Corpus ID: 21660478

Boosting up Scene Text Detectors with Guided CNN

@article{Yue2018BoostingUS,
  title={Boosting up Scene Text Detectors with Guided CNN},
  author={Xiaoyu Yue and Zhanghui Kuang and Z. Zhang and Zhenfang Chen and Pan He and Yu Qiao and Wei Zhang},
  journal={ArXiv},
  year={2018},
  volume={abs/1805.04132}
}
  • Xiaoyu Yue, Zhanghui Kuang, +4 authors Wei Zhang
  • Published 2018
  • Computer Science
  • ArXiv
  • Deep CNNs have achieved great success in text detection. [...] Key Method The proposed model consists of one guidance subnetwork, where a guidance mask is learned from the input image itself, and one primary text detector, where every convolution and non-linear operation are conducted only in the guidance mask. On the one hand, the guidance subnetwork filters out non-text regions coarsely, greatly reduces the computation complexity.Expand Abstract
    Geometry Normalization Networks for Accurate Scene Text Detection
    • 6
    • PDF
    Temporal Sequence Distillation: Towards Few-Frame Action Recognition in Videos
    • 4
    • PDF
    TextTubes for Detecting Curved Text in the Wild
    • 2
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 66 REFERENCES
    Very Deep Convolutional Networks for Large-Scale Image Recognition
    • 39,416
    • PDF
    Deep Residual Learning for Image Recognition
    • 50,397
    • PDF
    SSD: Single Shot MultiBox Detector
    • 8,272
    • Highly Influential
    • PDF
    Fully Convolutional Networks for Semantic Segmentation
    • 7,201
    • Highly Influential
    • PDF
    EAST: An Efficient and Accurate Scene Text Detector
    • 504
    • Highly Influential
    • PDF
    Text-Attentional Convolutional Neural Network for Scene Text Detection
    • 185
    • PDF
    Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection
    • 172
    • Highly Influential
    • PDF
    Robust Scene Text Detection with Convolution Neural Network Induced MSER Trees
    • 289
    • PDF