3 datasets found

The VQA-CP dataset is a split of the VQA dataset, designed to test generalization skills across changes in the answer distribution between the training and the test sets.

The dataset used in the paper is a set of sequential vision-and-language tasks, where each task consists of an image and a text input.

The Visual Genome dataset is a large-scale visual question answering dataset, containing 1.5 million images, each with 15-30 annotated entities, attributes, and relationships.