4 datasets found

A conditional language generation model with Big Five Personality (BFP) feature vectors as input context, which writes human-like short texts.

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...

BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

The dataset used in the paper is not explicitly mentioned, but it is implied to be a text-to-image dataset.