Skeleton-based action segmentation requires recognizing composable actio...
Self-supervised video representation learning aimed at maximizing simila...
Video anomaly detection in surveillance systems with only video-level la...
Skeleton-based two-person interaction recognition has been gaining incre...
We present Mask Atari, a new benchmark to help solve partially observabl...
Physical processes, camera movement, and unpredictable environmental
con...
We present Cycle-Contrastive Learning (CCL), a novel self-supervised met...
Sufficient supervised information is crucial for any machine learning mo...