mlsanityData to 7 Oct 2026

DAN: a Segmentation-free Document Attention Network for Handwritten Document Recognition

arXiv 2203.12273 ↗First posted 23 Mar 2022cs.CVcited by 62

Not on the map. Why?

Abstract (arXiv)

Unconstrained handwritten text recognition is a challenging computer vision task. It is traditionally handled by a two-step approach, combining line segmentation followed by text line recognition. For the first time, we propose an end-to-end segmentation-free architecture for the task of handwritten document recognition: the Document Attention Network. In addition to text recognition, the model is trained to label text parts using begin and end tags in an XML-like fashion. This model is made up of an FCN encoder for feature extraction and a stack of transformer decoder layers for a recurrent token-by-token prediction process. It takes whole text documents as input and sequentially outputs characters, as well as logical layout tokens. Contrary to the existing segmentation-based approaches, the model is trained without using any segmentation label. We achieve competitive results on the READ 2016 dataset at page level, as well as double-page level with a CER of 3.43% and 3.70%, respectively. We also provide results for the RIMES 2009 dataset at page level, reaching 4.54% of CER. We provide all source code and pre-trained model weights at https://github.com/FactoDeepLearning/DAN.

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). Builds on 33 of its 56 references that are in the map. First posted on arXiv 23 Mar 2022.

Builds on

33 of 56 references.

References · 33

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  6. 2015An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognitioncited by 519
  7. 2020LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understandingcited by 406
  8. 2021TrOCR: Transformer-based Optical Character Recognition with Pre-trained Modelscited by 278
  9. 2021Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformercited by 134
  10. 2018Chargrid: Towards Understanding 2D Documentscited by 100
  11. 2017Learning to Extract Semantic Structure from Documents Using Multimodal Fully Convolutional Neural Networkcited by 92
  12. 2021Vision Transformer for Fast and Efficient Scene Text Recognitioncited by 81
21 more
  1. 2020Pay Attention to What You Read: Non-recurrent Handwritten Text-Line Recognitioncited by 71
  2. 2019BERTgrid: Contextualized Embedding for 2D Document Representation and Understandingcited by 63
  3. 2019Evaluating Sequence-to-Sequence Models for Handwritten Text Recognitioncited by 58
  4. 2020OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfoldcited by 53
  5. 2017Curriculum Dropoutcited by 50
  6. 2020End-to-end Handwritten Paragraph Text Recognition Using a Vertical Attention Networkcited by 50
  7. 2016Joint Line Segmentation and Transcription for End-to-End Handwritten Paragraph Recognitioncited by 46
  8. 2016Scan, Attend and Read: End-to-End Handwritten Paragraph Recognition with MDLSTM Attentioncited by 45
  9. 2021Handwritten Mathematical Expression Recognition with Bidirectionally Trained Transformercited by 34
  10. 2018dhSegment: A generic deep-learning approach for document segmentationcited by 32
  11. 2018A Two-Stage Method for Text Line Detection in Historical Documentscited by 26
  12. 2021Full Page Handwriting Recognition via Image to Sequence Extractioncited by 24
  13. 2020Recurrence-free unconstrained handwritten text recognition using gated fully convolutional networkcited by 23
  14. 2021SPAN: a Simple Predict & Align Network for Handwritten Paragraph Recognitioncited by 19
  15. 2021DocSynth: A Layout Guided Approach for Controllable Document Image Synthesiscited by 17
  16. 2021Transformer-Based Approach for Joint Handwriting and Named Entity Recognition in Historical documentscited by 17
  17. 2019A Neural Model for Text Localization, Transcription and Named Entity Recognition in Full Pagescited by 16
  18. 2020Multiple Document Datasets Pre-training Improves Text Line Detection With Deep Neural Networkscited by 11
  19. 2019A Computationally Efficient Pipeline Approach to Full Page Offline Handwritten Text Recognitioncited by 9
  20. 2018Multi-Task Handwritten Document Layout Analysiscited by 8
  21. 2020Have convolutions already made recurrence obsolete for unconstrained handwritten text recognition ?cited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 12; 2024: 19; 2025: 16; 2026: 15.

62 papers.

Sort:

By area:

  1. 2023Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth Evaluationcited by 46
  2. 2024Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentationcited by 30
  3. 2024HTR-VT: Handwritten Text Recognition with Vision Transformercited by 24
  4. 2024Sheet Music Transformer: End-To-End Optical Music Recognition Beyond Monophonic Transcriptioncited by 20
  5. 2024End-to-End Full-Page Optical Music Recognition for Pianoform Sheet Musiccited by 13
  6. 2024RoDLA: Benchmarking the Robustness of Document Layout Analysis Modelscited by 12
  7. 2025Handwritten Text Recognition: A Surveycited by 12
  8. 2025Multimodal LLMs for OCR, OCR Post-Correction, and Named Entity Recognition in Historical Documentscited by 12
  9. 2025Benchmarking Large Language Models for Handwritten Text Recognitioncited by 11
  10. 2024On the Generalization of Handwritten Text Recognition Modelscited by 10
  11. 2023Faster DAN: Multi-target Queries with Document Positional Encoding for End-to-end Handwritten Document Recognitioncited by 9
  12. 2023Key-value information extraction from full handwritten pagescited by 9
38 more
  1. 2024DANIEL: A fast Document Attention Network for Information Extraction and Labelling of handwritten documentscited by 9
  2. 2023End-to-End Page-Level Assessment of Handwritten Text Recognitioncited by 8
  3. 2024Multi-Page Document Visual Question Answering using Self-Attention Scoring Mechanismcited by 8
  4. 2023MSdocTr-Lite: A Lite Transformer for Full Page Multi-script Handwriting Recognitioncited by 7
  5. 2023SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentationcited by 7
  6. 2024Improving Automatic Text Recognition with Language Models in the PyLaia Open-Source Librarycited by 5
  7. 2023Large Scale Genealogical Information Extraction From Handwritten Quebec Parish Recordscited by 4
  8. 2024The Socface Project: Large-Scale Collection, Processing, and Analysis of a Century of French Censusescited by 4
  9. 2024End-to-end information extraction in handwritten documents: Understanding Paris marriage records from 1880 to 1940cited by 4
  10. 2024General Detection-based Text Line Recognitioncited by 4
  11. 2024Self-Supervised Learning for Text Recognition: A Critical Surveycited by 3
  12. 2025DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learningcited by 3
  13. 2025UniHDSA: A Unified Relation Prediction Approach for Hierarchical Document Structure Analysiscited by 3
  14. 2025Meta-DAN: towards an efficient prediction strategy for page-level handwritten text recognitioncited by 3
  15. 2025CM1 -- A Dataset for Evaluating Few-Shot Information Extraction with Large Vision Language Modelscited by 3
  16. 2025Normalized vs Diplomatic Annotation: A Case Study of Automatic Information Extraction from Handwritten Uruguayan Birth Certificatescited by 3
  17. 2025Improving OCR using internal document redundancycited by 3
  18. 2024GraphKD: Exploring Knowledge Distillation Towards Document Object Detection with Structured Graph Creationcited by 2
  19. 2024Reading Order Independent Metrics for Information Extraction in Handwritten Documentscited by 2
  20. 2024Revisiting N-Gram Models: Their Impact in Modern Neural Networks for Handwritten Text Recognitioncited by 2
  21. 2025PILOT: A Promptable Interleaved Layout-aware OCR Transformercited by 2
  22. 2025MetaWriter: Personalized Handwritten Text Recognition Using Meta-Learned Prompt Tuningcited by 2
  23. 2023Entry Separation using a Mixed Visual and Textual Language Model: Application to 19th century French Trade Directoriescited by 1
  24. 2023Handwritten Text Recognition from Crowdsourced Annotationscited by 1
  25. 2024Spatial Context-based Self-Supervised Learning for Handwritten Text Recognitioncited by 1
  26. 2024GatedLexiconNet: A Comprehensive End-to-End Handwritten Paragraph Text Recognition Systemcited by 1
  27. 2025RVAFM: Re-parameterizing Vertical Attention Fusion Module for Handwritten Paragraph Text Recognitioncited by 1
  28. 2025Classifying the Unknown: In-Context Learning for Open-Vocabulary Text and Symbol Recognitioncited by 1
  29. 2025Relaxed syntax modeling in Transformers for future-proof license plate recognitioncited by 1
  30. 2026Few-shot Writer Adaptation via Multimodal In-Context Learningcited by 1
  31. 2026A Benchmark of State-Space Models vs. Transformers and BiLSTM-based Models for Historical Newspaper OCRcited by 1
  32. 2026Transcoda: End-to-End Zero-Shot Optical Music Recognition via Data-Centric Synthetic Trainingcited by 1
  33. 2023SIMARA: a database for key-value information extraction from full pagescited by 0
  34. 2023Leveraging Vision-Language Foundation Models for Fine-Grained Downstream Taskscited by 0
  35. 2023Proceedings of the 5th International Workshop on Reading Music Systemscited by 0
  36. 2024Improving Handwritten Text Recognition via 3D Attention and Multi-Scale Trainingcited by 0
  37. 2025Optimal Transport for Handwritten Text Recognition in a Low-Resource Regimecited by 0
  38. 2025HybriDLA: Hybrid Generation for Document Layout Analysiscited by 0

50 most cited of 62 All 62 (JSON)