Dataset - LDM

COCO Captions and Localized Narratives

The dataset used in the paper is COCO captions and Localized Narratives, which are used to generate image descriptions.
- Dataset
- JSON
VQA-CP v2 and VQA 2.0

The dataset used in the paper is VQA-CP v2 and VQA 2.0, which are two standard datasets for visual question answering.
- Dataset
- JSON

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

2 datasets found