4 datasets found

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

The proposed EPIC method is a pre-training approach that leverages more text tokens for learning vision-language associations.

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

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.