English

Dynamic Variational Autoencoders for Visual Process Modeling

Neural and Evolutionary Computing 2020-04-13 v3 Multimedia

Abstract

This work studies the problem of modeling visual processes by leveraging deep generative architectures for learning linear, Gaussian representations from observed sequences. We propose a joint learning framework, combining a vector autoregressive model and Variational Autoencoders. This results in an architecture that allows Variational Autoencoders to simultaneously learn a non-linear observation as well as a linear state model from sequences of frames. We validate our approach on artificial sequences and dynamic textures.

Keywords

Cite

@article{arxiv.1803.07488,
  title  = {Dynamic Variational Autoencoders for Visual Process Modeling},
  author = {Alexander Sagel and Hao Shen},
  journal= {arXiv preprint arXiv:1803.07488},
  year   = {2020}
}
R2 v1 2026-06-23T00:59:03.554Z