9 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 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...

MovingMNIST is a synthetic dataset for predicting the movement of two digits.

Video prediction is a challenging task. The quality of video frames from current state-of-the-art (SOTA) generative models tends to be poor and generalization beyond the...

The UVG dataset comprises 16 video sequences of 3840×2160, recorded at 120 frames per second.

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.

Moving MNIST is a benchmark data set for video recognition. There are 10,000 samples including 8,000 for training and 2,000 for test. Each sample consists of 20 sequential gray...

Spatially-displaced convolution for video prediction.