4 datasets found

A large-scale face image dataset that contains real face images and corresponding semantic segmentation map, sketch, and textual descriptions.

Generating motion from textual descriptions can be used in numerous applications in the game industry, film-making, and animating robots. For example, a typical way to access new...

HumanAct12 dataset is a large-scale 3D human motion dataset with textual descriptions.

HumanML3D is a text-to-motion dataset built upon AMASS dataset and HumanAct12. It provides a wide range of motion-language pairs which cover ordinary activities, such as...