Bibliography (5):

1. VideoGPT: Video Generation using VQ-VAE and Transformers

2. VQ-GAN: Taming Transformers for High-Resolution Image Synthesis

3. UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild

4. https://www.youtube.com/watch?v=WZj7vW2mTJo

5. https://songweige.github.io/projects/tats/index.html