ViewCLR: Learning Self-supervised Video Representation for Unseen Viewpoints
ViewCLR: Learning Self-supervised Video Representation for Unseen Viewpoints
Learning self-supervised video representation predominantly focuses on discriminating instances generated from simple data augmentation schemes. However, the learned representation often fails to generalize over unseen camera viewpoints. To this end, we propose ViewCLR, that learns self-supervised video representation invariant to camera viewpoint changes. We introduce a viewpoint-generator that can be …