mlsanityData to 7 Oct 2026

Character Region Awareness for Text Detection

arXiv 1904.01941 ↗First posted 3 Apr 2019cs.CVcited by 273

Not on the map. Why?

Abstract (arXiv)

Scene text detection methods based on neural networks have emerged recently and have shown promising results. Previous methods trained with rigid word-level bounding boxes exhibit limitations in representing the text region in an arbitrary shape. In this paper, we propose a new scene text detection method to effectively detect text area by exploring each character and affinity between characters. To overcome the lack of individual character level annotations, our proposed framework exploits both the given character-level annotations for synthetic images and the estimated character-level ground-truths for real images acquired by the learned interim model. In order to estimate affinity between characters, the network is trained with the newly proposed representation for affinity. Extensive experiments on six benchmarks, including the TotalText and CTW-1500 datasets which contain highly curved texts in natural images, demonstrate that our character-level text detection significantly outperforms the state-of-the-art detectors. According to the results, our proposed method guarantees high flexibility in detecting complicated scene text images, such as arbitrarily-oriented, curved, or deformed texts.

Key facts. Cited by 273 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: 61; 2023: 44; 2024: 53; 2025: 39; 2026: 30.

273 papers.

Sort:

By area:

  1. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  2. 2021OCR-free Document Understanding Transformercited by 400
  3. 2025SkyReels-V2: Infinite-length Film Generative Modelcited by 218
  4. 2022Chart-to-Text: A Large-Scale Benchmark for Chart Summarizationcited by 166
  5. 2023UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoningcited by 158
  6. 2023Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generationcited by 153
  7. 2024Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenizationcited by 98
  8. 2022Towards End-to-End Unified Scene Text Detection and Layout Analysiscited by 96
  9. 2022Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusioncited by 94
  10. 2021ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spottingcited by 84
  11. 2021Fourier Contour Embedding for Arbitrary-Shaped Text Detectioncited by 80
  12. 2024OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generationcited by 77
38 more
  1. 2024EasyAnimate: High-Performance Video Generation Framework with Hybrid Windows Attention and Reward Backpropagationcited by 76
  2. 2024A Survey of Multimodal Large Language Model from A Data-centric Perspectivecited by 73
  3. 2022Text Spotting Transformerscited by 70
  4. 2024ToonCrafter: Generative Cartoon Interpolationcited by 68
  5. 2024Allegro: Open the Black Box of Commercial-Level Video Generation Modelcited by 68
  6. 2023SPTS v2: Single-Point Scene Text Spottingcited by 66
  7. 2021PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Textcited by 65
  8. 2022Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detectioncited by 65
  9. 2021LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysiscited by 58
  10. 2024From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Modelscited by 52
  11. 2024From Pixels to Prose: A Large Dataset of Dense Image Captionscited by 52
  12. 2022DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformercited by 50
  13. 2021Adaptive Boundary Proposal Network for Arbitrary Shape Text Detectioncited by 47
  14. 2021SPTS: Single-Point Text Spottingcited by 45
  15. 2023Turning a CLIP Model into a Scene Text Detectorcited by 44
  16. 2024Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extractioncited by 44
  17. 2021MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understandingcited by 40
  18. 2022GLASS: Global to Local Attention for Scene-Text Spottingcited by 34
  19. 2021MOST: A Multi-Oriented Scene Text Detector with Localization Refinementcited by 33
  20. 2022Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learningcited by 33
  21. 2023FuseCap: Leveraging Large Language Models for Enriched Fused Image Captionscited by 33
  22. 2022OCR-VQGAN: Taming Text-within-Image Generationcited by 31
  23. 2024Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentationcited by 30
  24. 2023ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformercited by 29
  25. 2022Arbitrary Shape Text Detection via Boundary Transformercited by 28
  26. 2024Harnessing Webpage UIs for Text-Rich Visual Understandingcited by 28
  27. 2022Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spottingcited by 27
  28. 2023Towards Unified Scene Text Spotting based on Sequence Generationcited by 27
  29. 2021TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representationcited by 26
  30. 2021Towards Accurate Text-based Image Captioning with Content Diversity Explorationcited by 25
  31. 2024FakingRecipe: Detecting Fake News on Short Video Platforms from the Perspective of Creative Processcited by 25
  32. 2021De-rendering Stylized Textscited by 24
  33. 2021Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detectioncited by 23
  34. 2022End-to-End Video Text Spotting with Transformercited by 21
  35. 2021Stroke-Based Scene Text Erasing Using Synthetic Data for Trainingcited by 20
  36. 2022WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Modelscited by 20
  37. 2023ECG-Image-Kit: A Synthetic Image Generation Toolbox to Facilitate Deep Learning-Based Electrocardiogram Digitizationcited by 20
  38. 2025LayerD: Decomposing Raster Graphic Designs into Layerscited by 20

50 most cited of 273 All 273 (JSON)