SCVRL: Shuffled Contrastive Video Representation Learning


We propose SCVRL, a novel contrastive-based framework for self-supervised learning for videos. Differently from previous contrast learning based methods that mostly focus on learning visual semantics (e.g., CVRL), SCVRL is capable of learning both semantic and motion patterns. For that, we reformulate the popular shuffling pretext task within a modern contrastive learning paradigm. We show that our transformer-based network has a natural capacity to learn motion in self-supervised settings and achieves strong performance, outperforming CVRL on four benchmarks.

In Conference on Computer Vision and Pattern Recognition, CVPR 2021 workshop
Michael Dorkenwald
Michael Dorkenwald
PhD Student

Researcher in Computer Vision at University of Amsterdam