Long-Term Human Motion Prediction by Modeling Motion Context and Enhancing Motion Dynamic

@article{Tang2018LongTermHM,
  title={Long-Term Human Motion Prediction by Modeling Motion Context and Enhancing Motion Dynamic},
  author={Yongyi Tang and Lin Ma and W. Liu and W. Zheng},
  journal={ArXiv},
  year={2018},
  volume={abs/1805.02513}
}
  • Yongyi Tang, Lin Ma, +1 author W. Zheng
  • Published 2018
  • Computer Science
  • ArXiv
  • Human motion prediction aims at generating future frames of human motion based on an observed sequence of skeletons. Recent methods employ the latest hidden states of a recurrent neural network (RNN) to encode the historical skeletons, which can only address short-term prediction. In this work, we propose a motion context modeling by summarizing the historical human motion with respect to the current prediction. A modified highway unit (MHU) is proposed for efficiently eliminating motionless… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Enhancing the educational value of video games
    89
    Simplified Criterion of Steady-State Stability of Electric Power Systems
    1
    On automorphisms groups of cyclic p-gonal Riemann surfaces
    10
    History Repeats Itself: Human Motion Prediction via Motion Attention

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 28 REFERENCES
    Design and Implementation of an XML Firewall
    33
    Pluim . Nonrigid registration using a rigidity constraint
    • 1999
    A selective adiabatic spin-echo pulse
    31
    Single amino acid substitution enhances bacterial expression of PARP-4D214A.
    8
    Programmed Assembly of DNA-Coated Nanowire Devices
    92
    Population dynamics of the Bwindi mountain gorillas
    45
    The "improperly" oriented pyramidal cell in the cerebral cortex
    • 1931