no code implementations • 8 Feb 2022 • Ling Yang, Shenda Hong, Luxia Zhang
To the best of our knowledge, SPGN is the first to utilize spectral comparisons in different intervals and involve spectral propagation across all time series with graph networks for few-shot TSC.
no code implementations • 29 Sep 2021 • Ling Yang, Shenda Hong, Luxia Zhang
First, we revisit the augmentation methods for time series of existing works and note that they mostly use segment-level augmentation derived from time slicing, which may bring about sampling bias and incorrect optimization with false negatives due to the loss of global context.