mlsanityData to 7 Oct 2026

An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition

arXiv 1507.05717 ↗First posted 21 Jul 2015cs.CVcited by 519

Not on the map. Why?

Cited by 21 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Image-based sequence recognition has been a long-standing research topic in computer vision. In this paper, we investigate the problem of scene text recognition, which is among the most important and challenging tasks in image-based sequence recognition. A novel neural network architecture, which integrates feature extraction, sequence modeling and transcription into a unified framework, is proposed. Compared with previous systems for scene text recognition, the proposed architecture possesses four distinctive properties: (1) It is end-to-end trainable, in contrast to most of the existing algorithms whose components are separately trained and tuned. (2) It naturally handles sequences in arbitrary lengths, involving no character segmentation or horizontal scale normalization. (3) It is not confined to any predefined lexicon and achieves remarkable performances in both lexicon-free and lexicon-based scene text recognition tasks. (4) It generates an effective yet much smaller model, which is more practical for real-world application scenarios. The experiments on standard benchmarks, including the IIIT-5K, Street View Text and ICDAR datasets, demonstrate the superiority of the proposed algorithm over the prior arts. Moreover, the proposed algorithm performs well in the task of image-based music score recognition, which evidently verifies the generality of it.

Key facts. Cited by 519 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Jul 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 83; 2022: 105; 2023: 109; 2024: 81; 2025: 65; 2026: 76.

519 papers.

Sort:

By area:

  1. 2021OCR-free Document Understanding Transformercited by 400
  2. 2021MOTR: End-to-End Multiple-Object Tracking with Transformercited by 379
  3. 2021TrOCR: Transformer-based Optical Character Recognition with Pre-trained Modelscited by 278
  4. 2023TextDiffuser: Diffusion Models as Text Painterscited by 223
  5. 2021Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognitioncited by 194
  6. 2021WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognitioncited by 189
  7. 2021TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene textcited by 170
  8. 2024OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoningcited by 165
  9. 2022Scene Text Recognition with Permuted Autoregressive Sequence Modelscited by 148
  10. 2023TextDiffuser-2: Unleashing the Power of Language Models for Text Renderingcited by 136
  11. 2025PaddleOCR 3.0 Technical Reportcited by 136
  12. 2023DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understandingcited by 106
38 more
  1. 2022PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR Systemcited by 105
  2. 2021From Two to One: A New Scene Text Recognizer with Visual Language Modeling Networkcited by 97
  3. 2024LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understandingcited by 94
  4. 2021StrucTexT: Structured Text Understanding with Multi-Modal Transformerscited by 90
  5. 2022SVTR: Scene Text Recognition with a Single Visual Modelcited by 86
  6. 2021ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spottingcited by 84
  7. 2021TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrievalcited by 81
  8. 2021Vision Transformer for Fast and Efficient Scene Text Recognitioncited by 81
  9. 2024OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognitioncited by 74
  10. 2022SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognitioncited by 70
  11. 2022Text Spotting Transformerscited by 70
  12. 2022Syntax-Aware Network for Handwritten Mathematical Expression Recognitioncited by 68
  13. 2023SPTS v2: Single-Point Scene Text Spottingcited by 66
  14. 2021PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Textcited by 65
  15. 2021What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labelscited by 63
  16. 2022DAN: a Segmentation-free Document Attention Network for Handwritten Document Recognitioncited by 62
  17. 2023DocILE Benchmark for Document Information Localization and Extractioncited by 58
  18. 2023Conditional Text Image Generation with Diffusion Modelscited by 57
  19. 2021Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Studycited by 52
  20. 2024From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Modelscited by 52
  21. 2021PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Networkcited by 49
  22. 2021Robust Open-Vocabulary Translation from Visual Text Representationscited by 47
  23. 2021Open Images V5 Text Annotation and Yet Another Mask Text Spottercited by 46
  24. 2023Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth Evaluationcited by 46
  25. 2021Rethinking Text Line Recognition Modelscited by 45
  26. 2022Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognitioncited by 45
  27. 2022Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognitioncited by 45
  28. 2023Revisiting Scene Text Recognition: A Data Perspectivecited by 45
  29. 2023Vision Grid Transformer for Document Layout Analysiscited by 45
  30. 2024Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extractioncited by 44
  31. 2021PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognitioncited by 41
  32. 2022Towards Weakly-Supervised Text Spotting using a Multi-Task Transformercited by 41
  33. 2021MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understandingcited by 40
  34. 2022ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spottingcited by 40
  35. 2023GeoLayoutLM: Geometric Pre-training for Visual Information Extractioncited by 40
  36. 2023DTrOCR: Decoder-only Transformer for Optical Character Recognitioncited by 40
  37. 2021PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR Systemcited by 39
  38. 2021Handwriting Transformerscited by 37

50 most cited of 519 All 519 (JSON)