An Inception-inspired LSTM with 1x1, 3x3, and 5x5 kernels inside each gate yields modestly lower MAE and MSE than a convolutional LSTM for next-frame video prediction on KITTI and KTH.
An empirical exploration of recurrent network ar- chitectures
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Inception-inspired LSTM for Next-frame Video Prediction
An Inception-inspired LSTM with 1x1, 3x3, and 5x5 kernels inside each gate yields modestly lower MAE and MSE than a convolutional LSTM for next-frame video prediction on KITTI and KTH.