A deep learning framework with a new inverse-consistency loss aligns and averages time series across 128 UCR datasets without per-dataset regularization tuning.
The ucr time series archive,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Diffeomorphic Temporal Alignment Nets for Time-series Joint Alignment and Averaging
A deep learning framework with a new inverse-consistency loss aligns and averages time series across 128 UCR datasets without per-dataset regularization tuning.