5 datasets found

The dataset used in the paper is a video prediction dataset with occlusions, which is used to evaluate the proposed Fast Fourier Inception Networks (FFINet) for occluded video...

The KTH dataset consists of videos of 25 people performing different activities.

Decomposing motion and content for natural video sequence prediction.

We present an approach for high-resolution video frame pre-diction by conditioning on both past frames and past optical flows.

Spatially-displaced convolution for video prediction.