4 datasets found

The dataset used in the paper is a multi-object environment with a robotic arm and multiple objects to manipulate. The agent learns to control the objects independently and...

The DAVIS 2017 challenge dataset is a benchmark for video object segmentation. It consists of 150 sequences with multiple objects and instance-level pixel-wise annotations.

The MNIST(multi) dataset is used to test the ability of TARGET-VAE to identify multiple objects in images.

Large scale datasets [18, 17, 27, 6] boosted text conditional image generation quality. However, in some domains it could be difficult to make such datasets and usually it could...