PDFTime reformulates multivariate time series classification as a multi-stage prototype-based decision process, claiming SOTA results on UCR and UEA benchmarks.
Omni-scale cnns: a simple and effective kernel size configuration for time series classification.arXiv preprint arXiv:2002.10061
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3representative citing papers
FeDPM learns and aligns local discrete prototypical memories across domains to create a unified discrete latent space for LLM-based time series foundation models in a federated setting.
ROMAN converts time series into a shorter multiscale channel representation that lets standard CNN classifiers access scale and coarse-position information explicitly.
citing papers explorer
-
Prototype-Guided Classification Sub-Task Decoupling Framework: Enhancing Generalization and Interpretability for Multivariate Time Series
PDFTime reformulates multivariate time series classification as a multi-stage prototype-based decision process, claiming SOTA results on UCR and UEA benchmarks.
-
Discrete Prototypical Memories for Federated Time Series Foundation Models
FeDPM learns and aligns local discrete prototypical memories across domains to create a unified discrete latent space for LLM-based time series foundation models in a federated setting.
-
ROMAN: A Multiscale Routing Operator for Convolutional Time Series Models
ROMAN converts time series into a shorter multiscale channel representation that lets standard CNN classifiers access scale and coarse-position information explicitly.