Flowing ConvNets for Human Pose Estimation in Videos

@article{Pfister2015FlowingCF,
  title={Flowing ConvNets for Human Pose Estimation in Videos},
  author={Tomas Pfister and James Charles and Andrew Zisserman},
  journal={2015 IEEE International Conference on Computer Vision (ICCV)},
  year={2015},
  pages={1913-1921}
}
  • Tomas Pfister, James Charles, Andrew Zisserman
  • Published 2015
  • Computer Science
  • 2015 IEEE International Conference on Computer Vision (ICCV)
  • The objective of this work is human pose estimation in videos, where multiple frames are available. We investigate a ConvNet architecture that is able to benefit from temporal context by combining information across the multiple frames using optical flow. To this end we propose a network architecture with the following novelties: (i) a deeper network than previously investigated for regressing heatmaps, (ii) spatial fusion layers that learn an implicit spatial model, (iii) optical flow is used… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 341 CITATIONS

    Sequence-to-Sequence Learning for Human Pose Correction in Videos

    VIEW 13 EXCERPTS
    CITES RESULTS, METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Thin-Slicing Network: A Deep Structured Model for Pose Estimation in Videos

    VIEW 3 EXCERPTS
    CITES METHODS & BACKGROUND

    Human Pose Forecasting via Deep Markov Models

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    Multi-Scale Supervised Network for Human Pose Estimation

    VIEW 1 EXCERPT
    CITES BACKGROUND

    PoseFlow: A Deep Motion Representation for Understanding Human Behaviors in Videos

    VIEW 10 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video

    VIEW 2 EXCERPTS
    CITES METHODS

    Recurrent Human Pose Estimation

    VIEW 6 EXCERPTS
    CITES BACKGROUND & METHODS

    FILTER CITATIONS BY YEAR

    2014
    2020

    CITATION STATISTICS

    • 28 Highly Influenced Citations

    • Averaged 72 Citations per year from 2018 through 2020

    References

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

    Efficient object localization using Convolutional Networks

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    MODEC: Multimodal Decomposable Models for Human Pose Estimation