mlsanityData to 7 Oct 2026

FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents

arXiv 1905.13538 ↗First posted 27 May 2019cs.IR cs.CV cs.LGcited by 345

Not on the map. Why?

Cited by 60 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present a new dataset for form understanding in noisy scanned documents (FUNSD) that aims at extracting and structuring the textual content of forms. The dataset comprises 199 real, fully annotated, scanned forms. The documents are noisy and vary widely in appearance, making form understanding (FoUn) a challenging task. The proposed dataset can be used for various tasks, including text detection, optical character recognition, spatial layout analysis, and entity labeling/linking. To the best of our knowledge, this is the first publicly available dataset with comprehensive annotations to address FoUn task. We also present a set of baselines and introduce metrics to evaluate performance on the FUNSD dataset, which can be downloaded at https://guillaumejaume.github.io/FUNSD/.

Key facts. Cited by 345 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 28; 2022: 48; 2023: 67; 2024: 72; 2025: 69; 2026: 61.

345 papers.

Sort:

By area:

  1. 2025VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understandingcited by 502
  2. 2022LayoutLMv3: Pre-training for Document AI with Unified Text and Image Maskingcited by 481
  3. 2023OCRBench: On the Hidden Mystery of OCR in Large Multimodal Modelscited by 466
  4. 2021DocFormer: End-to-End Transformer for Document Understandingcited by 254
  5. 2023LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Modelscited by 217
  6. 2024MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizationscited by 174
  7. 2024TextMonkey: An OCR-Free Large Multimodal Model for Understanding Documentcited by 173
  8. 2024OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoningcited by 165
  9. 2022DiT: Self-supervised Pre-training for Document Image Transformercited by 152
  10. 2023Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Modelscited by 152
  11. 2022Unifying Vision, Text, and Layout for Universal Document Processingcited by 140
  12. 2021Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformercited by 134
38 more
  1. 2023Document Understanding Dataset and Evaluation (DUDE)cited by 132
  2. 2023BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questionscited by 125
  3. 2024NVLM: Open Frontier-Class Multimodal LLMscited by 124
  4. 2025olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Modelscited by 120
  5. 2021SelfDoc: Self-Supervised Document Representation Learningcited by 117
  6. 2023DocLLM: A layout-aware generative language model for multimodal document understandingcited by 112
  7. 2022LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understandingcited by 107
  8. 2023DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understandingcited by 106
  9. 2021BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documentscited by 104
  10. 2021LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understandingcited by 103
  11. 2021WebSRC: A Dataset for Web-Based Structural Reading Comprehensioncited by 98
  12. 2023KOSMOS-2.5: A Multimodal Literate Modelcited by 95
  13. 2021StructuralLM: Structural Pre-training for Form Understandingcited by 91
  14. 2021StrucTexT: Structured Text Understanding with Multi-Modal Transformerscited by 90
  15. 2022Unified Pretraining Framework for Document Understandingcited by 85
  16. 2021Kleister: Key Information Extraction Datasets Involving Long Documents with Complex Layoutscited by 82
  17. 2022Towards Complex Document Understanding By Discrete Reasoningcited by 82
  18. 2024Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-trainingcited by 82
  19. 2022End-to-end Document Recognition and Understanding with Dessurtcited by 73
  20. 2022XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understandingcited by 68
  21. 2024OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automationcited by 66
  22. 2022ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshotscited by 65
  23. 2022FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extractioncited by 64
  24. 2021Document AI: Benchmarks, Models and Applicationscited by 61
  25. 2023DocILE Benchmark for Document Information Localization and Extractioncited by 58
  26. 2024A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understandingcited by 57
  27. 2025Visual Agentic Reinforcement Fine-Tuningcited by 53
  28. 2025SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversioncited by 51
  29. 2025FineVision: Open Data Is All You Needcited by 51
  30. 2023DocFormerv2: Local Features for Document Understandingcited by 46
  31. 2023Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth Evaluationcited by 46
  32. 2025FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocitiescited by 46
  33. 2021MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understandingcited by 44
  34. 2023GeoLayoutLM: Geometric Pre-training for Visual Information Extractioncited by 40
  35. 2023StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-trainingcited by 39
  36. 2023ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extractioncited by 38
  37. 2024TextCoT: Zoom In for Enhanced Multimodal Text-Rich Image Understandingcited by 37
  38. 2022VRDU: A Benchmark for Visually-rich Document Understandingcited by 35

50 most cited of 345 All 345 (JSON)