LEFT: Learnable Fusion of Tri-view Tokens for Unsupervised Time Series Anomaly Detection
Open Access
- 8 August 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 4800-4811
Abstract
No abstract availableAll Related Versions
Funding Information
- The National Natural Science Foundation of China (12433011)
- the Guangdong Basic and Applied Basic Research Foundation (2024A1515011962)
- The Australian Research Council (FT210100624)
- The Australian Research Council (DP260100326)
- The Australian Research Council (DE230101033)
- The Australian Research Council (DP240101814)
- The Australian Research Council (LP230200892)
- The Australian Research Council (LP240200546)
This publication has 25 references indexed in Scilit:
- LogicGate: Adaptive Rule-Based Modeling of Exogenous Effects for Time Series Forecasting2026
- Improving time series forecasting in frequency domain using a multi resolution dual branch mixer with noise insensitive ArcTanLossScientific Reports, 2025
- CAST: An innovative framework for Cross-dimensional Attention Structure in TransformersPattern Recognition, 2024
- A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2024
- Unraveling the ‘Anomaly’ in Time Series Anomaly Detection: A Self-supervised Tri-domain Solution2024
- Temporal-Frequency Masked Autoencoders for Time Series Anomaly Detection2024
- Sequence-Aware Factorization Machines for Temporal Predictive Analytics2020
- Loda: Lightweight on-line detector of anomaliesMachine Learning, 2015
- Isolation Forest2008
- Support Vector Data DescriptionMachine Learning, 2004