Corpus ID: 211252522

Stochastic Latent Residual Video Prediction

@article{Franceschi2020StochasticLR,
  title={Stochastic Latent Residual Video Prediction},
  author={Jean-Yves Franceschi and Edouard Delasalles and Mickael Chen and Sylvain Lamprier and Patrick Gallinari},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.09219}
}
  • Jean-Yves Franceschi, Edouard Delasalles, +2 authors Patrick Gallinari
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • Designing video prediction models that account for the inherent uncertainty of the future is challenging. Most works in the literature are based on stochastic image-autoregressive recurrent networks, which raises several performance and applicability issues. An alternative is to use fully latent temporal models which untie frame synthesis and temporal dynamics. However, no such model for stochastic video prediction has been proposed in the literature yet, due to design and training difficulties… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 71 REFERENCES

    Unsupervised Learning of Object Structure and Dynamics from Videos

    VIEW 11 EXCERPTS
    HIGHLY INFLUENTIAL

    Stochastic Adversarial Video Prediction

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Temporal Difference Variational Auto-Encoder

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Automatic differentiation in PyTorch

    VIEW 1 EXCERPT
    HIGHLY INFLUENTIAL

    Dual Motion GAN for Future-Flow Embedded Video Prediction

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Recognizing human actions: a local SVM approach

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL