mlsanityData to 7 Oct 2026

Text Spotting Transformers

arXiv 2204.01918 ↗First posted 5 Apr 2022cs.CVcited by 70

Not on the map. Why?

Abstract (arXiv)

In this paper, we present TExt Spotting TRansformers (TESTR), a generic end-to-end text spotting framework using Transformers for text detection and recognition in the wild. TESTR builds upon a single encoder and dual decoders for the joint text-box control point regression and character recognition. Other than most existing literature, our method is free from Region-of-Interest operations and heuristics-driven post-processing procedures; TESTR is particularly effective when dealing with curved text-boxes where special cares are needed for the adaptation of the traditional bounding-box representations. We show our canonical representation of control points suitable for text instances in both Bezier curve and polygon annotations. In addition, we design a bounding-box guided polygon detection (box-to-polygon) process. Experiments on curved and arbitrarily shaped datasets demonstrate state-of-the-art performances of the proposed TESTR algorithm.

Key facts. Cited by 70 papers in the map (data through 7 Oct 2026). Builds on 37 of its 53 references that are in the map. First posted on arXiv 5 Apr 2022.

Builds on

37 of 53 references.

References · 37

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2017Mask R-CNNcited by 7,259
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  8. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  9. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  10. 2017Focal Loss for Dense Object Detectioncited by 749
  11. 2015An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognitioncited by 519
  12. 2019Character Region Awareness for Text Detectioncited by 273
25 more
  1. 2017EAST: An Efficient and Accurate Scene Text Detectorcited by 248
  2. 2019Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapescited by 171
  3. 2020ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Networkcited by 170
  4. 2019ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019cited by 138
  5. 2016Robust Scene Text Recognition with Automatic Rectificationcited by 121
  6. 2016TextBoxes: A Fast Text Detector with a Single Deep Neural Networkcited by 119
  7. 2018TextBoxes++: A Single-Shot Oriented Scene Text Detectorcited by 119
  8. 2020Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spottingcited by 114
  9. 2018FOTS: Fast Oriented Text Spotting with a Unified Networkcited by 109
  10. 2021Pose Recognition with Cascade Transformerscited by 99
  11. 2016Detecting Text in Natural Image with Connectionist Text Proposal Networkcited by 85
  12. 2021ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spottingcited by 84
  13. 2016Recursive Recurrent Nets with Attention Modeling for OCR in the Wildcited by 74
  14. 2021Line Segment Detection Using Transformers without Edgescited by 73
  15. 2019All You Need Is Boundary: Toward Arbitrary-Shaped Text Spottingcited by 66
  16. 2019Convolutional Character Networkscited by 61
  17. 2019Towards Unconstrained End-to-End Text Spottingcited by 57
  18. 2017Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networkscited by 56
  19. 2020Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spottingcited by 51
  20. 2020MANGO: A Mask Attention Guided One-Stage Scene Text Spottercited by 51
  21. 2018An end-to-end TextSpotter with Explicit Alignment and Attentioncited by 50
  22. 2021PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Networkcited by 49
  23. 2019Arbitrary Shape Scene Text Detection with Adaptive Text Region Representationcited by 45
  24. 2021Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queriescited by 31
  25. 2018TextNet: Irregular Text Reading from Images with an End-to-End Trainable Networkcited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 11; 2023: 20; 2024: 21; 2025: 14; 2026: 4.

70 papers.

Sort:

By area:

  1. 2024OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoningcited by 165
  2. 2022DETRs with Hybrid Matchingcited by 149
  3. 2022DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spottingcited by 74
  4. 2024OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognitioncited by 74
  5. 2023SPTS v2: Single-Point Scene Text Spottingcited by 66
  6. 2022DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformercited by 50
  7. 2022Connecting the Dots: Floorplan Reconstruction Using Two-Level Queriescited by 48
  8. 2024Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentationcited by 30
  9. 2023ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformercited by 29
  10. 2023Towards Unified Scene Text Spotting based on Sequence Generationcited by 27
  11. 2025OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Modelscited by 22
  12. 2023Scalable Mask Annotation for Video Text Spottingcited by 13
38 more
  1. 2024GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matchingcited by 12
  2. 2022Out-of-Vocabulary Challenge Reportcited by 11
  3. 2024DNTextSpotter: Arbitrary-Shaped Scene Text Spotting via Improved Denoising Trainingcited by 11
  4. 2023Turning a CLIP Model into a Scene Text Spottercited by 9
  5. 2024Inverse-like Antagonistic Scene Text Spotting via Reading-Order Estimation and Dynamic Samplingcited by 9
  6. 2024Bridging the Gap Between End-to-End and Two-Step Text Spottingcited by 9
  7. 2023Hierarchical Text Spotter for Joint Text Spotting and Layout Analysiscited by 8
  8. 2023DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spottingcited by 7
  9. 2023The mapKurator System: A Complete Pipeline for Extracting and Linking Text from Historical Mapscited by 7
  10. 2023A3S: Adversarial learning of semantic representations for Scene-Text Spottingcited by 6
  11. 2024SwinTextSpotter v2: Towards Better Synergy for Scene Text Spottingcited by 5
  12. 2024TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Modelcited by 5
  13. 2025Text-Aware Image Restoration with Diffusion Modelscited by 5
  14. 2023MixNet: Toward Accurate Detection of Challenging Scene Text in the Wildcited by 4
  15. 2024General Detection-based Text Line Recognitioncited by 4
  16. 2025GoMatching++: Parameter- and Data-Efficient Arbitrary-Shaped Video Text Spotting and Benchmarkingcited by 4
  17. 2025LRANet++: Low-Rank Approximation Network for Accurate and Efficient Text Spottingcited by 4
  18. 2023PBFormer: Capturing Complex Scene Text Shape with Polynomial Band Transformercited by 3
  19. 2023SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gapcited by 3
  20. 2024WeCromCL: Weakly Supervised Cross-Modality Contrastive Learning for Transcription-only Supervised Text Spottingcited by 3
  21. 2022Text Detection & Recognition in the Wild for Robot Localizationcited by 2
  22. 2023Selective Scene Text Removalcited by 2
  23. 2023STEP -- Towards Structured Scene-Text Spottingcited by 2
  24. 2023Diving into the Depths of Spotting Text in Multi-Domain Noisy Scenescited by 2
  25. 2024Text Grouping Adapter: Adapting Pre-trained Text Detector for Layout Analysiscited by 2
  26. 2024SegHist: A General Segmentation-based Framework for Chinese Historical Document Text Line Detectioncited by 2
  27. 2024Platypus: A Generalized Specialist Model for Reading Text in Various Formscited by 2
  28. 2024FastTextSpotter: A High-Efficiency Transformer for Multilingual Scene Text Spottingcited by 2
  29. 2025PILOT: A Promptable Interleaved Layout-aware OCR Transformercited by 2
  30. 2025SemiETS: Integrating Spatial and Content Consistencies for Semi-Supervised End-to-end Text Spottingcited by 2
  31. 2025TextMamba: Scene Text Detector with Mambacited by 2
  32. 2025Unified Diffusion Transformer for High-fidelity Text-Aware Image Restorationcited by 2
  33. 2022Single Shot Self-Reliant Scene Text Spotter by Decoupled yet Collaborative Detection and Recognitioncited by 1
  34. 2022Runner-Up Solution to ECCV 2022 Challenge on Out of Vocabulary Scene Text Understanding: Cropped Word Recognitioncited by 1
  35. 2023Keyword Spotting Simplified: A Segmentation-Free Approach using Character Counting and CTC re-scoringcited by 1
  36. 2023Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting Performancecited by 1
  37. 2023Progressive Evolution from Single-Point to Polygon for Scene Textcited by 1
  38. 2024Dynamic Relation Transformer for Contextual Text Block Detectioncited by 1

50 most cited of 70 All 70 (JSON)