4 datasets found

Groups: Visual Reasoning Formats: JSON

Filter Results

  • VQA-CP

    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.

  • CLEVR dataset

    The CLEVR dataset is a dataset for visual question answering, where each image is annotated with a question.

  • NLVR2

    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.

  • Visual Genome

    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.