1 code implementation • CVPR 2022 • Salar Hosseini Khorasgani, Yuxuan Chen, Florian Shkurti
One of the key reasons for this is that sampling pairs of similar video clips, a required step for many self-supervised contrastive learning methods, is currently done conservatively to avoid false positives.
Ranked #1 on Self-Supervised Action Recognition on UCF101 (Pre-Training Dataset metric)