Variable-length Time Series Classification: Benchmarking, Analysis and Effective Spectral Pooling Strategy
We present the first comprehensive benchmark for variable-length time series classification tasks, evaluating the effectiveness of 22 previously widely-used length normalization methods across 14 publicly available VTS datasets and 8 backbones, and propose a novel spectral pooling layer to process variable-length time series.
The code can be found in [Code]