Research map / Time series / Foundation models for time series
Deep Canonical Time Warping
Check 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 |
|---|---|---|---|
| Use deep nonlinear feature transformations with temporal warping instead of linear canonical projections | CTW for XRMB acoustic-articulatory alignment · XRMB | alignment error: 58.92 ± 28.8 -> 7.19 ± 1.79 | Helped |
| Use deep nonlinear feature transformations with temporal warping instead of direct observation-space alignment | DTW for XRMB acoustic-articulatory alignment · XRMB | alignment error: 63.52 ± 27.06 -> 7.19 ± 1.79 | Helped |
| Use DCTW's learned nonlinear representations for visual-auditory alignment | Audio-visual alignment methods · CUAVE | alignment error | Helped |
| Use deep nonlinear representations rather than linear projections for facial action-unit alignment | CTW and GTW · MMI Facial Expression Dataset | temporal phase detection accuracy | Helped |
| Use a shared learned representation for multiple feature sets | Temporal alignment on Weizmann · Weizmann | alignment error | Helped |
Closest papers by meaning
- Deep Declarative Dynamic Time Warping for End-to-End Learning of Alignment Paths (ICLR 2023 · similarity 0.90)
- TimePoint: Accelerated Time Series Alignment via Self-Supervised Keypoint and Descriptor Learning (ICML 2025 · similarity 0.90)
- Perturbed Dynamic Time Warping: A Probabilistic Framework and Generalized Variants (ICLR 2026 · similarity 0.89)
- Diffeomorphic Temporal Alignment Nets (NeurIPS 2019 · similarity 0.89)
- Time Series Representations with Hard-Coded Invariances (ICML 2025 · similarity 0.85)
- TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment (AAAI 2025 · similarity 0.85)
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.