6 datasets found

Formats: JSON Tags: image description

Filter Results

  • Twitter A11y

    The dataset used in the paper to evaluate the effectiveness of Twitter accessibility.

  • Framing Image Description as a Ranking Task

    A dataset for evaluating the performance of image description models.

  • DIOR-RSVG

    The DIOR-RSVG dataset is a large-scale dataset containing 17,402 remote sensing images and 38,320 unique attribute descriptions.

  • DIOR-IDD

    The attribute-guided DIOR-IDD dataset is a combination of the DIOR-RSVG and DIOR-IDD datasets. The dataset includes 23,463 image-text pairs and is used to train the MGIMM model.

  • 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.

  • MSCOCO

    Human Pose Estimation (HPE) aims to estimate the position of each joint point of the human body in a given image. HPE tasks support a wide range of downstream tasks such as...
You can also access this registry using the API (see API Docs).