Research map / Time series / Foundation models for time series
Generalized Time Warping Invariant Dictionary Learning for Time Series Classification and Clustering
Ruiyu Xu, Chao Wang, Yongxiang Li, Jianguo Wu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use GTWIDL instead of DTW-based dictionary learning (TWI-kSVD, RISLDTW, RISLDTW-ELS) for classification | dictionary-learning classifier · UPPER | classification accuracy: 0.9139 -> 0.9885 | Improved |
| use GTWIDL instead of WDTW 1NN for classification | classifier · LOWER | classification accuracy: 0.9473 -> 0.9888 | Improved |
| use GTWIDL instead of WDTW 1NN for classification | classifier · FiftyWords | classification accuracy: 0.7714 -> 0.7429 | Hurt |
| use GTWIDL instead of WDTW 1NN for classification | classifier · char-traj | classification accuracy: 0.9605 -> 0.9595 | Hurt |
| use GTWIDL instead of RISLDTW-ELS for classification | classifier · DSR | classification accuracy: 0.8399 -> 0.9608 | Improved |
| use GTWIDL instead of DTW 1NN for classification | classifier · ArrowHead | classification accuracy: 0.7029 -> 0.8514 | Improved |
| refine SSC clustering with GTWIDL dictionaries iteratively | Sparse Subspace Clustering · Trace (clustering) | clustering accuracy: 0.5900 -> 1.0000 | Improved |
| refine SSC clustering with GTWIDL dictionaries iteratively | Sparse Subspace Clustering · LOWER (clustering) | clustering accuracy: 0.6750 -> 0.7837 | Improved |
| use GTWIDL instead of DDTW spectral clustering | clustering · UMD (clustering) | clustering accuracy: 0.6797 -> 0.6537 | Hurt |
| use GTWIDL instead of RISLDTW k-means clustering | clustering · DIGITS (clustering) | clustering accuracy: 0.6580 -> 0.9510 | Improved |
| use GTWIDL instead of WDTW spectral clustering | clustering · char-traj (clustering) | clustering accuracy: 0.8110 -> 0.8030 | Hurt |
| choose atoms per class adaptively with threshold zeta instead of a fixed number of atoms | GTWIDL classifier · classification benchmarks | classification accuracy | Improved |
Closest papers by meaning
- Perturbed Dynamic Time Warping: A Probabilistic Framework and Generalized Variants (ICLR 2026 · similarity 0.87)
- DTWNet: a Dynamic Time Warping Network (NeurIPS 2019 · similarity 0.87)
- Soft-DTW: a Differentiable Loss Function for Time-Series (ICML 2017 · similarity 0.86)
- Deep Canonical Time Warping for Simultaneous Alignment and Representation Learning of Sequences (TPAMI 2017 · similarity 0.86)
- Improved Learning via k-DTW: A Novel Dissimilarity Measure for Curves (ICML 2025 · similarity 0.85)
- TimePoint: Accelerated Time Series Alignment via Self-Supervised Keypoint and Descriptor Learning (ICML 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
