KeyMemoryRNN: A Flexible Prediction Framework for Spatiotemporal Prediction Networks
Most previous recurrent neural networks for spatiotemporal prediction have difficulty in learning the long-term spatiotemporal correlations and capturing skip-frame correlations. The reason is that the recurrent neural networks update the memory states only using information from the previous time s...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | article |
| Language: | EN |
| Published: |
IEEE
2021
|
| Subjects: | |
| Online Access: | https://doaj.org/article/2b32dae151a54f3baa0971aa0135b6a9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|