Research map / Architectures and efficiency / RNNs and normalization
Self-Adaptive Motion Tracking against On-body Displacement of Flexible Sensors
Chengxu Zuo, Jiawei Fang, Shihui Guo, Yipeng Qin
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 Fourier Feature Encoding to the LSTM (all components absent otherwise) (ablation) | LSTM baseline · Table 3 | MAE: 13.40 -> 11.81 | Improved |
| Add Affine Transformation layer alone (ablation) | LSTM baseline · Table 3 | MAE: 13.40 -> 12.58 | Improved |
| Add SD loss alone without affine layer (ablation) | LSTM baseline · Table 3 | MAE: 13.40 -> 14.36 | Hurt |
| Add SD loss on top of affine layer (ablation) | Affine only · Table 3 | MAE: 12.58 -> 10.27 | Improved |
| Add affine layer on top of FFE + SD loss (ablation) | FFE + SD loss · Table 3 | MAE: 12.36 -> 7.32 | Improved |
| Add SD loss on top of FFE + affine (ablation) | FFE + Affine · Table 3 | MAE: 9.38 -> 7.32 | Improved |
| Add FFE on top of affine + SD loss (ablation) | Affine + SD loss · Table 3 | MAE: 10.27 -> 7.32 | Improved |
| Add FFE to SD loss alone (ablation) | SD loss only · Table 3 | MAE: 14.36 -> 12.36 | Improved |
| Adapt with the proposed method vs best SOTA domain adaptation (HoMM) | HoMM · Table 1 | MAE: 11.03 -> 7.32 | Improved |
| Unsupervised adaptation instead of supervised tuning of affine layer | Supervised upper bound · Table 1 | MAE: 5.63 -> 7.32 | No clear effect |
| Proposed method vs AdvSKM on user 1 | AdvSKM · Table 2 user 1 | MAE: 11.84 -> 12.07 | No clear effect |
| Proposed method vs baselines on user 5 | D-CORAL · Table 2 user 5 | MAE: 19.41 -> 13.96 | Improved |
Closest papers by meaning
- Inertia-1: An Open Exploration of Wearable Motion Foundation Models (NeurIPS 2026 · similarity 0.83)
- MoPFormer: Motion-Primitive Transformer for Wearable-Sensor Activity Recognition (NeurIPS 2025 · similarity 0.83)
- SuDA: Support-based Domain Adaptation for Sim2Real Hinge Joint Tracking with Flexible Sensors (ICML 2024 · similarity 0.83)
- RelCon: Relative Contrastive Learning for a Motion Foundation Model for Wearable Data (ICLR 2025 · similarity 0.82)
- Scaling Wearable Foundation Models (ICLR 2025 · similarity 0.82)
- Spatial-Related Sensors Matters: 3D Human Motion Reconstruction Assisted with Textual Semantics (AAAI 2024 · similarity 0.81)
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.
