3 datasets found

Groups: Image Captioning Organizations: No Organization Formats: JSON

Filter Results

  • Conceptual Captions 3M

    The Conceptual Captions 3M dataset is a large-scale image-text dataset used for vision-language pre-training.

  • COCO Captions

    Object detection is a fundamental task in computer vision, requiring large annotated datasets that are difficult to collect.

  • 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.