A visual MAE, combined with time-patch embedding and cross-channel GCN augmentation, achieves state-of-the-art irregular multivariate time series forecasting and few-shot performance.
Spectral temporal graph neural network for multivariate time-series forecasting
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
IMTS is Worth Time $\times$ Channel Patches: Visual Masked Autoencoders for Irregular Multivariate Time Series Prediction
A visual MAE, combined with time-patch embedding and cross-channel GCN augmentation, achieves state-of-the-art irregular multivariate time series forecasting and few-shot performance.