Corpus ID: 52291953

An Integral Pose Regression System for the ECCV2018 PoseTrack Challenge

@article{Sun2018AnIP,
  title={An Integral Pose Regression System for the ECCV2018 PoseTrack Challenge},
  author={Xiao Sun and Chuankang Li and Stephen Lin},
  journal={ArXiv},
  year={2018},
  volume={abs/1809.06079}
}
  • Xiao Sun, Chuankang Li, Stephen Lin
  • Published 2018
  • Computer Science
  • ArXiv
  • For the ECCV 2018 PoseTrack Challenge, we present a 3D human pose estimation system based mainly on the integral human pose regression method. We show a comprehensive ablation study to examine the key performance factors of the proposed system. Our system obtains 47mm MPJPE on the CHALL_H80K test dataset, placing second in the ECCV2018 3D human pose estimation challenge. Code will be released to facilitate future work. 

    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 13 REFERENCES

    Compositional Human Pose Regression

    VIEW 1 EXCERPT

    2D Human Pose Estimation: New Benchmark and State of the Art Analysis

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Towards Accurate Multi-person Pose Estimation in the Wild

    VIEW 2 EXCERPTS

    Latent structured models for human pose estimation

    Integral Human Pose Regression

    VIEW 11 EXCERPTS
    HIGHLY INFLUENTIAL

    Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose

    VIEW 1 EXCERPT

    Automatic differentiation in PyTorch

    VIEW 1 EXCERPT

    Deep Residual Learning for Image Recognition

    VIEW 1 EXCERPT