Sleep-only contrastive pretraining improves results on non-sleep EEG and ECG tasks relative to training from scratch and matches or exceeds some specialized models.
InceptionTime: Finding AlexNet for time series classification
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 2polarities
background 2representative citing papers
Fusing chart visualizations with raw time series improves or maintains classification accuracy on UCR datasets when the visuals add non-redundant information.
Pruning hybrid time series classifiers including the new Hydrant combination can reduce energy consumption by up to 80% while keeping accuracy loss below 5%.
Synthetic experiments reveal that class-dependent effects appear in both perturbation-based and ground-truth evaluations of time series feature attributions, often producing contradictory rankings of attribution quality due to differences in feature amplitude or temporal extent between classes.
citing papers explorer
-
Pretraining on Sleep Data Improves non-Sleep Biosignal Tasks
Sleep-only contrastive pretraining improves results on non-sleep EEG and ECG tasks relative to training from scratch and matches or exceeds some specialized models.
-
VTBench: A Multimodal Framework for Time-Series Classification with Chart-Based Representations
Fusing chart visualizations with raw time series improves or maintains classification accuracy on UCR datasets when the visuals add non-redundant information.
-
Pruning Extensions and Efficiency Trade-Offs for Sustainable Time Series Classification
Pruning hybrid time series classifiers including the new Hydrant combination can reduce energy consumption by up to 80% while keeping accuracy loss below 5%.
-
Why Do Class-Dependent Evaluation Effects Occur with Time Series Feature Attributions? A Synthetic Data Investigation
Synthetic experiments reveal that class-dependent effects appear in both perturbation-based and ground-truth evaluations of time series feature attributions, often producing contradictory rankings of attribution quality due to differences in feature amplitude or temporal extent between classes.