Making the Invisible Visible: Action Recognition Through Walls and Occlusions

@article{Li2019MakingTI,
  title={Making the Invisible Visible: Action Recognition Through Walls and Occlusions},
  author={T. Li and Lijie Fan and M. Zhao and Yingcheng Liu and D. Katabi},
  journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2019},
  pages={872-881}
}
  • T. Li, Lijie Fan, +2 authors D. Katabi
  • Published 2019
  • Computer Science, Engineering
  • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • Understanding people's actions and interactions typically depends on seeing them. [...] Key Method Our model takes radio frequency (RF) signals as input, generates 3D human skeletons as an intermediate representation, and recognizes actions and interactions of multiple people over time. By translating the input to an intermediate skeleton-based representation, our model can learn from both vision-based and RF-based datasets, and allow the two tasks to help each other. We show that our model achieves comparable…Expand Abstract

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-7 OF 7 CITATIONS

    Learning Longterm Representations for Person Re-Identification Using Radio Signals

    • Lijie Fan, T. Li, +3 authors D. Katabi
    • Computer Science
    • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2020
    VIEW 3 EXCERPTS
    CITES METHODS & BACKGROUND

    Optical Non-Line-of-Sight Physics-Based 3D Human Pose Estimation

    VIEW 3 EXCERPTS
    CITES BACKGROUND

    Through-Wall Human Mesh Recovery Using Radio Signals

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Seeing through walls

    A Motion Induced Passive Infrared (PIR) Sensor for Stationary Human Occupancy Detection

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 55 REFERENCES

    Through-Wall Human Pose Estimation Using Radio Signals

    VIEW 1 EXCERPT

    Action Recognition with Improved Trajectories

    VIEW 1 EXCERPT

    Single Shot Temporal Action Detection

    VIEW 1 EXCERPT

    Temporal Action Detection with Structured Segment Networks

    VIEW 1 EXCERPT

    Skeleton based action recognition with convolutional neural network

    • Y. Du, Yun Fu, Liang Wang
    • Computer Science
    • 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)
    • 2015
    VIEW 2 EXCERPTS

    Hierarchical recurrent neural network for skeleton based action recognition

    • Yong Du, Wei Wang, Liang Wang
    • Computer Science
    • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2015
    VIEW 1 EXCERPT

    RF-based 3D skeletons

    VIEW 7 EXCERPTS