An improved ConvLSTM with attention and residual modules is claimed to predict cylinder wake flows with fewer parameters, faster training, and lower errors than standard ConvLSTM.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Convolutional Long Short-Term Memory Neural Networks Based Numerical Simulation of Flow Field
An improved ConvLSTM with attention and residual modules is claimed to predict cylinder wake flows with fewer parameters, faster training, and lower errors than standard ConvLSTM.