Universal time-series representation learning: A survey

P Trirat, Y Shin, J Kang, Y Nam, J Na, M Bae… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Time-series data exists in every corner of real-world systems and services, ranging from
satellites in the sky to wearable devices on human bodies. Learning representations by …

Weakly-supervised temporal action localization with multi-modal plateau Transformers

X Hu, K Li, D Patel, E Kruus… - Proceedings of the …, 2024‏ - openaccess.thecvf.com
Abstract Weakly Supervised Temporal Action Localization (WSTAL) aims to jointly localize
and classify action segments in untrimmed videos with only video level annotations. To …

Breaking the time-frequency granularity discrepancy in time-series anomaly detection

Y Nam, S Yoon, Y Shin, M Bae, H Song… - Proceedings of the …, 2024‏ - dl.acm.org
In light of the remarkable advancements made in time-series anomaly detection (TSAD),
recent emphasis has been placed on exploiting the frequency domain as well as the time …

Exploiting Representation Curvature for Boundary Detection in Time Series

Y Shin, J Park, S Yoon, H Song… - Advances in Neural …, 2025‏ - proceedings.neurips.cc
Boundaries are the timestamps at which a class in a time series changes. Recently,
representation-based boundary detection has gained popularity, but its emphasis on …

Context consistency regularization for label sparsity in time series

Y Shin, S Yoon, H Song, D Park, B Kim… - International …, 2023‏ - proceedings.mlr.press
Labels are typically sparse in real-world time series due to the high annotation cost.
Recently, consistency regularization techniques have been used to generate artificial labels …

Label propagation techniques for artifact detection in imbalanced classes using photoplethysmogram signals

C Macabiau, TD Le, K Albert, M Shahriari… - IEEE …, 2024‏ - ieeexplore.ieee.org
This study aimed to investigate the application of label propagation techniques to propagate
labels among photoplethysmogram (PPG) signals, particularly in imbalanced class …

Online Drift Detection with Maximum Concept Discrepancy

K Wan, Y Liang, S Yoon - Proceedings of the 30th ACM SIGKDD …, 2024‏ - dl.acm.org
Continuous learning from an immense volume of data streams becomes exceptionally
critical in the internet era. However, data streams often do not conform to the same …

VarDrop: Enhancing Training Efficiency by Reducing Variate Redundancy in Periodic Time Series Forecasting

J Kang, Y Shin, JG Lee - arxiv preprint arxiv:2501.14183, 2025‏ - arxiv.org
Variate tokenization, which independently embeds each variate as separate tokens, has
achieved remarkable improvements in multivariate time series forecasting. However …

Representation-based time series label propagation for active learning

D Chen, XY Li, A Li, YB Yang - 2023 26th International …, 2023‏ - ieeexplore.ieee.org
Time series data are ubiquitous and informative nowadays, but the labels are difficult to
obtain. Active learning is one way to reduce labeling efforts. The label-continuous property …

Multivariate time series anomaly detection method based on mTranAD

C Zhang, Y Li, J Li, G Li, H Ma - International Conference on Intelligent …, 2023‏ - Springer
Multivariate time series anomaly detection is a crucial area of research in several domains,
including finance, logistics, and manufacturing. Successfully identifying abnormal behaviors …