The video action segmentation task is regularly explored under weaker fo...
State-of-the-art methods for self-supervised sequential action alignment...
We present a self-supervised approach for learning video representations...
We present a sampling-free approach for computing the epistemic uncertai...
The lack of large-scale real datasets with annotationsmakes transfer lea...
Effectively measuring the similarity between two human motions is necess...
One-shot pose estimation for tasks such as body joint localization, came...