68. Zhang, K., Shasha, D.: Simple fast algorithms for the editing distance between trees and related problems. SIAM J. Comput. 18, 1245–1262 (12 1989). https://doi.org/10.1137/0218082 7 ↗
  69. Zhang, Z., Zhang, C., Shen, W., Yao, C., Liu, W., Bai, X.: Multi-oriented text detection with fully convolutional networks. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 4159–4167 (2016). https://doi.org/10.1109/CVPR.2016.451 13 — [doi:10.1109/cvpr.2016.451](https://doi.org/10.1109/cvpr.2016.451) ↗
  70. Zhong, X., ShafieiBavani, E., Jimeno Yepes, A.: Image-based table recognition: Data, model, and evaluation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) Computer Vision – ECCV 2020. pp. 564–580. Springer International Publishing, Cham (2020) 7 find