Research map / Time series / Foundation models for time series
TapNet: Multivariate Time Series Classification with Attentional Prototypical Network
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 |
|---|---|---|---|
| TapNet (attentional prototype network + random dimension permutation) vs strongest baseline | MTS classifiers · UEA MTS archive | average rank: 3.23 -> 1.15 | Helped |
| TapNet vs MLSTM-FCN deep baseline | MTS classifiers · SpokenArabicDigits | accuracy: 0.99 -> 0.983 | Hurt |
| add unlabeled test data to prototype estimation (Semi-TapNet) | TapNet · Handwriting | accuracy: 0.3565 -> 0.3882 | Helped |
| add unlabeled data (Semi-TapNet) | TapNet · StandWalkJump | accuracy: 0.4 -> 0.4 | No clear effect |
| add unlabeled data (Semi-TapNet) | TapNet · ArticularyWordRecognition | accuracy: 0.987 -> 0.993 | Helped |
Closest papers by meaning
- MPTSNet: Integrating Multiscale Periodic Local Patterns and Global Dependencies for Multivariate Time Series Classification (AAAI 2025 · similarity 0.91)
- TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning (ICML 2024 · similarity 0.88)
- Revisiting Attention for Multivariate Time Series Forecasting (AAAI 2025 · similarity 0.86)
- T-Rep: Representation Learning for Time Series using Time-Embeddings (ICLR 2024 · similarity 0.85)
- Temporal Query Network for Efficient Multivariate Time Series Forecasting (ICML 2025 · similarity 0.85)
- TVNet: A Novel Time Series Analysis Method Based on Dynamic Convolution and 3D-Variation (ICLR 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.