ST-Tree couples a Swin Transformer feature extractor with a prototype-based neural tree, reporting average accuracy of 0.789 on 10 UEA multivariate time series datasets, with visualizations of node prototypes as evidence of interpretability.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ST-Tree with Interpretability for Multivariate Time Series Classification
ST-Tree couples a Swin Transformer feature extractor with a prototype-based neural tree, reporting average accuracy of 0.789 on 10 UEA multivariate time series datasets, with visualizations of node prototypes as evidence of interpretability.