mlsanityData to 7 Oct 2026

DocBank: A Benchmark Dataset for Document Layout Analysis

arXiv 2006.01038 ↗First posted 1 Jun 2020cs.CLcited by 152

Not on the map. Why?

Abstract (arXiv)

Document layout analysis usually relies on computer vision models to understand documents while ignoring textual information that is vital to capture. Meanwhile, high quality labeled datasets with both visual and textual information are still insufficient. In this paper, we present DocBank, a benchmark dataset that contains 500K document pages with fine-grained token-level annotations for document layout analysis. DocBank is constructed using a simple yet effective way with weak supervision from the LaTeX documents available on the arXiv.com. With DocBank, models from different modalities can be compared fairly and multi-modal approaches will be further investigated and boost the performance of document layout analysis. We build several strong baselines and manually split train/dev/test sets for evaluation. Experiment results show that models trained on DocBank accurately recognize the layout information for a variety of documents. The DocBank dataset is publicly available at urlhttps://github.com/doc-analysis/DocBank.

Key facts. Cited by 152 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 21; 2022: 13; 2023: 31; 2024: 33; 2025: 30; 2026: 24.

152 papers.

Sort:

By area:

  1. 2022DiT: Self-supervised Pre-training for Document Image Transformercited by 152
  2. 2022DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysiscited by 146
  3. 2024OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotationscited by 144
  4. 2022Unifying Vision, Text, and Layout for Universal Document Processingcited by 140
  5. 2023Document Understanding Dataset and Evaluation (DUDE)cited by 132
  6. 2023DocLLM: A layout-aware generative language model for multimodal document understandingcited by 112
  7. 2021LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understandingcited by 103
  8. 2021WebSRC: A Dataset for Web-Based Structural Reading Comprehensioncited by 98
  9. 2024Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Wantcited by 98
  10. 2024LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understandingcited by 94
  11. 2021StrucTexT: Structured Text Understanding with Multi-Modal Transformerscited by 90
  12. 2022Towards Complex Document Understanding By Discrete Reasoningcited by 82
38 more
  1. 2024DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perceptioncited by 80
  2. 2021LayoutReader: Pre-training of Text and Layout for Reading Order Detectioncited by 79
  3. 2024TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergycited by 70
  4. 2021Document AI: Benchmarks, Models and Applicationscited by 61
  5. 2024A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understandingcited by 57
  6. 2023Vision Grid Transformer for Document Layout Analysiscited by 45
  7. 2023M6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysiscited by 44
  8. 2024Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extractioncited by 44
  9. 2021VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relationscited by 40
  10. 2024Image Over Text: Transforming Formula Recognition Evaluation with Character Detection Matchingcited by 39
  11. 2022OCR-IDL: OCR Annotations for Industry Document Library Datasetcited by 35
  12. 2022VRDU: A Benchmark for Visually-rich Document Understandingcited by 35
  13. 2024DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Modelscited by 34
  14. 2022Robust Table Detection and Structure Recognition from Heterogeneous Document Imagescited by 30
  15. 2021VILA: Improving Structured Content Extraction from Scientific PDFs Using Visual Layout Groupscited by 27
  16. 2024InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructionscited by 27
  17. 2021Entity Relation Extraction as Dependency Parsing in Visually Rich Documentscited by 23
  18. 2024DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understandingcited by 23
  19. 2023HRDoc: Dataset and Baseline Method Toward Hierarchical Reconstruction of Document Structurescited by 22
  20. 2023Diffusion-based Document Layout Generationcited by 21
  21. 2023CCpdf: Building a High Quality Corpus for Visually Rich Documents from Web Crawl Datacited by 21
  22. 2024Deep Learning based Visually Rich Document Content Understanding: A Surveycited by 21
  23. 2024MMDocBench: Benchmarking Large Vision-Language Models for Fine-Grained Visual Document Understandingcited by 18
  24. 2022Doc-GCN: Heterogeneous Graph Convolutional Networks for Document Layout Analysiscited by 17
  25. 2021LAMPRET: Layout-Aware Multimodal PreTraining for Document Understandingcited by 15
  26. 2024READoc: A Unified Benchmark for Realistic Document Structured Extractioncited by 15
  27. 2025P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmarkcited by 15
  28. 2024Detect-Order-Construct: A Tree Construction based Approach for Hierarchical Document Structure Analysiscited by 14
  29. 2024SciPostLayout: A Dataset for Layout Analysis and Layout Generation of Scientific Posterscited by 14
  30. 2024PDF-WuKong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Samplingcited by 14
  31. 2025KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understandingcited by 14
  32. 2023BaDLAD: A Large Multi-Domain Bengali Document Layout Analysis Datasetcited by 13
  33. 2024RoDLA: Benchmarking the Robustness of Document Layout Analysis Modelscited by 12
  34. 2024Visually Guided Generative Text-Layout Pre-training for Document Intelligencecited by 12
  35. 2025Handwritten Text Recognition: A Surveycited by 12
  36. 2022Relational Representation Learning in Visually-Rich Documentscited by 11
  37. 2023Beyond Document Page Classification: Design, Datasets, and Challengescited by 10
  38. 2024LAPDoc: Layout-Aware Prompting for Documentscited by 9

50 most cited of 152 All 152 (JSON)