3 datasets found

Groups: Image Annotation Organizations: No Organization

Filter Results

  • RefCOCOg

    The RefCOCOg dataset is a reconstructed dataset of the MS-COCO dataset, containing 85,474 referring expressions for 54,822 objects in 26,711 images.

  • RefCOCO

    The dataset used in the paper is a benchmark for referring expression grounding, containing 142,210 referring expressions for 50,000 referents in 19,994 images.

  • 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.