mlsanityData to 7 Oct 2026

PubLayNet: largest dataset ever for document layout analysis

arXiv 1908.07836 ↗First posted 16 Aug 2019cs.CLcited by 349

Not on the map. Why?

Cited by 29 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Recognizing the layout of unstructured digital documents is an important step when parsing the documents into structured machine-readable format for downstream applications. Deep neural networks that are developed for computer vision have been proven to be an effective method to analyze layout of document images. However, document layout datasets that are currently publicly available are several magnitudes smaller than established computing vision datasets. Models have to be trained by transfer learning from a base model that is pre-trained on a traditional computer vision dataset. In this paper, we develop the PubLayNet dataset for document layout analysis by automatically matching the XML representations and the content of over 1 million PDF articles that are publicly available on PubMed Central. The size of the dataset is comparable to established computer vision datasets, containing over 360 thousand document images, where typical document layout elements are annotated. The experiments demonstrate that deep neural networks trained on PubLayNet accurately recognize the layout of scientific articles. The pre-trained models are also a more effective base mode for transfer learning on a different document domain. We release the dataset (https://github.com/ibm-aur-nlp/PubLayNet) to support development and evaluation of more advanced models for document layout analysis.

Key facts. Cited by 349 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 41; 2022: 44; 2023: 65; 2024: 70; 2025: 66; 2026: 63.

349 papers.

Sort:

By area:

  1. 2022LayoutLMv3: Pre-training for Document AI with Unified Text and Image Maskingcited by 481
  2. 2021InfographicVQAcited by 430
  3. 2023LayoutGPT: Compositional Visual Planning and Generation with Large Language Modelscited by 337
  4. 2021DocFormer: End-to-End Transformer for Document Understandingcited by 254
  5. 2024General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Modelcited by 174
  6. 2024OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoningcited by 165
  7. 2022DiT: Self-supervised Pre-training for Document Image Transformercited by 152
  8. 2022DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysiscited by 146
  9. 2024OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotationscited by 144
  10. 2023LayoutDM: Discrete Diffusion Model for Controllable Layout Generationcited by 141
  11. 2022Unifying Vision, Text, and Layout for Universal Document Processingcited by 140
  12. 2023Document Understanding Dataset and Evaluation (DUDE)cited by 132
38 more
  1. 2021SelfDoc: Self-Supervised Document Representation Learningcited by 117
  2. 2023The Semantic Scholar Open Data Platformcited by 109
  3. 2021LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understandingcited by 103
  4. 2021WebSRC: A Dataset for Web-Based Structural Reading Comprehensioncited by 98
  5. 2024Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Wantcited by 98
  6. 2022Towards End-to-End Unified Scene Text Detection and Layout Analysiscited by 96
  7. 2024LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understandingcited by 94
  8. 2021CanvasVAE: Learning to Generate Vector Graphic Documentscited by 93
  9. 2022TableFormer: Table Structure Understanding with Transformerscited by 93
  10. 2021Variational Transformer Networks for Layout Generationcited by 88
  11. 2022Unified Pretraining Framework for Document Understandingcited by 85
  12. 2021Constrained Graphic Layout Generation via Latent Optimizationcited by 83
  13. 2022Towards Complex Document Understanding By Discrete Reasoningcited by 82
  14. 2025MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigmcited by 81
  15. 2024DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perceptioncited by 80
  16. 2021LayoutReader: Pre-training of Text and Layout for Reading Order Detectioncited by 79
  17. 2024OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognitioncited by 74
  18. 2021BLT: Bidirectional Layout Transformer for Controllable Layout Generationcited by 69
  19. 2022XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understandingcited by 68
  20. 2025Detect Anything via Next Point Predictioncited by 66
  21. 2024Focus Anywhere for Fine-grained Multi-page Document Understandingcited by 62
  22. 2021Document AI: Benchmarks, Models and Applicationscited by 61
  23. 2021LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysiscited by 58
  24. 2023DocILE Benchmark for Document Information Localization and Extractioncited by 58
  25. 2023LayoutDM: Transformer-based Diffusion Model for Layout Generationcited by 57
  26. 2023LayoutPrompter: Awaken the Design Ability of Large Language Modelscited by 47
  27. 2023Vision Grid Transformer for Document Layout Analysiscited by 45
  28. 2022A Multi-Task Benchmark for Korean Legal Language Understanding and Judgement Predictioncited by 44
  29. 2023M6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysiscited by 44
  30. 2023DiffUTE: Universal Text Editing Diffusion Modelcited by 44
  31. 2024Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extractioncited by 44
  32. 2025dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Modelcited by 44
  33. 2022LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restrictioncited by 43
  34. 2022Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Taskscited by 42
  35. 2025Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generationcited by 42
  36. 2023Unifying Layout Generation with a Decoupled Diffusion Modelcited by 41
  37. 2021VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relationscited by 40
  38. 2023LayoutDiffusion: Improving Graphic Layout Generation by Discrete Diffusion Probabilistic Modelscited by 40

50 most cited of 349 All 349 (JSON)