mlsanityData to 14 Oct 2026

PubTables-1M: Towards comprehensive table extraction from unstructured documents

arXiv 2110.00061 ↗First posted 30 Sep 2021cs.LG cs.CVcited by 126

Not on the map. Why?

Abstract (arXiv)

Recently, significant progress has been made applying machine learning to the problem of table structure inference and extraction from unstructured documents. However, one of the greatest challenges remains the creation of datasets with complete, unambiguous ground truth at scale. To address this, we develop a new, more comprehensive dataset for table extraction, called PubTables-1M. PubTables-1M contains nearly one million tables from scientific articles, supports multiple input modalities, and contains detailed header and location information for table structures, making it useful for a wide variety of modeling approaches. It also addresses a significant source of ground truth inconsistency observed in prior datasets called oversegmentation, using a novel canonicalization procedure. We demonstrate that these improvements lead to a significant increase in training performance and a more reliable estimate of model performance at evaluation for table structure recognition. Further, we show that transformer-based object detection models trained on PubTables-1M produce excellent results for all three tasks of detection, structure recognition, and functional analysis without the need for any special customization for these tasks. Data and code will be released at https://github.com/microsoft/table-transformer.

Key facts. Cited by 126 papers in the map (data through 14 Oct 2026). Builds on 8 of its 28 references that are in the map. First posted on arXiv 30 Sep 2021.

Builds on

8 of 28 references.

References · 8

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  2. 2020End-to-End Object Detection with Transformerscited by 7,414
  3. 2019Image-based table recognition: data, model, and evaluationcited by 237
  4. 2020Global Table Extractor (GTE): A Framework for Joint Table Identification and Cell Structure Recognition Using Visual Contextcited by 147
  5. 2019TableBank: A Benchmark Dataset for Table Detection and Recognitioncited by 102
  6. 2020CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documentscited by 98
  7. 2019Complicated Table Structure Recognitioncited by 92
  8. 2020TableNet: Deep Learning model for end-to-end Table detection and Tabular data extraction from Scanned Document Imagescited by 69

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 6; 2023: 22; 2024: 25; 2025: 31; 2026: 42.

126 papers.

Sort:

By area:

  1. 2023Document Understanding Dataset and Evaluation (DUDE)cited by 135
  2. 2022Towards Complex Document Understanding By Discrete Reasoningcited by 82
  3. 2025Dolphin: Document Image Parsing via Heterogeneous Anchor Promptingcited by 79
  4. 2024TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergycited by 71
  5. 2023DocILE Benchmark for Document Information Localization and Extractioncited by 58
  6. 2025SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversioncited by 53
  7. 2024Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extractioncited by 44
  8. 2023Improving Table Structure Recognition with Visual-Alignment Sequential Coordinate Modelingcited by 41
  9. 2024UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-world Document Analysiscited by 40
  10. 2023Optimized Table Tokenization for Table Structure Recognitioncited by 34
  11. 2024TextHawk2: A Large Vision-Language Model Excels in Bilingual OCR and Grounding with 16x Fewer Tokenscited by 32
  12. 2022GriTS: Grid table similarity metric for table structure recognitioncited by 28
38 more
  1. 2023A large-scale dataset for end-to-end table recognition in the wildcited by 24
  2. 2025OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Modelscited by 23
  3. 2025Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligencecited by 20
  4. 2023LORE: Logical Location Regression Network for Table Structure Recognitioncited by 19
  5. 2024MMDocBench: Benchmarking Large Vision-Language Models for Fine-Grained Visual Document Understandingcited by 19
  6. 2022Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networkscited by 17
  7. 2025NVIDIA Nemotron Nano V2 VLcited by 17
  8. 2022Deep learning for table detection and structure recognition: A surveycited by 15
  9. 2023Aligning benchmark datasets for table structure recognitioncited by 15
  10. 2024READoc: A Unified Benchmark for Realistic Document Structured Extractioncited by 15
  11. 2024PoTable: Towards Systematic Thinking via Plan-then-Execute Stage Reasoning on Tablescited by 14
  12. 2024Enhancing Vision-Language Pre-training with Rich Supervisionscited by 13
  13. 2024UniTable: Towards a Unified Framework for Table Recognition via Self-Supervised Pretrainingcited by 13
  14. 2025Benchmarking Multimodal LLMs on Recognition and Understanding over Chemical Tablescited by 13
  15. 2023SEMv2: Table Separation Line Detection Based on Instance Segmentationcited by 12
  16. 2023Robust Table Structure Recognition with Dynamic Queries Enhanced Detection Transformercited by 12
  17. 2024Efficient Prompting for LLM-based Generative Internet of Thingscited by 12
  18. 2024UniTabNet: Bridging Vision and Language Models for Enhanced Table Structure Recognitioncited by 11
  19. 2023Rethinking Image-based Table Recognition Using Weakly Supervised Methodscited by 10
  20. 2025FS-DAG: Few Shot Domain Adapting Graph Networks for Visually Rich Document Understandingcited by 10
  21. 2024JDocQA: Japanese Document Question Answering Dataset for Generative Language Modelscited by 9
  22. 2024LORE++: Logical Location Regression Network for Table Structure Recognition with Pre-trainingcited by 8
  23. 2025Granite Embedding R2 Modelscited by 8
  24. 2023Towards End-to-End Semi-Supervised Table Detection with Deformable Transformercited by 7
  25. 2023Bridging the Performance Gap between DETR and R-CNN for Graphical Object Detection in Document Imagescited by 7
  26. 2023DSG: An End-to-End Document Structure Generatorcited by 7
  27. 2024SEMv3: A Fast and Robust Approach to Table Separation Line Detectioncited by 7
  28. 2023Grab What You Need: Rethinking Complex Table Structure Recognition with Flexible Components Deliberationcited by 6
  29. 2023Table Detection for Visually Rich Document Imagescited by 6
  30. 2024A Hybrid Approach for Document Layout Analysis in Document imagescited by 6
  31. 2025SPRINT: Script-agnostic Structure Recognition in Tablescited by 6
  32. 2024Towards End-to-End Semi-Supervised Table Detection with Semantic Aligned Matching Transformercited by 5
  33. 2025SCORE: A Semantic Evaluation Framework for Generative Document Parsingcited by 5
  34. 2024The Socface Project: Large-Scale Collection, Processing, and Analysis of a Century of French Censusescited by 4
  35. 2024End-to-End Semi-Supervised approach with Modulated Object Queries for Table Detection in Documentscited by 4
  36. 2025DocSAM: Unified Document Image Segmentation via Query Decomposition and Heterogeneous Mixed Learningcited by 4
  37. 2026How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settingscited by 4
  38. 2023Revisiting Table Detection Datasets for Visually Rich Documentscited by 3

50 most cited of 126 All 126 (JSON)