mlsanityData to 7 Oct 2026

OCR-IDL: OCR Annotations for Industry Document Library Dataset

arXiv 2202.12985 ↗First posted 25 Feb 2022cs.CV cs.AIcited by 35

Not on the map. Why?

Abstract (arXiv)

Pretraining has proven successful in Document Intelligence tasks where deluge of documents are used to pretrain the models only later to be finetuned on downstream tasks. One of the problems of the pretraining approaches is the inconsistent usage of pretraining data with different OCR engines leading to incomparable results between models. In other words, it is not obvious whether the performance gain is coming from diverse usage of amount of data and distinct OCR engines or from the proposed models. To remedy the problem, we make public the OCR annotations for IDL documents using commercial OCR engine given their superior performance over open source OCR models. The contributed dataset (OCR-IDL) has an estimated monetary value over 20K US. It is our hope that OCR-IDL can be a starting point for future works on Document Intelligence. All of our data and its collection process with the annotations can be found in https://github.com/furkanbiten/idldata.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Builds on 39 of its 54 references that are in the map. First posted on arXiv 25 Feb 2022.

Builds on

39 of 54 references.

References · 39

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2017Mask R-CNNcited by 7,259
  5. 2019Towards VQA Models That Can Readcited by 1,696
  6. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,288
  7. 2019SpanBERT: Improving Pre-training by Representing and Predicting Spanscited by 832
  8. 2019LayoutLM: Pre-training of Text and Layout for Document Image Understandingcited by 549
  9. 2021InfographicVQAcited by 430
  10. 2020LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understandingcited by 406
  11. 2019PubLayNet: largest dataset ever for document layout analysiscited by 349
  12. 2019Scene Text Visual Question Answeringcited by 327
27 more
  1. 2021DocFormer: End-to-End Transformer for Document Understandingcited by 254
  2. 2019Image-based table recognition: data, model, and evaluationcited by 233
  3. 2015Evaluation of Deep Convolutional Nets for Document Image Classification and Retrievalcited by 212
  4. 2021Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognitioncited by 194
  5. 2020DocBank: A Benchmark Dataset for Document Layout Analysiscited by 152
  6. 2021Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformercited by 134
  7. 2021SelfDoc: Self-Supervised Document Representation Learningcited by 117
  8. 2020CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documentscited by 98
  9. 2021Variational Transformer Networks for Layout Generationcited by 88
  10. 2021LaTr: Layout-Aware Transformer for Scene-Text VQAcited by 72
  11. 2020Sequence-to-Sequence Contrastive Learning for Text Recognitioncited by 70
  12. 2020SCATTER: Selective Context Attentional Scene Text Recognizercited by 69
  13. 2020Table Structure Recognition using Top-Down and Bottom-Up Cuescited by 53
  14. 2019READ: Recursive Autoencoders for Document Layout Generationcited by 51
  15. 2019ICDAR 2019 Competition on Scene Text Visual Question Answeringcited by 46
  16. 2021Document Collection Visual Question Answeringcited by 45
  17. 2020DE-GAN: A Conditional Generative Adversarial Network for Document Enhancementcited by 44
  18. 2021Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Featurescited by 34
  19. 2022DocEnTr: An End-to-End Document Image Enhancement Transformercited by 28
  20. 2021Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognitioncited by 25
  21. 2021ICDAR 2021 Competition on Document VisualQuestion Answeringcited by 19
  22. 2021DocSynth: A Layout Guided Approach for Controllable Document Image Synthesiscited by 17
  23. 2020Multi-Modal Reasoning Graph for Scene-Text Based Fine-Grained Image Classification and Retrievalcited by 10
  24. 2020Fine-grained Image Classification and Retrieval by Combining Visual and Locally Pooled Textual Featurescited by 6
  25. 2020StacMR: Scene-Text Aware Cross-Modal Retrievalcited by 6
  26. 2021One-shot Compositional Data Generation for Low Resource Handwritten Text Recognitioncited by 6
  27. 2020Multimodal grid features and cell pointers for Scene Text Visual Question Answeringcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 6; 2024: 10; 2025: 11; 2026: 4.

35 papers.

Sort:

By area:

  1. 2024What matters when building vision-language models?cited by 321
  2. 2023Nougat: Neural Optical Understanding for Academic Documentscited by 240
  3. 2024Building and better understanding vision-language models: insights and future directionscited by 169
  4. 2024xGen-MM (BLIP-3): A Family of Open Large Multimodal Modelscited by 116
  5. 2022Hierarchical multimodal transformers for Multi-Page DocVQAcited by 102
  6. 2025Detect Anything via Next Point Predictioncited by 66
  7. 2023DocILE Benchmark for Document Information Localization and Extractioncited by 58
  8. 2025Scalable Vision Language Model Training via High Quality Data Curationcited by 54
  9. 2025SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversioncited by 51
  10. 2026LongCat-Next: Lexicalizing Modalities as Discrete Tokenscited by 30
  11. 2024DocVLM: Make Your VLM an Efficient Readercited by 27
  12. 2025Scaling Vision Pre-Training to 4K Resolutioncited by 26
23 more
  1. 2023CCpdf: Building a High Quality Corpus for Visually Rich Documents from Web Crawl Datacited by 21
  2. 2025M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performancecited by 19
  3. 2023Beyond Document Page Classification: Design, Datasets, and Challengescited by 10
  4. 2025Towards Understanding Visual Grounding in Visual Language Modelscited by 9
  5. 2024VisFocus: Prompt-Guided Vision Encoders for OCR-Free Dense Document Understandingcited by 8
  6. 2022Graph Neural Networks and Representation Embedding for Table Extraction in PDF Documentscited by 6
  7. 2022On Web-based Visual Corpus Construction for Visual Document Understandingcited by 5
  8. 2023On Evaluation of Document Classification using RVL-CDIPcited by 5
  9. 2024Large Language Models for Page Stream Segmentationcited by 5
  10. 2025Towards Natural Language-Based Document Image Retrieval: New Dataset and Benchmarkcited by 5
  11. 2022MUST-VQA: MUltilingual Scene-text VQAcited by 4
  12. 2024SynthDoc: Bilingual Documents Synthesis for Visual Document Understandingcited by 4
  13. 2025SAILViT: Towards Robust and Generalizable Visual Backbones for MLLMs via Gradual Feature Refinementcited by 4
  14. 2023Context-Aware Classification of Legal Document Pagescited by 3
  15. 2025AdaLRS: Loss-Guided Adaptive Learning Rate Search for Efficient Foundation Model Pretrainingcited by 3
  16. 2024Can AI Models Appreciate Document Aesthetics? An Exploration of Legibility and Layout Quality in Relation to Prediction Confidencecited by 2
  17. 2024TAP-VL: Text Layout-Aware Pre-training for Enriched Vision-Language Modelscited by 1
  18. 2024Towards Multi-Modal Mastery: A 4.5B Parameter Truly Multi-Modal Small Language Modelcited by 1
  19. 2025Cross-Lingual SynthDocs: A Large-Scale Synthetic Corpus for Any to Arabic OCR and Document Understandingcited by 1
  20. 2026VersaViT: Enhancing MLLM Vision Backbones via Task-Guided Optimizationcited by 1
  21. 2025RWKV-UI: UI Understanding with Enhanced Perception and Reasoningcited by 0
  22. 2026VERSE: Visual Embedding Reduction and Space Exploration. Clustering-Guided Insights for Training Data Enhancement in Visually-Rich Document Understandingcited by 0
  23. 2026PubMed-OCR: PMC Open Access OCR Annotationscited by 0