7 datasets found

Filter Results

  • VrR-VG

    The dataset used in the paper is VrR-VG, which is used for visual relation detection and scene graph generation.

  • VisualGenome

    A dataset for scene graph generation with annotations in the form of subject-predicate-object.

  • Open Images Dataset

    The dataset used in the experiment consists of 50 images equally distributed between five classes: aircraft, bird, bicycle, boat, and dog. Each class has 5 true positive images...

  • Visual Semantic Role Labeling

    The V-COCO dataset is a large-scale visual semantic graph dataset, containing 4,946 images annotated with object and predicate labels to form a scene graph.

  • General Visual Question Answering

    The GQA dataset is a large-scale visual semantic graph dataset, containing 8,208 images annotated with object and predicate labels to form a scene graph.

  • One-shot Scene Graph Generation

    One-shot scene graph generation task, utilizing rich prior knowledge from Visual Genome and ConceptNet.

  • 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.