Pose-Aware Video Transformers

Human perception of surroundings is often guided by the various poses present within the environment. Many computer vision tasks, such as human action recognition and robot imitation learning, rely on pose-based entities like human skeletons or robotic arms.

Data and Resources

Cite this as

Dominick Reilly, Aman Chadha, Srijan Das (2024). Dataset: Pose-Aware Video Transformers. https://doi.org/10.57702/yb13mrt6

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author Dominick Reilly
More Authors
Aman Chadha
Srijan Das
Homepage https://github.com/dominickrei/PoseAwareVT