Elamur Research⌕
☰
home / papers / 2025 / KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding

KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding

Paper · 2025 · Ahmed Heakl, Muhammad Abdullah Sohail, Mukul Ranjan et al.

Summary

Arabic OCR trails English OCR. The script is cursive and written right to left, and its typography is rich. Existing Arabic datasets mostly cover isolated handwriting or printed lines, not full document understanding. KITAB-Bench fills this gap with 8,809 evaluation samples spread over 9 major tasks and 36 sub-domains. The tasks are PDF-to-Markdown, layout detection, line detection and recognition, table recognition, image-to-text, chart-to-DataFrame, diagram-to-JSON, and VQA. The data combines existing Arabic datasets, manually gathered and annotated PDFs, and extra material produced by a five-phase pipeline in which an LLM generates and humans check. The authors also introduce two structure-aware metrics: CharTeX for charts and CODM for diagrams. They then evaluate classic OCR engines and vision-language models. VLMs such as Gemini, GPT-4o and Qwen beat traditional tools like EasyOCR, PaddleOCR and Surya by about 60% in CER on average. Even so, end-to-end PDF-to-Markdown remains weak, with the best system reaching about 65%. The benchmark gives Arabic document processing a shared, multi-task yardstick.

Key points

  • Sample counts per task: Image to Text 3,760, Layout 2,100, VQA 902, Charts to DataFrame 576, Table Recognition 456, Line Detection and Line Recognition 378 each, Diagram to JSON 226, PDF to Markdown 33.
  • On text recognition, Gemini-2.0-Flash has the lowest errors (CER 0.13, WER 0.32), and AIN reaches WER 0.28. EasyOCR (CER 0.58) and Tesseract (0.54) are mid-range, while PaddleOCR drops to CER 0.79.
  • A hand-picked set of 104 hard samples covers fonts, diacritics, elongation and tilted text.
    • Azure OCR leads on diacritics (ChrF 40.5) and elongation (35.2).
    • GPT-4o is best on tilted text (13.1).
    • Tesseract collapses on tilted text (5.9).
    • No model wins every category.
  • Across 16 chart types, Gemini-2.0-Flash scores highest on simple charts (Pie 72.4, Dot 72.7, Bar 69.2). Violin (32.3) and Box plots (22.5) are hard for all models.
  • Specialized tools such as Surya, RT-DETR Layout and EasyOCR stay competitive on single tasks. They lose clearly to large VLMs on the end-to-end PDF-to-Markdown task.

Interesting ideas

  • I1. The benchmark includes a small, deliberately chosen hard-case slice grouped by phenomenon, and it shows that system rankings change depending on the phenomenon. Averages alone would hide this.
  • I2. Structured outputs like charts and diagrams are scored with dedicated structure-aware metrics (CharTeX, CODM) instead of raw string overlap. This makes the score track whether the extracted structure is correct.
  • I3. Supplementary data comes from a multi-phase pipeline in which an LLM drafts content and humans verify and correct it. This scales coverage while keeping quality controlled.
  • I4. Results are broken down by sub-type, and the breakdown shows that discrete, clearly separated inputs are much easier than continuous or overlapping ones. This explains why scores vary instead of just recording that they do.
  • I5. Component-level winners do not stay ahead in the end-to-end task, so the benchmark measures both separate stages and the full pipeline.

For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

  • I1 (learn): Build phenomenon-tagged challenge slices (coordination, long-distance dependencies, garden paths) so evaluation shows which witness parser is strong where, rather than a single overall score.
  • I2 (world): Score extracted entity/state/event graphs with a graph-matching metric that credits correct nodes and relations, instead of comparing serialized text.
  • I3 (learn): Mirror this phasing for LLM-teacher tiers, with generation, automatic checks, then human or witness-parser agreement, before silver trees enter training.
  • I4 (answer): Split school-test and word-problem results by problem type (single-step vs multi-quantity comparison) to locate exactly where the reader fails.
  • I5 (tree): Measure parser quality both by LAS and by downstream frame and answer accuracy, since a better LAS may not carry through the full text → answer chain.

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

 Institutions

🎓Linköping UniversityLinköping · Sweden18 works · 2,319 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 worksComputer Vision and Pattern Recognition · 3,486 works

🧭 Topics 2Research subjects and languages the work is about.Semitic languages · 3,066 worksEvaluation & benchmarks · 1,341 works

Cite

Cite as Ahmed Heakl, Muhammad Abdullah Sohail, Mukul Ranjan, Rania Elbadry, Ghazi Shazan Ahmad, Mohamed El-Geish, Omar Maher, Zhiqiang Shen, Fahad Shahbaz Khan and Salman Khan. 2025. KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding. Findings of the Association for Computational Linguistics: ACL 2025.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2025.findings-acl.1135

@inproceedings{heakl2025kitab,
  title = {{KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding}},
  author = {Ahmed Heakl, Muhammad Abdullah Sohail, Mukul Ranjan, Rania Elbadry, Ghazi Shazan Ahmad, Mohamed El-Geish, Omar Maher, Zhiqiang Shen, Fahad Shahbaz Khan and Salman Khan},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2025},
  year = {2025},
  doi = {10.18653/v1/2025.findings-acl.1135},
  url = {https://doi.org/10.18653/v1/2025.findings-acl.1135}
}

References

67 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Ahmed Abdelali, Hamdy Mubarak, Shammur Absar Chowdhury, Maram Hasanain, Basel Mousi, Sabri Boughorbel, Yassine El Kheir, Daniel Izham, Fahim Dalvi, Majd Hawasly, et al. 2023. Larabench: Benchmarking arabic ai with large language models. arXiv preprint arXiv:2305.14982. ↗
  2. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774. ↗
  3. Fakhraddin Alwajih, El Moatez Billah Nagoudi, Gagan Bhatia, Abdelrahman Mohamed, and Muhammad Abdul-Mageed. 2024. Peacock: A family of arabic multimodal large language models and benchmarks. arXiv preprint arXiv:2403.01031. ↗
  4. Christoph Auer, Maksym Lysak, Ahmed Nassar, Michele Dolfi, Nikolaos Livathinos, Panos Vagenas, Cesar Berrospi Ramis, Matteo Omenetti, Fabian Lindlbauer, Kasper Dinkla, et al. 2024. Docling technical report. arXiv preprint arXiv:2408.09869. ↗
  5. Gagan Bhatia, El Moatez Billah Nagoudi, Fakhraddin Alwajih, and Muhammad Abdul-Mageed. 2024. Qalam: A multimodal llm for arabic optical character and handwriting recognition. arXiv preprint arXiv:2407.13559. ↗
  6. Houda Bouamor, Nizar Habash, Mohammad Salameh, Wajdi Zaghouani, Owen Rambow, Dana Abdulrahim, Ossama Obeid, Salam Khalifa, Fadhl Eryani, Alexander Erdmann, et al. 2018. The madar arabic dialect corpus and lexicon. In Proceedings of the eleventh international conference on language resources and evaluation (LREC 2018). find
  7. Houcine Boubaker, Abdelkarim Elbaati, Najiba Tagougui, Haikal El Abed, Monji Kherallah, Volker Märgner, and Adel M. Alimi. 2021. Adab database. find
  8. Hassina Bouressace and Janos Csirik. 2019. Printed arabic text database for automatic recognition systems. In Proceedings of the 2019 5th International Conference on Computer and Technology Applications, pages 107– 111. find
  9. Xavier Cattan. 2021. img2table: Extract tables from images and scanned pdfs. https://github.com/xav ctn/img2table. Accessed: 2025-02-14. ↗
  10. H. Cheng, P. Zhang, S. Wu, et al. 2023. M6doc: A large-scale multi-format, multi-type, multi-layout, multi-language, multi-annotation category dataset for modern document layout analysis. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). find
  11. Matt Deitke, Christopher Clark, Sangho Lee, Rohun Tripathi, Yue Yang, Jae Sung Park, Mohammadreza Salehi, Niklas Muennighoff, Kyle Lo, Luca Soldaini, et al. 2024. Molmo and pixmo: Open weights and open data for state-of-the-art multimodal models. arXiv preprint arXiv:2409.17146. ↗
  12. Yuning Du, Chenxia Li, Ruoyu Guo, Cheng Cui, Weiwei Liu, Jun Zhou, Bin Lu, Yehua Yang, Qiwen Liu, Xiaoguang Hu, et al. 2021. Pp-ocrv2: Bag of tricks for ultra lightweight ocr system. arXiv preprint arXiv:2109.03144. ↗
  13. Yuning Du, Chenxia Li, Ruoyu Guo, Xiaoting Yin, Weiwei Liu, Jun Zhou, Yifan Bai, Zilin Yu, Yehua Yang, Qingqing Dang, et al. 2020. Pp-ocr: A practical ultra lightweight ocr system. arXiv preprint arXiv:2009.09941. ↗
  14. Husni A. El-Muhtaseb. 2010. Pats-a01 - an arabic text database. https://faculty.kfupm.edu.sa/ics/m uhtaseb/ArabicOCR/PATS-A01.htm. Database for Arabic Text Recognition Research. ↗
  15. Ali Elfilali. 2023. Hindawi books dataset. https://huggingface.co/datasets/Ali-C137/Hindaw i-Books-dataset. Dataset. ↗
  16. Ling Fu, Biao Yang, Zhebin Kuang, Jiajun Song, Yuzhe Li, Linghao Zhu, Qidi Luo, Xinyu Wang, Hao Lu, Mingxin Huang, et al. 2024. Ocrbench v2: An improved benchmark for evaluating large multimodal models on visual text localization and reasoning. arXiv preprint arXiv:2501.00321. ↗
  17. Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al. 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530. ↗
  18. Sara Ghaboura, Ahmed Heakl, Omkar Thawakar, Ali Alharthi, Ines Riahi, Abduljalil Saif, Jorma Laaksonen, Fahad S Khan, Salman Khan, and Rao M Anwer. 2024. Camel-bench: A comprehensive arabic lmm benchmark. arXiv preprint arXiv:2410.18976. ↗
  19. Google DeepMind. 2025. Gemini Model Updates -February 2025. Accessed: 2025-02-14. find
  20. Heba Hassan, Ahmed El-Mahdy, and Mohamed E Hussein. 2021. Arabic scene text recognition in the deep learning era: Analysis on a novel dataset. IEEE Access, 9:107046–107058. find
  21. Ahmed Heakl, Sara Ghaboura, Omkar Thawkar, Fahad Shahbaz Khan, Hisham Cholakkal, Rao Muhammad Anwer, and Salman Khan. 2025. Ain: The arabic inclusive large multimodal model. arXiv preprint arXiv:2502.00094. ↗
  22. Aaron Hurst, Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276. ↗
  23. JaidedAI. 2020. Easyocr: Ready-to-use optical character recognition with multi-language support. https://github.com/JaidedAI/EasyOCR. Accessed: 2025-02-14. ↗
  24. Benjamin Kiessling, Daniel Stökl Ben Ezra, and Matthew Thomas Miller. 2019. Badam: A public dataset for baseline detection in arabic-script manuscripts. In Proceedings of the 5th International Workshop on Historical Document Imaging and Processing, page 13–18, New York, NY, USA. Association for Computing Machinery. find
  25. Chenxia Li, Weiwei Liu, Ruoyu Guo, Xiaoting Yin, Kaitao Jiang, Yongkun Du, Yuning Du, Lingfeng Zhu, Baohua Lai, Xiaoguang Hu, et al. 2022. Pp-ocrv3: More attempts for the improvement of ultra lightweight ocr system. arXiv preprint arXiv:2206.03001. ↗
  26. Minghao Li, Lei Cui, Shaohan Huang, Furu Wei, Ming Zhou, and Zhoujun Li. 2019. Tablebank: A benchmark dataset for table detection and recognition. arXiv preprint arXiv:1903.01949. ↗
  27. Minghao Li, Yiheng Xu, Leyang Cui, Shaohan Huang, Furu Wei, and Zhoujun Li. 2020. Docbank: A benchmark dataset for document layout analysis. arXiv preprint arXiv:2006.01038. ↗
  28. Yiren Li, Zheng Huang, Junchi Yan, Yi Zhou, Fan Ye, and Xianhui Liu. 2021. Gfte: graph-based financial table extraction. In Pattern Recognition. ICPR International Workshops and Challenges: Virtual Event, January 10–15, 2021, Proceedings, Part II, pages 644–658. Springer. find
  29. Nikolaos Livathinos, Cesar Berrospi, Maksym Lysak, Viktor Kuropiatnyk, Ahmed Nassar, Andre Carvalho, Michele Dolfi, Christoph Auer, Kasper Dinkla, and Peter Staar. 2021. Robust pdf document conversion using recurrent neural networks. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 15137–15145. find
  30. Sabri A Mahmoud, Irfan Ahmad, Wasfi G Al-Khatib, Mohammad Alshayeb, Mohammad Tanvir Parvez, Volker Märgner, and Gernot A Fink. 2014. Khatt: An open arabic offline handwritten text database. Pattern Recognition, 47(3):1096–1112. find
  31. Sabri A Mahmoud, Hamzah Luqman, Baligh M Al-Helali, Galal BinMakhashen, and Mohammad Tanvir Parvez. 2018. Online-khatt: an open-vocabulary database for arabic online-text processing. The Open Cybernetics & Systemics Journal, 12(1). find
  32. Microsoft. 2024. OCR - Optical Character Recognition - Azure AI services. Accessed: 2025-05-27. find
  33. Hamdy Mubarak, Hend Al-Khalifa, and AbdulMohsen Al-Thubaity. 2022. Overview of osact5 shared task on arabic offensive language and hate speech detection. In Proceedinsg of the 5th Workshop on Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur’an QA and Fine-Grained Hate Speech Detection, pages 162–166.
  34. NAMAA-Space. 2025. Qari-ocr: A high-accuracy model for arabic optical character recognition. https://huggingface.co/collections/NAMAA-Space/q ari-ocr-a-high-accuracy-model-for-arabic-o ptical-character-67c6cdff9584ef0684391335. Accessed: 2025-05-27. ↗
  35. Ahmed Nassar, Nikolaos Livathinos, Maksym Lysak, and Peter Staar. 2022. Tableformer: Table structure understanding with transformers. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4614–4623. find
  36. Shubham Singh Paliwal, D Vishwanath, Rohit Rahul, Monika Sharma, and Lovekesh Vig. 2019. 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), pages 128–133. IEEE. find
  37. Werner Pantke, Martin Dennhardt, Daniel Fecker, Volker Märgner, and Tim Fingscheidt. 2014. An historical handwritten arabic dataset for segmentation-free word spotting-hadara80p. In 2014 14th International Conference on Frontiers in Handwriting Recognition, pages 15–20. IEEE. find
  38. Vik Paruchuri. 2024a. Marker: Convert pdf to markdown and other formats. https://github.com/VikPa ruchuri/marker. ↗
  39. Vik Paruchuri. 2024b. Surya: Accurate line-by-line text detection and recognition in complex documents. https://github.com/VikParuchuri/surya. ↗
  40. Mario Pechwitz, S Snoussi Maddouri, Volker Märgner, Noureddine Ellouze, Hamid Amiri, et al. 2002. Ifn/enit-database of handwritten arabic words. In Proc. of CIFED, volume 2, pages 127–136. Citeseer. find
  41. Birgit Pfitzmann, Christoph Auer, Michele Dolfi, Ahmed S Nassar, and Peter W J Staar. 2022. Doclaynet: A large human-annotated dataset for document-layout analysis. arXiv preprint arXiv:2206.01062. ↗
  42. Maja Popović. 2015. chrf: character n-gram f-score for automatic mt evaluation. In Proceedings of the tenth workshop on statistical machine translation, pages 392– 395. ↗
  43. Devashish Prasad, Ayan Gadpal, Kshitij Kapadni, Manish Visave, and Kavita Sultanpure. 2020. Cascadetabnet: An approach for end to end table detection and structure recognition from image-based documents. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops, pages 572–573. find
  44. Mohamed Rashad. 2024. Arabic-nougat: Fine-tuning vision transformers for arabic ocr and markdown extraction. arXiv preprint arXiv:2411.17835. ↗
  45. Rana SM Saad, Randa I Elanwar, NS Abdel Kader, Samia Mashali, and Margrit Betke. 2016. Bce-arabic-v1 dataset: Towards interpreting arabic document images for people with visual impairments. In Proceedings of the 9th ACM International Conference on PErvasive Technologies Related to Assistive Environments, pages 1–8. find
  46. M. Saeed, A. Chan, A. Mijar, and J. Moukarzel. 2024. Muharaf: Manuscripts of handwritten arabic dataset for cursive text recognition. arXiv preprint arXiv:2406.09630. ↗
  47. Sebastian Schreiber, Stefan Agne, Ivo Wolf, Andreas Dengel, and Sheraz Ahmed. 2017. Deepdesrt: Deep learning for detection and structure recognition of tables in document images. In 2017 14th IAPR international conference on document analysis and recognition (IC-DAR), volume 1, pages 1162–1167. IEEE. find
  48. Zejiang Shen, Ruochen Zhang, Melissa Dell, Benjamin Charles Germain Lee, Jacob Carlson, and Weining Li. 2021. Layoutparser: A unified toolkit for deep learning based document image analysis. In Document Analysis and Recognition–ICDAR 2021: 16th International Conference, Lausanne, Switzerland, September 5–10, 2021, Proceedings, Part I 16, pages 131–146. Springer. find
  49. Fouad Slimane, Rolf Ingold, Slim Kanoun, Adel M Alimi, and Jean Hennebert. 2009. A new arabic printed text image database and evaluation protocols. In 2009 10th international conference on document analysis and recognition, pages 946–950. IEEE. find
  50. Ray Smith. 2007. An overview of the tesseract ocr engine. In Ninth international conference on document analysis and recognition (ICDAR 2007), volume 2, pages 629–633. IEEE. ↗
  51. Peter WJ Staar, Michele Dolfi, Christoph Auer, and Costas Bekas. 2018. Corpus conversion service: A machine learning platform to ingest documents at scale. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 774–782. find
  52. Jingqun Tang, Qi Liu, Yongjie Ye, Jinghui Lu, Shu Wei, Chunhui Lin, Wanqing Li, Mohamad Fitri Faiz Bin Mahmood, Hao Feng, Zhen Zhao, Yanjie Wang, Yuliang Liu, Hao Liu, Xiang Bai, and Can Huang. 2024. Mtvqa: Benchmarking multilingual text-centric visual question answering. Preprint, arXiv:2405.11985. ↗
  53. Gemma Team, Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova, Alexandre Ramé, Morgane Rivière, et al. 2025. Gemma 3 technical report. arXiv preprint arXiv:2503.19786. ↗
  54. Bin Wang, Chao Xu, Xiaomeng Zhao, Linke Ouyang, Fan Wu, Zhiyuan Zhao, Rui Xu, Kaiwen Liu, Yuan Qu, Fukai Shang, et al. 2024a. Mineru: An open-source solution for precise document content extraction. arXiv preprint arXiv:2409.18839. ↗
  55. Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, et al. 2024b. Qwen2-vl: Enhancing vision-language model’s perception of the world at any resolution. arXiv preprint arXiv:2409.12191. ↗
  56. Maurice Weber, Carlo Siebenschuh, Rory Butler, Anton Alexandrov, Valdemar Thanner, Georgios Tsolakis, Haris Jabbar, Ian Foster, Bo Li, Rick Stevens, et al. 2023. Wordscape: a pipeline to extract multilingual, visually rich documents with layout annotations from web crawl data. Advances in Neural Information Processing Systems, 36:26048–26068. find
  57. Haoran Wei, Chenglong Liu, Jinyue Chen, Jia Wang, Lingyu Kong, Yanming Xu, Zheng Ge, Liang Zhao, Jianjian Sun, Yuang Peng, et al. 2024. General ocr theory: Towards ocr-2.0 via a unified end-to-end model. arXiv preprint arXiv:2409.01704. ↗
  58. Yue Wu and Prem Natarajan. 2017. Self-organized text detection with minimal post-processing via border learning. In International Conference on Computer Vision. find
  59. Renqiu Xia, Bo Zhang, Haoyang Peng, Hancheng Ye, Xiangchao Yan, Peng Ye, Botian Shi, Yu Qiao, and Junchi Yan. 2023. Structchart: Perception, structuring, reasoning for visual chart understanding. arXiv preprint arXiv:2309.11268. ↗
  60. Renqiu Xia, Bo Zhang, Hancheng Ye, Xiangchao Yan, Qi Liu, Hongbin Zhou, Zijun Chen, Min Dou, Botian Shi, Junchi Yan, et al. 2024. Chartx & chartvlm: A versatile benchmark and foundation model for complicated chart reasoning. arXiv preprint arXiv:2402.12185. ↗
  61. Taha Zerrouki and Amar Balla. 2017. Tashkeela: Novel corpus of arabic vocalized texts, data for auto-diacritization systems. Data in brief, 11:147. find
  62. Y Zhao, W Lv, S Xu, J Wei, G Wang, Q Dang, Y Liu, and J Chen. 2023. Detrs beat yolos on real-time object detection. arxiv e-prints. arXiv preprint arXiv:2304.08069. ↗
  63. Z. Zhao, H. Kang, B. Wang, and C. He. 2024. Doclayout-yolo: Enhancing document layout analysis through diverse synthetic data and global-to-local adaptive perception. arXiv preprint arXiv:2410.12628. ↗
  64. Xinyi Zheng, Douglas Burdick, Lucian Popa, Xu Zhong, and Nancy Xin Ru Wang. 2021. 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, pages 697–706. find
  65. X Zhong, E ShafieiBavani, and A Jimeno-Yepes. 2019a. Image-based table recognition: data, model, and evaluation. corr abs/1911.10683. arXiv preprint arXiv:1911.10683. ↗
  66. Xu Zhong, Elaheh ShafieiBavani, and Antonio Jimeno Yepes. 2020. Image-based table recognition: data, model, and evaluation. In European conference on computer vision, pages 564–580. Springer. find
  67. Xu Zhong, Jianbin Tang, and Antonio Jimeno Yepes. 2019b. Publaynet: largest dataset ever for document layout analysis. In 2019 International conference on document analysis and recognition (ICDAR), pages 1015– 1022. IEEE. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/heakl-2025-kitab-bench-comprehensive-multi-domain/