mlsanityData to 7 Oct 2026

What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis

arXiv 1904.01906 ↗First posted 3 Apr 2019cs.CVcited by 191

Not on the map. Why?

Abstract (arXiv)

Many new proposals for scene text recognition (STR) models have been introduced in recent years. While each claim to have pushed the boundary of the technology, a holistic and fair comparison has been largely missing in the field due to the inconsistent choices of training and evaluation datasets. This paper addresses this difficulty with three major contributions. First, we examine the inconsistencies of training and evaluation datasets, and the performance gap results from inconsistencies. Second, we introduce a unified four-stage STR framework that most existing STR models fit into. Using this framework allows for the extensive evaluation of previously proposed STR modules and the discovery of previously unexplored module combinations. Third, we analyze the module-wise contributions to performance in terms of accuracy, speed, and memory demand, under one consistent set of training and evaluation datasets. Such analyses clean up the hindrance on the current comparisons to understand the performance gain of the existing modules.

Key facts. Cited by 191 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 46; 2022: 42; 2023: 42; 2024: 29; 2025: 15; 2026: 17.

191 papers.

Sort:

By area:

  1. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,449
  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. 2021Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognitioncited by 194
  6. 2021TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene textcited by 170
  7. 2022Chart-to-Text: A Large-Scale Benchmark for Chart Summarizationcited by 166
  8. 2022Scene Text Recognition with Permuted Autoregressive Sequence Modelscited by 148
  9. 2022SVTR: Scene Text Recognition with a Single Visual Modelcited by 86
  10. 2021Vision Transformer for Fast and Efficient Scene Text Recognitioncited by 81
  11. 2021LaTr: Layout-Aware Transformer for Scene-Text VQAcited by 72
  12. 2021What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labelscited by 63
38 more
  1. 2023Conditional Text Image Generation with Diffusion Modelscited by 57
  2. 2023Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizercited by 53
  3. 2021Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Studycited by 52
  4. 2021PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Networkcited by 49
  5. 2021TextStyleBrush: Transfer of Text Aesthetics from a Single Examplecited by 48
  6. 2021Rethinking Text Line Recognition Modelscited by 45
  7. 2022Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognitioncited by 45
  8. 2023Revisiting Scene Text Recognition: A Data Perspectivecited by 45
  9. 2024TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Controlcited by 44
  10. 2021SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Modelscited by 43
  11. 2021PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognitioncited by 41
  12. 2022ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spottingcited by 40
  13. 2024OneChart: Purify the Chart Structural Extraction via One Auxiliary Tokencited by 39
  14. 2021CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognitioncited by 36
  15. 2022Multi-Granularity Prediction for Scene Text Recognitioncited by 36
  16. 2022Exploring Stroke-Level Modifications for Scene Text Editingcited by 36
  17. 2021Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Featurescited by 34
  18. 2022GLASS: Global to Local Attention for Scene-Text Spottingcited by 34
  19. 2021Primitive Representation Learning for Scene Text Recognitioncited by 28
  20. 2021MetaHTR: Towards Writer-Adaptive Handwritten Text Recognitioncited by 27
  21. 2022Self-supervised Character-to-Character Distillation for Text Recognitioncited by 27
  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. 2024SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognitioncited by 23
  27. 2022On the Cross-dataset Generalization in License Plate Recognitioncited by 22
  28. 2026AgentOCR: Reimagining Agent History via Optical Self-Compressioncited by 22
  29. 2022SimAN: Exploring Self-Supervised Representation Learning of Scene Text via Similarity-Aware Normalizationcited by 21
  30. 2022Improving End-to-End Text Image Translation From the Auxiliary Text Translation Taskcited by 20
  31. 2023DocParser: End-to-end OCR-free Information Extraction from Visually Rich Documentscited by 19
  32. 2023Context Perception Parallel Decoder for Scene Text Recognitioncited by 19
  33. 2023Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognitioncited by 18
  34. 2021Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillationcited by 17
  35. 2022Multimodal Semi-Supervised Learning for Text Recognitioncited by 16
  36. 2023CLIPTER: Looking at the Bigger Picture in Scene Text Recognitioncited by 16
  37. 2022Towards Benchmarking and Evaluating Deepfake Detectioncited by 15
  38. 2022Seq-UPS: Sequential Uncertainty-aware Pseudo-label Selection for Semi-Supervised Text Recognitioncited by 14

50 most cited of 191 All 191 (JSON)