Frequency Domain Transformer Networks for Video Prediction
arXiv:1903.00271
Abstract
The task of video prediction is forecasting the next frames given some previous frames. Despite much recent progress, this task is still challenging mainly due to high nonlinearity in the spatial domain. To address this issue, we propose a novel architecture, Frequency Domain Transformer Network (FDTN), which is an end-to-end learnable model that estimates and uses the transformations of the signal in the frequency domain. Experimental evaluations show that this approach can outperform some widely used video prediction methods like Video Ladder Network (VLN) and Predictive Gated Pyramids (PGP).
arXiv commentAccepted for European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), Bruges, Belgium, to appear April 2019
References in corpus (8)
- Decoupled Weight Decay Regularization
- Semi-Supervised Learning with Ladder Networks
- PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning
- Transformation-Based Models of Video Sequences
- Video Pixel Networks
- Video Ladder Networks
- Learning to relate images: Mapping units, complex cells and simultaneous eigenspaces
- A Neurally-Inspired Hierarchical Prediction Network for Spatiotemporal Sequence Learning and Prediction