Corpus ID: 10426070

DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection

@article{Ouyang2014DeepIDNetMA,
  title={DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection},
  author={Wanli Ouyang and Ping Luo and Xingyu Zeng and Shi Qiu and Yonglong Tian and Hongsheng Li and Shuo Yang and Zhe Wang and Yuanjun Xiong and Chen Qian and Zhenyao Zhu and Ruohui Wang and Chen Change Loy and Xiaogang Wang and Xiaoou Tang},
  journal={ArXiv},
  year={2014},
  volume={abs/1409.3505}
}
  • Wanli Ouyang, Ping Luo, +12 authors Xiaoou Tang
  • Published 2014
  • Computer Science
  • ArXiv
  • In this paper, we propose multi-stage and deformable deep convolutional neural networks for object detection. This new deep learning object detection diagram has innovations in multiple aspects. In the proposed new deep architecture, a new deformation constrained pooling (defpooling) layer models the deformation of object parts with geometric constraint and penalty. With the proposed multistage training strategy, multiple classifiers are jointly optimized to process samples at different… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 115 CITATIONS, ESTIMATED 53% COVERAGE

    DeepID-Net: Deformable deep convolutional neural networks for object detection

    Learning Rotation-Invariant and Fisher Discriminative Convolutional Neural Networks for Object Detection

    Improved Object Detection With Iterative Localization Refinement in Convolutional Neural Networks

    VIEW 1 EXCERPT
    CITES METHODS

    Iterative localization refinement in convolutional neural networks for improved object detection

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Exploit All the Layers: Fast and Accurate CNN Object Detector with Scale Dependent Pooling and Cascaded Rejection Classifiers

    • Fan Yang, Wongun Choi, Yuanqing Lin
    • Computer Science
    • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2016

    Jointly Learning Deep Features, Deformable Parts, Occlusion and Classification for Pedestrian Detection

    FILTER CITATIONS BY YEAR

    2013
    2020

    CITATION STATISTICS

    • 4 Highly Influenced Citations

    • Averaged 12 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 82 REFERENCES

    Scalable Object Detection Using Deep Neural Networks

    VIEW 1 EXCERPT

    Multi-stage Contextual Deep Learning for Pedestrian Detection

    VIEW 1 EXCERPT

    Joint Deep Learning for Pedestrian Detection

    VIEW 4 EXCERPTS

    Latent hierarchical structural learning for object detection

    VIEW 13 EXCERPTS
    HIGHLY INFLUENTIAL