mlsanityData to 7 Oct 2026

Scene Text Detection and Recognition: The Deep Learning Era

arXiv 1811.04256 ↗First posted 10 Nov 2018cs.CVcited by 114

Not on the map. Why?

Abstract (arXiv)

With the rise and development of deep learning, computer vision has been tremendously transformed and reshaped. As an important research area in computer vision, scene text detection and recognition has been inescapably influenced by this wave of revolution, consequentially entering the era of deep learning. In recent years, the community has witnessed substantial advancements in mindset, approach and performance. This survey is aimed at summarizing and analyzing the major changes and significant progresses of scene text detection and recognition in the deep learning era. Through this article, we devote to: (1) introduce new insights and ideas; (2) highlight recent techniques and benchmarks; (3) look ahead into future trends. Specifically, we will emphasize the dramatic differences brought by deep learning and the grand challenges still remained. We expect that this review paper would serve as a reference book for researchers in this field. Related resources are also collected and compiled in our Github repository: https://github.com/Jyouhou/SceneTextPapers.

Key facts. Cited by 114 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 22; 2022: 22; 2023: 35; 2024: 10; 2025: 16; 2026: 9.

114 papers.

Sort:

By area:

  1. 2021Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognitioncited by 194
  2. 2022Scene Text Recognition with Permuted Autoregressive Sequence Modelscited by 148
  3. 2022Towards End-to-End Unified Scene Text Detection and Layout Analysiscited by 96
  4. 2022Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusioncited by 94
  5. 2022DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spottingcited by 74
  6. 2023Conditional Text Image Generation with Diffusion Modelscited by 57
  7. 2021TextStyleBrush: Transfer of Text Aesthetics from a Single Examplecited by 48
  8. 2021Rethinking Text Line Recognition Modelscited by 45
  9. 2023Vision Grid Transformer for Document Layout Analysiscited by 45
  10. 2023Turning a CLIP Model into a Scene Text Detectorcited by 44
  11. 2021SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Modelscited by 43
  12. 2022ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spottingcited by 40
38 more
  1. 2023GeoLayoutLM: Geometric Pre-training for Visual Information Extractioncited by 40
  2. 2023SODFormer: Streaming Object Detection with Transformer Using Events and Framescited by 39
  3. 2021CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognitioncited by 36
  4. 2022Multi-Granularity Prediction for Scene Text Recognitioncited by 36
  5. 2021MOST: A Multi-Oriented Scene Text Detector with Localization Refinementcited by 33
  6. 2023CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Modelcited by 30
  7. 2021A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformercited by 26
  8. 2021Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognitioncited by 24
  9. 2022Levenshtein OCRcited by 24
  10. 2023ICDAR 2023 Competition on Hierarchical Text Detection and Recognitioncited by 23
  11. 2024Visual Text Generation in the Wildcited by 22
  12. 2025Investigating Text Insulation and Attention Mechanisms for Complex Visual Text Generationcited by 22
  13. 2023Towards Real-World Writing Assistance: A Chinese Character Checking Benchmark with Faked and Misspelled Characterscited by 21
  14. 2023Diffusion in the Dark: A Diffusion Model for Low-Light Text Recognitioncited by 20
  15. 2023Modeling Entities as Semantic Points for Visual Information Extraction in the Wildcited by 20
  16. 2023Context Perception Parallel Decoder for Scene Text Recognitioncited by 19
  17. 2021A Multiplexed Network for End-to-End, Multilingual OCRcited by 18
  18. 2022Vision-Language Pre-Training for Boosting Scene Text Detectorscited by 18
  19. 2023Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognitioncited by 18
  20. 2025Visual Text Processing: A Comprehensive Review and Unified Evaluationcited by 18
  21. 2025HunyuanOCR Technical Reportcited by 18
  22. 2021Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillationcited by 17
  23. 2022Text-DIAE: A Self-Supervised Degradation Invariant Autoencoders for Text Recognition and Document Enhancementcited by 16
  24. 2022Multimodal Semi-Supervised Learning for Text Recognitioncited by 16
  25. 2023Improving Scene Text Image Super-resolution via Dual Prior Modulation Networkcited by 15
  26. 2022Seq-UPS: Sequential Uncertainty-aware Pseudo-label Selection for Semi-Supervised Text Recognitioncited by 14
  27. 2026HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Bettercited by 14
  28. 2023Scalable Mask Annotation for Video Text Spottingcited by 13
  29. 2023LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognitioncited by 13
  30. 2023Towards Robust Real-Time Scene Text Detection: From Semantic to Instance Representation Learningcited by 12
  31. 2024DNTextSpotter: Arbitrary-Shaped Scene Text Spotting via Improved Denoising Trainingcited by 11
  32. 2023TextDiff: Mask-Guided Residual Diffusion Models for Scene Text Image Super-Resolutioncited by 10
  33. 2024Class-Aware Mask-Guided Feature Refinement for Scene Text Recognitioncited by 10
  34. 2025VidText: Towards Comprehensive Evaluation for Video Text Understandingcited by 10
  35. 2022Pure Transformer with Integrated Experts for Scene Text Recognitioncited by 9
  36. 2023TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognitioncited by 9
  37. 2026Towards Long-horizon Agentic Multimodal Searchcited by 9
  38. 2023Self-distillation Regularized Connectionist Temporal Classification Loss for Text Recognition: A Simple Yet Effective Approachcited by 8

50 most cited of 114 All 114 (JSON)