mlsanityData to 7 Oct 2026

SCATTER: Selective Context Attentional Scene Text Recognizer

arXiv 2003.11288 ↗First posted 25 Mar 2020cs.CVcited by 69

Not on the map. Why?

Abstract (arXiv)

Scene Text Recognition (STR), the task of recognizing text against complex image backgrounds, is an active area of research. Current state-of-the-art (SOTA) methods still struggle to recognize text written in arbitrary shapes. In this paper, we introduce a novel architecture for STR, named Selective Context ATtentional Text Recognizer (SCATTER). SCATTER utilizes a stacked block architecture with intermediate supervision during training, that paves the way to successfully train a deep BiLSTM encoder, thus improving the encoding of contextual dependencies. Decoding is done using a two-step 1D attention mechanism. The first attention step re-weights visual features from a CNN backbone together with contextual features computed by a BiLSTM layer. The second attention step, similar to previous papers, treats the features as a sequence and attends to the intra-sequence relationships. Experiments show that the proposed approach surpasses SOTA performance on irregular text recognition benchmarks by 3.7% on average.

Key facts. Cited by 69 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 25; 2022: 17; 2023: 11; 2024: 14; 2025: 2.

69 papers.

Sort:

By area:

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  2. 2021TrOCR: Transformer-based Optical Character Recognition with Pre-trained Modelscited by 278
  3. 2021DocFormer: End-to-End Transformer for Document Understandingcited by 254
  4. 2022Scene Text Recognition with Permuted Autoregressive Sequence Modelscited by 148
  5. 2021ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spottingcited by 84
  6. 2021Vision Transformer for Fast and Efficient Scene Text Recognitioncited by 81
  7. 2021LaTr: Layout-Aware Transformer for Scene-Text VQAcited by 72
  8. 2021What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labelscited by 63
  9. 2023DocFormerv2: Local Features for Document Understandingcited by 46
  10. 2021Rethinking Text Line Recognition Modelscited by 45
  11. 2022Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognitioncited by 45
  12. 2024Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extractioncited by 44
38 more
  1. 2021PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognitioncited by 41
  2. 2024Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworkscited by 41
  3. 2024M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitionscited by 38
  4. 2022OCR-IDL: OCR Annotations for Industry Document Library Datasetcited by 35
  5. 2022GLASS: Global to Local Attention for Scene-Text Spottingcited by 34
  6. 2021Primitive Representation Learning for Scene Text Recognitioncited by 28
  7. 2021MetaHTR: Towards Writer-Adaptive Handwritten Text Recognitioncited by 27
  8. 2022Self-supervised Character-to-Character Distillation for Text Recognitioncited by 27
  9. 2024DocVLM: Make Your VLM an Efficient Readercited by 27
  10. 2021Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognitioncited by 25
  11. 2021Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognitioncited by 24
  12. 2024GRAM: Global Reasoning for Multi-Page VQAcited by 23
  13. 2021Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillationcited by 17
  14. 2022Text-DIAE: A Self-Supervised Degradation Invariant Autoencoders for Text Recognition and Document Enhancementcited by 16
  15. 2022Multimodal Semi-Supervised Learning for Text Recognitioncited by 16
  16. 2023CLIPTER: Looking at the Bigger Picture in Scene Text Recognitioncited by 16
  17. 2023Towards Models that Can See and Readcited by 15
  18. 2022Seq-UPS: Sequential Uncertainty-aware Pseudo-label Selection for Semi-Supervised Text Recognitioncited by 14
  19. 2024Layout Agnostic Scene Text Image Synthesis with Diffusion Modelscited by 14
  20. 2021Towards the Unseen: Iterative Text Recognition by Distilling from Errorscited by 12
  21. 2022Towards Open-Set Text Recognition via Label-to-Prototype Learningcited by 12
  22. 2023CLIPAG: Towards Generator-Free Text-to-Image Generationcited by 12
  23. 2023IPAD: Iterative, Parallel, and Diffusion-based Network for Scene Text Recognitioncited by 12
  24. 2024EvoWiki: Evaluating LLMs on Evolving Knowledgecited by 12
  25. 2021TextAdaIN: Paying Attention to Shortcut Learning in Text Recognizerscited by 11
  26. 2022Out-of-Vocabulary Challenge Reportcited by 11
  27. 2024Inverse-like Antagonistic Scene Text Spotting via Reading-Order Estimation and Dynamic Samplingcited by 9
  28. 2022Open-set Text Recognition via Character-Context Decouplingcited by 8
  29. 2024Self-Supervised Pre-training with Symmetric Superimposition Modeling for Scene Text Recognitioncited by 8
  30. 2021Representation and Correlation Enhanced Encoder-Decoder Framework for Scene Text Recognitioncited by 6
  31. 2021Revisiting Classification Perspective on Scene Text Recognitioncited by 5
  32. 2021FEDS -- Filtered Edit Distance Surrogatecited by 5
  33. 2021I2C2W: Image-to-Character-to-Word Transformers for Accurate Scene Text Recognitioncited by 5
  34. 2021Implicit Feature Alignment: Learn to Convert Text Recognizer to Text Spottercited by 5
  35. 2021Data Augmentation for Scene Text Recognitioncited by 5
  36. 2021Visual-Semantic Transformer for Scene Text Recognitioncited by 5
  37. 2023Weakly supervised information extraction from inscrutable handwritten document imagescited by 4
  38. 2024A + B: A General Generator-Reader Framework for Optimizing LLMs to Unleash Synergy Potentialcited by 3

50 most cited of 69 All 69 (JSON)