Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencoder Paper • 2108.05028 • Published Aug 11, 2021
Decompose the Sounds and Pixels, Recompose the Events Paper • 2112.11547 • Published Dec 21, 2021 • 1
Self-supervised Spatiotemporal Representation Learning by Exploiting Video Continuity Paper • 2112.05883 • Published Dec 11, 2021 • 1