mlsanityData to 7 Oct 2026

Multi-Oriented Text Detection with Fully Convolutional Networks

arXiv 1604.04018 ↗First posted 14 Apr 2016cs.CVcited by 36

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a novel approach for text detec- tion in natural images. Both local and global cues are taken into account for localizing text lines in a coarse-to-fine pro- cedure. First, a Fully Convolutional Network (FCN) model is trained to predict the salient map of text regions in a holistic manner. Then, text line hypotheses are estimated by combining the salient map and character components. Fi- nally, another FCN classifier is used to predict the centroid of each character, in order to remove the false hypotheses. The framework is general for handling text in multiple ori- entations, languages and fonts. The proposed method con- sistently achieves the state-of-the-art performance on three text detection benchmarks: MSRA-TD500, ICDAR2015 and ICDAR2013.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Apr 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 6; 2023: 8; 2024: 3; 2025: 2; 2026: 2.

36 papers.

Sort:

By area:

  1. 2021OCR-free Document Understanding Transformercited by 400
  2. 2022Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusioncited by 94
  3. 2021ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spottingcited by 84
  4. 2023Turning a CLIP Model into a Scene Text Detectorcited by 44
  5. 2025A Survey of Multimodal Retrieval-Augmented Generationcited by 37
  6. 2021Primitive Representation Learning for Scene Text Recognitioncited by 28
  7. 2021TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representationcited by 26
  8. 2021Stroke-Based Scene Text Erasing Using Synthetic Data for Trainingcited by 20
  9. 2023Towards Robust Real-Time Scene Text Detection: From Semantic to Instance Representation Learningcited by 12
  10. 2022Text Growing on Leafcited by 11
  11. 2023Turning a CLIP Model into a Scene Text Spottercited by 9
  12. 2021All You Need is a Second Look: Towards Arbitrary-Shaped Text Detectioncited by 7
24 more
  1. 2022CBNet: A Plug-and-Play Network for Segmentation-Based Scene Text Detectioncited by 6
  2. 2022A Scene-Text Synthesis Engine Achieved Through Learning from Decomposed Real-World Datacited by 5
  3. 2021TricubeNet: 2D Kernel-Based Object Representation for Weakly-Occluded Oriented Object Detectioncited by 2
  4. 2023FoSp: Focus and Separation Network for Early Smoke Segmentationcited by 2
  5. 2024TEXTRON: Weakly Supervised Multilingual Text Detection through Data Programmingcited by 2
  6. 2024Text Grouping Adapter: Adapting Pre-trained Text Detector for Layout Analysiscited by 2
  7. 2024The First Swahili Language Scene Text Detection and Recognition Datasetcited by 2
  8. 2021VML-MOC: Segmenting a multiply oriented and curved handwritten text lines datasetcited by 1
  9. 2021Conceptual Text Region Network: Cognition-Inspired Accurate Scene Text Detectioncited by 1
  10. 2021DUET: Detection Utilizing Enhancement for Text in Scanned or Captured Documentscited by 1
  11. 2022Text detection and recognition based on a lensless imaging systemcited by 1
  12. 2026EpiSAM: Character Segmentation in Challenging Stone Inscriptionscited by 1
  13. 2021Arbitrary-Shaped Text Detection withAdaptive Text Region Representationcited by 0
  14. 2021MT: Multi-Perspective Feature Learning Network for Scene Text Detectioncited by 0
  15. 2021Context-Free TextSpotter for Real-Time and Mobile End-to-End Text Detection and Recognitioncited by 0
  16. 2021Bidirectional Regression for Arbitrary-Shaped Text Detectioncited by 0
  17. 2021Scene Text recognition with Full Normalizationcited by 0
  18. 2022DPTNet: A Dual-Path Transformer Architecture for Scene Text Detectioncited by 0
  19. 2023Cursive Caption Text Detection in Videoscited by 0
  20. 2023Box2Poly: Memory-Efficient Polygon Prediction of Arbitrarily Shaped and Rotated Textcited by 0
  21. 2023Towards Detecting, Recognizing, and Parsing the Address Information from Bangla Signboard: A Deep Learning-based Approachcited by 0
  22. 2023Enhancing Scene Text Detectors with Realistic Text Image Synthesis Using Diffusion Modelscited by 0
  23. 2025OTSNet: A Neurocognitive-Inspired Observation-Thinking-Spelling Pipeline for Scene Text Recognitioncited by 0
  24. 2026Back-Tracking from Clarity: Self-Learning to See Text from Afarcited by 0