Unsupervised 2D Gaussian landmarks, moved by a residual LSTM, enable long-range video interpolation and prediction while preserving foreground structure.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Video Interpolation and Prediction with Unsupervised Landmarks
Unsupervised 2D Gaussian landmarks, moved by a residual LSTM, enable long-range video interpolation and prediction while preserving foreground structure.