Recurrent Neural Networks

TSRUp, or Transformation-based Spatial Recurrent Unit p, is a modification of a ConvGRU used in the TriVD-GAN architecture for video generation.

It largely follows TSRUc, but computes $\theta$, $u$ and $c$ in parallel given $x_{t}$ and $h_{t−1}$, yielding the following replacement for the $c$ update equation:

$$ c = \rho\left(W_{c} \star_{n}\left[h_{t-1}; x_{t}\right] + b_{c} \right) $$

In these equations $\sigma$ and $\rho$ are the elementwise sigmoid and ReLU functions respectively and the $\star_{n}$ represents a convolution with a kernel of size $n \times n$. Brackets are used to represent a feature concatenation.

Source: Transformation-based Adversarial Video Prediction on Large-Scale Data


Paper Code Results Date Stars


Task Papers Share
Video Generation 1 50.00%
Video Prediction 1 50.00%