PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning
Yunbo Wang, Zhifeng Gao, Mingsheng Long, Jianmin Wang, Philip S Yu
Abstract
We present PredRNN++, a recurrent network for spatiotemporal predictive learning. In pursuit of a great modeling capability for short-term video dynamics, we make our network deeper in time by leveraging a new recurrent structure named Causal LSTM with cascaded dual memories. To alleviate the gradient propagation difficulties in deep predictive models, we propose a Gradient Highway Unit, which provides alternative quick routes for the gradient flows from outputs back to long-range previous inputs. The gradient highway units work seamlessly with the causal LSTMs, enabling our model to capture the short-term and the long-term video dependencies adaptively. Our model achieves state-of-the-art prediction results on both synthetic and real video datasets, showing its power in modeling entangled motions.
BibTeX
@InProceedings{pmlr-v80-wang18b,
title = {{P}red{RNN}++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning},
author = {Wang, Yunbo and Gao, Zhifeng and Long, Mingsheng and Wang, Jianmin and Yu, Philip S},
booktitle = {Proceedings of the 35th International Conference on Machine Learning},
pages = {5123--5132},
year = {2018},
editor = {Dy, Jennifer and Krause, Andreas},
volume = {80},
series = {Proceedings of Machine Learning Research},
month = {10--15 Jul},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v80/wang18b/wang18b.pdf},
url = {https://proceedings.mlr.press/v80/wang18b.html},
abstract = {We present PredRNN++, a recurrent network for spatiotemporal predictive learning. In pursuit of a great modeling capability for short-term video dynamics, we make our network deeper in time by leveraging a new recurrent structure named Causal LSTM with cascaded dual memories. To alleviate the gradient propagation difficulties in deep predictive models, we propose a Gradient Highway Unit, which provides alternative quick routes for the gradient flows from outputs back to long-range previous inputs. The gradient highway units work seamlessly with the causal LSTMs, enabling our model to capture the short-term and the long-term video dependencies adaptively. Our model achieves state-of-the-art prediction results on both synthetic and real video datasets, showing its power in modeling entangled motions.}
}