SCVRL: Shuffled Contrastive Video Representation Learning
This work addresses video representation learning for computer vision, offering an incremental improvement over existing methods.
The paper tackles the problem of self-supervised learning for videos by proposing SCVRL, a contrastive-based framework that learns both semantic and motion patterns, outperforming CVRL on four benchmarks.
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.