Corpus ID: 219530740

Person Re-identification in the 3D Space

@article{Zheng2020PersonRI,
  title={Person Re-identification in the 3D Space},
  author={Zhedong Zheng and Yi Yang},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.04569}
}
  • Zhedong Zheng, Yi Yang
  • Published 2020
  • Computer Science
  • ArXiv
  • People live in a 3D world. However, existing works on person re-identification (re-id) mostly consider the representation learning in a 2D space, intrinsically limiting the understanding of people. In this work, we address this limitation by exploring the prior knowledge of the 3D body structure. Specifically, we project 2D images to a 3D space and introduce a novel Omni-scale Graph Network (OG-Net) to learn the representation from sparse 3D points. With the help of 3D geometry information, we… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    Citations

    Publications citing this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 52 REFERENCES

    Dynamic Graph CNN for Learning on Point Clouds

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    ImageNet: A large-scale hierarchical image database

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Deep Residual Learning for Image Recognition

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Squeeze-and-Excitation Networks

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    The Graph Neural Network Model

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in Vitro

    VIEW 4 EXCERPTS

    3D ShapeNets: A deep representation for volumetric shapes

    VIEW 1 EXCERPT

    A Discriminatively Learned CNN Embedding for Person Reidentification

    VIEW 1 EXCERPT