3 datasets found

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

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

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...