Research map / Probabilistic and scientific modeling / Molecules and proteins
Out-of-Sight Embodied Agents: Multimodal Tracking, Sensor Fusion, and Trajectory Forecasting
Haichao Zhang, Yi Xu, Yun Fu
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 Sensor Denoising Encoder (ablation) | VPD model · Vi-Fi | SUM: 32.12 -> 27.24 | Improved |
| add Sensor Denoising Encoder (ablation) | VPD model · JRDB | SUM: 29.66 -> 25.51 | Improved |
| add Mapping Parameters Estimator (ablation) | VPD model · Vi-Fi | SUM: 32.33 -> 27.24 | Improved |
| add Mapping Parameters Estimator (ablation) | VPD model · JRDB | SUM: 32.94 -> 25.51 | Improved |
| add VPP module (ablation) | VPD model · Vi-Fi | SUM: 28.42 -> 27.24 | Improved |
| add VPP module (ablation) | VPD model · JRDB | SUM: 32.48 -> 25.51 | Improved |
| add OPD module (ablation) | VPD model · Vi-Fi | SUM: 27.33 -> 27.24 | Improved |
| add OPD module (ablation) | VPD model · JRDB | SUM: 30.01 -> 25.51 | Improved |
| insert VPD into Vanilla RNN two-stage pipeline | Vanilla RNN · JRDB | SUM: 138.41 -> 31.32 | Improved |
| insert VPD into Vanilla LSTM two-stage pipeline | Vanilla LSTM · Vi-Fi | SUM: 118.44 -> 30.39 | Improved |
| insert VPD into Vanilla Transformer two-stage pipeline | Vanilla Transformer · JRDB | SUM: 36.99 -> 25.51 | Improved |
| insert VPD into Vanilla LSTM two-stage pipeline | Vanilla LSTM · JRDB | MSE-P: 41.28 -> 41.80 | No clear effect |
Closest papers by meaning
- OOSTraj: Out-of-Sight Trajectory Prediction With Vision-Positioning Denoising (CVPR 2024 · similarity 0.95)
- Unified Multi-Agent Trajectory Modeling with Masked Trajectory Diffusion (ICCV 2025 · similarity 0.88)
- Quo Vadis: Is Trajectory Forecasting the Key Towards Long-Term Multi-Object Tracking? (NeurIPS 2022 · similarity 0.87)
- Forecasting From LiDAR via Future Object Detection (CVPR 2022 · similarity 0.86)
- Pedestrian Trajectory Prediction with Missing Data: Datasets, Imputation, and Benchmarking (NeurIPS 2024 · similarity 0.86)
- Future-Aware End-to-End Driving: Bidirectional Modeling of Trajectory Planning and Scene Evolution (NeurIPS 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.
