1. Attention is all you need;vaswani;Advances in Neural IInformation Processing Systems,2017
2. Dropout: a simple way to prevent neural networks from overfitting;srivastava;The Journal of Machine Learning Research,2014
3. Decoupled spatial-temporal attention network for skeleton-based action recognition;shi;arXiv preprint arXiv 2007 09948,2020
4. Sequence level training with recurrent neural networks;ranzato;arXiv preprint arXiv 1511 06732,2015
5. Auto-conditioned recurrent networks for extended complex human motion synthesis;zhou;International Conference on Learning Representations,2018