T1 uses one-to-one channel-head binding in a CNN-Transformer hybrid to achieve robust multivariate time-series imputation, cutting average MSE by 46% versus the next-best baseline across 11 datasets even at 70% missingness.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2representative citing papers
MUDRA extends FLDA to multivariate time series with missing data via an ECM algorithm and shows improved classification over prior methods on the Articulary Word Recognition dataset.
citing papers explorer
-
T1: One-to-One Channel-Head Binding for Multivariate Time-Series Imputation
T1 uses one-to-one channel-head binding in a CNN-Transformer hybrid to achieve robust multivariate time-series imputation, cutting average MSE by 46% versus the next-best baseline across 11 datasets even at 70% missingness.
-
Multivariate Functional Linear Discriminant Analysis for the Classification of Short Time Series with Missing Data
MUDRA extends FLDA to multivariate time series with missing data via an ECM algorithm and shows improved classification over prior methods on the Articulary Word Recognition dataset.