Research map / Architectures and efficiency / Attention and transformers
CTIN: Robust Contextual Transformer Network for Inertial Navigation
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 |
|---|---|---|---|
| Use CTIN instead of the strongest listed baseline | inertial navigation · RIDI Seen | ATE: 2.33 -> 1.39 | Helped |
| Use CTIN instead of the strongest listed baseline | inertial navigation · RIDI Unseen | ATE: 1.97 -> 1.86 | Helped |
| Use CTIN instead of the strongest listed baseline | inertial navigation · OxIOD Seen | ATE: 2.40 -> 2.32 | Helped |
| Use CTIN instead of the strongest listed baseline | inertial navigation · OxIOD Unseen | ATE: 3.51 -> 3.34 | Helped |
| Use CTIN instead of the strongest listed baseline | inertial navigation · RoNIN Seen | ATE: 3.99 -> 4.62 | Hurt |
| Use CTIN instead of the strongest listed baseline | inertial navigation · RoNIN Unseen | ATE: 5.76 -> 5.61 | Helped |
| Use CTIN instead of the strongest listed baseline | inertial navigation · IDOL Seen | ATE: 4.44 -> 2.90 | Helped |
| Use CTIN instead of the strongest listed baseline | inertial navigation · IDOL Unseen | ATE: 3.81 -> 3.69 | Helped |
| Use CTIN instead of the strongest listed baseline | inertial navigation · CTIN Seen | ATE: 2.02 -> 1.28 | Helped |
| Add attention layers in place of conventional spatial convolutions (ablation) | CTIN and R-ResNet · CTIN dataset | trajectory error and velocity MSE | Helped |
| Use the combined IVL+CNL multi-task loss rather than individual comparison losses (ablation) | CTIN · CTIN dataset | ATE and D-RTE | Helped |
| Use IVL+CNL rather than MSE, IVL, or CNL (ablation) | CTIN · RIDI, OxIOD, and IDOL | trajectory error | Helped |
Closest papers by meaning
- iMoT: Inertial Motion Transformer for Inertial Navigation (AAAI 2025 · similarity 0.86)
- EqNIO: Subequivariant Neural Inertial Odometry (ICLR 2025 · similarity 0.84)
- NaviFormer: A Spatio-Temporal Context-Aware Transformer for Object Navigation (AAAI 2025 · similarity 0.83)
- Accurate and Steady Inertial Pose Estimation through Sequence Structure Learning and Modulation (NeurIPS 2024 · similarity 0.83)
- Wavelet Dynamic Selection Network for Inertial Sensor Signal Enhancement (AAAI 2024 · similarity 0.82)
- Tartan IMU: A Light Foundation Model for Inertial Positioning in Robotics (CVPR 2025 · similarity 0.82)
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.