Time2State: An Unsupervised Framework for Inferring the Latent States in Time Series Data
Summary: Unsupervised Time2State infers latent states in massive multivariate time series, exposing high-level semantics (e.g., run, walk, jump). A sliding-window encoder with a novel LSE-Loss reduces computational cost and yields up to 15% accuracy gains over prior time-series representation methods. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Chengyu Wang (National University of Defense Technology)
- 2. Kui Wu (University of Victoria)
- 3. Tongqing Zhou (National University of Defense Technology)
- 4. Zhiping Cai (National University of Defense Technology)
BibTeX Citation
@inproceedings{wang_sigmod23,
title = {{Time2State: An Unsupervised Framework for Inferring the Latent States in Time Series Data}},
author = {Wang, Chengyu and Wu, Kui and Zhou, Tongqing and Cai, Zhiping},
series = {{SIGMOD} '23},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3588697},
url = {https://dl.acm.org/doi/10.1145/3588697},
year = {2023}
}Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 9,302 | ISSD: Indicator Selection for Time Series State Detection | 2025 | SIGMOD | 5.289545e-05 |
| 10,607 | CLaP - State Detection from Time Series | 2026 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 2 of 2 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 291 | OPTICS: Ordering Points To Identify the Clustering Structure | 1999 | SIGMOD | 0.00022264197 |
| 4,379 | AutoPlait: Automatic Mining of Co-evolving Time Sequences | 2014 | SIGMOD | 6.735265e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 12,471 | Parsimonious Linear Fingerprinting for Time Series | 2010 | VLDB |
| 2 | 3,399 | Finding Semantics in Time Series | 2011 | SIGMOD |
| 3 | 4,851 | Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles | 2022 | VLDB |
| 4 | 5,986 | AutoTSAD: Unsupervised Holistic Anomaly Detection for Time Series Data | 2024 | VLDB |
| 5 | 2,346 | Series2Graph: Graph-based Subsequence Anomaly Detection for Time Series | 2020 | VLDB |
| 6 | 7,060 | Interpretable Clustering of Multivariate Time Series with Time2Feat | 2023 | VLDB |
| 7 | 5,038 | Time2Feat: Learning Interpretable Representations for Multivariate Time Series Clustering | 2023 | VLDB |
| 8 | 9,698 | TimeCSL: Unsupervised Contrastive Learning of General Shapelets for Explorable Time Series Analysis | 2024 | VLDB |
| 9 | 13,360 | A Shapelet-based Framework for Unsupervised Multivariate Time Series Representation Learning | 2024 | VLDB |
| 10 | 10,607 | CLaP - State Detection from Time Series | 2026 | VLDB |