mlsanityData to 7 Oct 2026

Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning

arXiv 2207.11934 ↗First posted 25 Jul 2022cs.CVcited by 33

Not on the map. Why?

Abstract (arXiv)

Text detection and recognition are essential components of a modern OCR system. Most OCR approaches attempt to obtain accurate bounding boxes of text at the detection stage, which is used as the input of the text recognition stage. We observe that when using tight text bounding boxes as input, a text recognizer frequently fails to achieve optimal performance due to the inconsistency between bounding boxes and deep representations of text recognition. In this paper, we propose Box Adjuster, a reinforcement learning-based method for adjusting the shape of each text bounding box to make it more compatible with text recognition models. Additionally, when dealing with cross-domain problems such as synthetic-to-real, the proposed method significantly reduces mismatches in domain distribution between the source and target domains. Experiments demonstrate that the performance of end-to-end text recognition systems can be improved when using the adjusted bounding boxes as the ground truths for training. Specifically, on several benchmark datasets for scene text understanding, the proposed method outperforms state-of-the-art text spotters by an average of 2.0% F-Score on end-to-end text recognition tasks and 4.6% F-Score on domain adaptation tasks.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Builds on 31 of its 47 references that are in the map. First posted on arXiv 25 Jul 2022.

Builds on

31 of 47 references.

References · 31

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  6. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  7. 2015Spatial Transformer Networkscited by 1,423
  8. 2015An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognitioncited by 519
  9. 2016Synthetic Data for Text Localisation in Natural Imagescited by 396
  10. 2019Character Region Awareness for Text Detectioncited by 273
  11. 2017EAST: An Efficient and Accurate Scene Text Detectorcited by 248
  12. 2019Real-time Scene Text Detection with Differentiable Binarizationcited by 212
19 more
  1. 2020ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Networkcited by 170
  2. 2017Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognitioncited by 161
  3. 2019ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019cited by 138
  4. 2018Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognitioncited by 130
  5. 2019ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboardcited by 127
  6. 2014Reading Text in the Wild with Convolutional Neural Networkscited by 122
  7. 2016Robust Scene Text Recognition with Automatic Rectificationcited by 121
  8. 2016TextBoxes: A Fast Text Detector with a Single Deep Neural Networkcited by 119
  9. 2020Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spottingcited by 114
  10. 2018FOTS: Fast Oriented Text Spotting with a Unified Networkcited by 109
  11. 2022Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detectioncited by 65
  12. 2017Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networkscited by 56
  13. 2020Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spottingcited by 51
  14. 2018An end-to-end TextSpotter with Explicit Alignment and Attentioncited by 50
  15. 2021PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Networkcited by 49
  16. 2015Active Object Localization with Deep Reinforcement Learningcited by 42
  17. 2017Tree-Structured Reinforcement Learning for Sequential Object Localizationcited by 12
  18. 2017SEE: Towards Semi-Supervised End-to-End Scene Text Recognitioncited by 12
  19. 2017Collaborative Deep Reinforcement Learning for Joint Object Searchcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 8; 2026: 20.

33 papers.

Sort:

By area:

  1. 2024TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergycited by 70
  2. 2024TextSquare: Scaling up Text-Centric Visual Instruction Tuningcited by 62
  3. 2024Harmonizing Visual Text Comprehension and Generationcited by 54
  4. 2025Effects of Prompt Length on Domain-specific Tasks for Large Language Modelscited by 10
  5. 2025Journey into Automation: Image-Derived Pavement Texture Extraction and Evaluationcited by 7
  6. 2025A Comprehensive Review of AI Agents: Transforming Possibilities in Technology and Beyondcited by 6
  7. 2025Regression and Forecasting of U.S. Stock Returns Based on LSTMcited by 4
  8. 2025DREAM: Document Reconstruction via End-to-end Autoregressive Modelcited by 2
  9. 2024Efficiently Leveraging Linguistic Priors for Scene Text Spottingcited by 1
  10. 2025TDRI: Two-Phase Dialogue Refinement and Co-Adaptation for Interactive Image Generationcited by 1
  11. 2024Hear the Scene: Audio-Enhanced Text Spottingcited by 0
  12. 2025First-place Solution for Streetscape Shop Sign Recognition Competitioncited by 0
21 more
  1. 2025Cross-Modal Synergies: Unveiling the Potential of Motion-Aware Fusion Networks in Handling Dynamic and Static ReID Scenarioscited by 0
  2. 2026LPCAN: Lightweight Pyramid Cross-Attention Network for Rail Surface Defect Detection Using RGB-D Datacited by 0
  3. 2026Knowledge-Embedded and Hypernetwork-Guided Few-Shot Substation Meter Defect Image Generation Methodcited by 0
  4. 2026MA-LipNet: Multi-Dimensional Attention Networks for Robust Lipreadingcited by 0
  5. 2026The Diffusion Duet: Harmonizing Dual Channels with Wavelet Suppression for Image Separationcited by 0
  6. 2026Detecting Deepfakes with Multivariate Soft Blending and CLIP-based Image-Text Alignmentcited by 0
  7. 2026Efficient Image Super-Resolution with Multi-Scale Spatial Adaptive Attention Networkscited by 0
  8. 2026A Deformable Attention-Based Detection Transformer with Cross-Scale Feature Fusion for Industrial Coil Spring Inspectioncited by 0
  9. 2026Caption Generation for Dongba Paintings via Prompt Learning and Semantic Fusioncited by 0
  10. 2026Transmittance-Guided Structure-Texture Decomposition for Nighttime Image Dehazingcited by 0
  11. 2026Hierarchical Awareness Adapters with Hybrid Pyramid Feature Fusion for Dense Depth Predictioncited by 0
  12. 2026Adaptive Slicing-Assisted Hyper Inference for Enhanced Small Object Detection in High-Resolution Imagerycited by 0
  13. 2026Feature Perturbation Pool-based Fusion Network for Unified Multi-Class Industrial Defect Detectioncited by 0
  14. 2026Lightweight Real-Time Rendering Parameter Optimization via XGBoost-Driven Lookup Tablescited by 0
  15. 2026Image Classification via Random Dilated Convolution with Multi-Branch Feature Extraction and Context Excitationcited by 0
  16. 2026Gait Recognition via Deep Residual Networks and Multi-Branch Feature Fusioncited by 0
  17. 2026Local Spatiotemporal Convolutional Network for Robust Gait Recognitioncited by 0
  18. 2026Do You Need Text Rectification? Soft Attention Mask Embedding for Rectification-Free Scene Text Spottingcited by 0
  19. 2026ProWAFT: A ROMA-LPD Instance for Workload-Aware and Dynamic Fault Tolerance in FPGA-Based CNN Acceleratorscited by 0
  20. 2026Rank-Consistent Set Reasoning for Co-Salient Object Detectioncited by 0
  21. 2026Contour-Guided Spectral Routing for Robust Real-Time Pedestrian Detectioncited by 0