mlsanityData to 7 Oct 2026

Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition

arXiv 1406.2227 ↗First posted 9 Jun 2014cs.CVcited by 214

Not on the map. Why?

Abstract (arXiv)

In this work we present a framework for the recognition of natural scene text. Our framework does not require any human-labelled data, and performs word recognition on the whole image holistically, departing from the character based recognition systems of the past. The deep neural network models at the centre of this framework are trained solely on data produced by a synthetic text generation engine -- synthetic data that is highly realistic and sufficient to replace real data, giving us infinite amounts of training data. This excess of data exposes new possibilities for word recognition models, and here we consider three models, each one "reading" words in a different way: via 90k-way dictionary encoding, character sequence encoding, and bag-of-N-grams encoding. In the scenarios of language based and completely unconstrained text recognition we greatly improve upon state-of-the-art performance on standard datasets, using our fast, simple machinery and requiring zero data-acquisition costs.

Key facts. Cited by 214 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Jun 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 47; 2022: 52; 2023: 45; 2024: 41; 2025: 17; 2026: 12.

214 papers.

Sort:

By area:

  1. 2022GIT: A Generative Image-to-text Transformer for Vision and Languagecited by 536
  2. 2023OCRBench: On the Hidden Mystery of OCR in Large Multimodal Modelscited by 466
  3. 2021OCR-free Document Understanding Transformercited by 400
  4. 2021TrOCR: Transformer-based Optical Character Recognition with Pre-trained Modelscited by 278
  5. 2023TextDiffuser: Diffusion Models as Text Painterscited by 223
  6. 2021Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognitioncited by 194
  7. 2021TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene textcited by 170
  8. 2022Scene Text Recognition with Permuted Autoregressive Sequence Modelscited by 148
  9. 2021From Two to One: A New Scene Text Recognizer with Visual Language Modeling Networkcited by 97
  10. 2023KOSMOS-2.5: A Multimodal Literate Modelcited by 95
  11. 2022SVTR: Scene Text Recognition with a Single Visual Modelcited by 86
  12. 2021Vision Transformer for Fast and Efficient Scene Text Recognitioncited by 81
38 more
  1. 2021What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labelscited by 63
  2. 2023Conditional Text Image Generation with Diffusion Modelscited by 57
  3. 2021Rethinking Text Line Recognition Modelscited by 45
  4. 2022Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognitioncited by 45
  5. 2022Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognitioncited by 45
  6. 2023Revisiting Scene Text Recognition: A Data Perspectivecited by 45
  7. 2021SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Modelscited by 43
  8. 2022ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spottingcited by 40
  9. 2021Text Prior Guided Scene Text Image Super-resolutioncited by 37
  10. 2024HRVDA: High-Resolution Visual Document Assistantcited by 37
  11. 2021CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognitioncited by 36
  12. 2022Multi-Granularity Prediction for Scene Text Recognitioncited by 36
  13. 2022Exploring Stroke-Level Modifications for Scene Text Editingcited by 36
  14. 2021Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Featurescited by 34
  15. 2022MaskOCR: Text Recognition with Masked Encoder-Decoder Pretrainingcited by 34
  16. 2022GLASS: Global to Local Attention for Scene-Text Spottingcited by 34
  17. 2023CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Modelcited by 30
  18. 2021Primitive Representation Learning for Scene Text Recognitioncited by 28
  19. 2022PreSTU: Pre-Training for Scene-Text Understandingcited by 27
  20. 2022Self-supervised Character-to-Character Distillation for Text Recognitioncited by 27
  21. 2021A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformercited by 26
  22. 2021Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognitioncited by 25
  23. 2022Self-supervised Implicit Glyph Attention for Text Recognitioncited by 25
  24. 2021Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognitioncited by 24
  25. 2022Levenshtein OCRcited by 24
  26. 2023ICDAR 2023 Competition on Hierarchical Text Detection and Recognitioncited by 23
  27. 2024SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognitioncited by 23
  28. 2022End-to-End Video Text Spotting with Transformercited by 21
  29. 2022General Intelligence Requires Rethinking Explorationcited by 20
  30. 2023Context Perception Parallel Decoder for Scene Text Recognitioncited by 19
  31. 2023Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognitioncited by 18
  32. 2023Attention Where It Matters: Rethinking Visual Document Understanding with Selective Region Concentrationcited by 18
  33. 2024Choose What You Need: Disentangled Representation Learning for Scene Text Recognition, Removal and Editingcited by 18
  34. 2021Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillationcited by 17
  35. 2024Instruction-Guided Scene Text Recognitioncited by 17
  36. 2022Multimodal Semi-Supervised Learning for Text Recognitioncited by 16
  37. 2023CLIPTER: Looking at the Bigger Picture in Scene Text Recognitioncited by 16
  38. 2023Scene Text Image Super-resolution based on Text-conditional Diffusion Modelscited by 15

50 most cited of 214 All 214 (JSON)