Research map / Time series / Foundation models for time series
Diffeomorphic Temporal Alignment Nets
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| align signals with DTAN before averaging | Synthetic Dir(32) test · Synthetic Dir(32) test | variance: 0.466 -> 0.234 | Helped |
| apply recurrent warps (R-DTAN4) instead of single warp, same parameters (ablation) | DTAN · Synthetic Dir(16) test | variance: 0.332 -> 0.154 | Helped |
| apply recurrent warps (R-DTAN4) instead of single warp (ablation) | DTAN · Synthetic Dir(8) train | variance: 0.254 -> 0.122 | Helped |
| use DTAN alignment before nearest centroid classification, versus Euclidean mean | NCC on UCR · UCR archive (84 datasets) | % datasets better or equal: 93% | Helped |
| DTAN averaging versus SoftDTW averaging | NCC on UCR · UCR archive (84 datasets) | % datasets better or equal: 62% | Mixed |
| feed DTAN-aligned input to CNN classifier | CNN · UCR archive (84 datasets) | % datasets better or equal: 87% | Helped |
Closest papers by meaning
- Regularization-free Diffeomorphic Temporal Alignment Nets (ICML 2023 · similarity 0.94)
- Closed-Form Diffeomorphic Transformations for Time Series Alignment (ICML 2022 · similarity 0.90)
- Deep Declarative Dynamic Time Warping for End-to-End Learning of Alignment Paths (ICLR 2023 · similarity 0.89)
- Deep Canonical Time Warping (CVPR 2016 · similarity 0.89)
- TimePoint: Accelerated Time Series Alignment via Self-Supervised Keypoint and Descriptor Learning (ICML 2025 · similarity 0.88)
- TStruct: Learning Shared Temporal Structures for Long-Term Time-Series Forecasting (NeurIPS 2026 · 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.