-
BIMM: Brain Inspired Masked Modeling for Video Representation Learning
The Brain Inspired Masked Modeling (BIMM) framework conducts self-supervised video representation learning inspired by the process of visual information processing in the human... -
Motion-Focused Contrastive Learning of Video Representations
Motion-focused Contrastive Learning (MCL) method for self-supervised video representation learning. -
YOVO-3M and YOVO-10M
The YOVO-3M and YOVO-10M datasets are newly-created web video datasets for weakly-supervised video representation learning.
