4 datasets found

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

A dataset for evaluating the performance of image description models.

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.

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...