VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning.
Hao TanJie LeiThomas WolfMohit BansalPublished in: CoRR (2021)
Keyphrases
- online learning
- learning algorithm
- learning process
- training process
- prediction accuracy
- online training
- interactive video
- knowledge acquisition
- supervised learning
- artificial neural networks
- video data
- video sequences
- learning experience
- learning tasks
- reinforcement learning
- learning machines
- radial basis function network
- learning speed
- learning stage
- bayesian networks
- real time