Corpus ID: 5668282

Detecting Faces Using Region-based Fully Convolutional Networks

@article{Wang2017DetectingFU,
  title={Detecting Faces Using Region-based Fully Convolutional Networks},
  author={Yitong Wang and Xing Ji and Zheng Zhou and Hao Wang and Zhifeng Li},
  journal={ArXiv},
  year={2017},
  volume={abs/1709.05256}
}
  • Yitong Wang, Xing Ji, +2 authors Zhifeng Li
  • Published in ArXiv 2017
  • Computer Science
  • Face detection has achieved great success using the region-based methods. [...] Key Method In our approach, we adopt the fully convolutional Residual Network (ResNet) as the backbone network. Particularly, We exploit several new techniques including position-sensitive average pooling, multi-scale training and testing and on-line hard example mining strategy to improve the detection accuracy. Over two most popular and challenging face detection benchmarks, FDDB and WIDER FACE, Face R-FCN achieves superior…Expand Abstract

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Figures and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 45 CITATIONS

    Computer Vision – ECCV 2018

    VIEW 10 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Face Detection Using R-FCN Based Deformable Convolutional Networks

    VIEW 3 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    SSD-Sface: Single shot multibox detector for small faces

    • C. Thuis
    • 2018
    VIEW 4 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    Accurate Face Detection for High Performance

    VIEW 5 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    SANet: Smoothed Attention Network for Single Stage Face Detector

    VIEW 3 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    Segmentation is All You Need

    VIEW 7 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    Face Detection Using Improved Faster RCNN

    VIEW 5 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    ASFD: Automatic and Scalable Face Detector

    VIEW 1 EXCERPT
    CITES BACKGROUND

    KPNet: Towards Minimal Face Detector

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 34 REFERENCES

    Deep Residual Learning for Image Recognition

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    R-FCN: Object Detection via Region-based Fully Convolutional Networks

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Training Region-Based Object Detectors with Online Hard Example Mining

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    WIDER FACE: A Face Detection Benchmark

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Face R-CNN

    VIEW 15 EXCERPTS

    S^3FD: Single Shot Scale-Invariant Face Detector

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Gamow. Fast R-CNN

    • R. Girshick, G.J.P.N. Fotheringham-Smythe
    • In International Conference on Computer Vision (ICCV),
    • 2015
    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

    VIEW 12 EXCERPTS
    HIGHLY INFLUENTIAL