Search Results for author:
Found 2 papers, 2 papers with code
Learning to Embed Time Series Patches Independently
However, we argue that capturing such patch dependencies might not be an optimal strategy for time series representation learning; rather, learning to embed patches independently results in better time series representations.
Soft Contrastive Learning for Time Series
SoftCLT is a plug-and-play method for time series contrastive learning that improves the quality of learned representations without bells and whistles.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
