6 datasets found

Tags: Visual Grounding

Filter Results

  • 3DVG-Transformer

    A dataset for visual grounding on point clouds, focusing on relation modeling.

  • GUI Grounding Dataset

    A GUI grounding dataset for testing visual grounding abilities of agents.

  • ScanNet200

    Diff2Scene uses ScanNet, Matterport3D, ScanNet200 and Replica for open-vocabulary 3D semantic segmentation and visual grounding tasks.

  • Replica

    The Replica dataset contains 18 various highly photo-realistic indoor environments. It provides dense-mesh, high-resolution RGBD images and a large range of instance annotations...

  • RefCOCO, RefCOCO+, and RefCOCOg

    Visual Grounding is a task that aims to locate a target object according to a natural language expression. The dataset used in this paper is RefCOCO, RefCOCO+, and RefCOCOg.

  • 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.
You can also access this registry using the API (see API Docs).