Image Classifiers are Efficient Self-Supervised Video Representation Learners
By Owais Iqbal · Paper · cs.CV
We introduce VideoMSN, a Masked Siamese Network framework for efficient self-supervised spatio-temporal representation learning in videos. Instead of relying on heavy 3D architectures or reconstruction-based autoencoders for learning with unlabeled data, we repurpose standard ima
Tags: Cs.cv