Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Reading Your Actions: Learning Generalizable Action Representations via Pre-training AEMG
Zhenghao Huang, Huilin Yao, Kaikai Wang, Lin Shu
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 |
|---|---|---|---|
| add EMG vocabulary with vector quantization (ablation) | AEMG-Large · ULB-MLG LOSO | accuracy (%): 62.3 -> 91.50 | Improved |
| add masked modeling pre-training (ablation) | AEMG-Large · ULB-MLG LOSO | accuracy (%): 81.3 -> 91.50 | Improved |
| add masked modeling pre-training (ablation) | AEMG-Large · Ninapro DB4 LOSO | accuracy (%): 79.5 -> 88.10 | Improved |
| use NCT contraction-based tokenization instead of fixed windows (ablation) | AEMG · 4 datasets LOSO average | accuracy (%): 82.15 -> 91.28 | Improved |
| use NCT instead of fixed windows (ablation) | AEMG · VQ reconstruction | reconstruction loss | Improved |
| use NCT instead of fixed windows (ablation) | AEMG · masked pre-training | mask prediction accuracy | Hurt |
| scale from AEMG-Base to AEMG-Large | AEMG · 4 datasets LOSO average | accuracy (%): 86.49 -> 89.81 | Improved |
| fine-tune with only 5% target data instead of 80% | AEMG-Large · ULB-MLG | accuracy (%): 91.00 -> 88.50 | Mixed |
| use AEMG-Large instead of best domain adaptation baseline on EMG-EPN | AEMG-Large · EMG-EPN LOSO | accuracy (%): 88.97 -> 88.32 | Hurt |
Closest papers by meaning
- emg2qwerty: A Large Dataset with Baselines for Touch Typing using Surface Electromyography (NeurIPS 2024 · similarity 0.90)
- EMGBench: Benchmarking Out-of-Distribution Generalization and Adaptation for Electromyography (NeurIPS 2024 · similarity 0.88)
- SplashNet: Split‑and‑Share Encoders for Accurate and Efficient Typing with Surface Electromyography (NeurIPS 2025 · similarity 0.88)
- emg2pose: A Large and Diverse Benchmark for Surface Electromyographic Hand Pose Estimation (NeurIPS 2024 · similarity 0.86)
- Quasi-Linear ICA for Motor Unit Decomposition during Dynamic Contractions (NeurIPS 2026 · similarity 0.86)
- Learning Options for Compositional Motor Control with Adapter Banks (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.
