Research map / Probabilistic and scientific modeling / Dynamical systems
Toward Time-Continuous Data Inference in Sparse Urban CrowdSensing
Hao Du, Wenbin Liu, Ziyu Sun, Haoyang Su, En Wang, Yuanbo Xu
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 time-aware timescale fusion with physical intervals (ablation) | Mamba-DMF · Highways England 2021 (1month), 0.9 deleted | RMSE: 75.2 -> 42.8 | Improved |
| add time-aware timescale fusion (ablation) | Mamba-DMF · Highways England 2021 (2months), 0.9 deleted | RMSE: 58.7 -> 40.7 | Improved |
| add time-aware timescale fusion (ablation) | Mamba-DMF · Highways England 2021 (2months), 0.5 deleted | RMSE: 31.5 -> 31.8 | No clear effect |
| add time-aware timescale fusion (ablation) | Mamba-DMF · Highways England 2021 (1month), 0.5 deleted | RMSE: 30.4 -> 29.2 | Improved |
| use Mamba temporal encoder with DMF on extremely sparse data | DMF · SensorScope, 1/57 sensed | RMSE: 4.7 -> 2.5 | Improved |
| use Mamba temporal encoder with DMF on extremely sparse data | DMF · Highways England, 1/15 sensed | RMSE: 40.7 -> 22.9 | Improved |
| time-continuous TIME-DMF vs time-discrete methods | STformer · U-AIR | RMSE: 80.2 -> 80.8 | No clear effect |
| time-continuous TIME-DMF vs time-discrete methods | STformer · TaxiSpeed | RMSE: 10068.7 -> 8822.4 | Improved |
| time-continuous TIME-DMF vs time-discrete methods | STformer · Highways England C | RMSE: 50.8 -> 42.5 | Improved |
| use Mamba encoder instead of Transformers | iTransformer · Efficiency | training time per epoch: 58ms -> 1.8ms | Improved |
Closest papers by meaning
- Learning from Highly Sparse Spatio-temporal Data (NeurIPS 2024 · similarity 0.83)
- Decomposed Spatio-Temporal Mamba for Long-Term Traffic Prediction (AAAI 2025 · similarity 0.83)
- DiM-TS: Bridge the Gap Between Selective State Space Models and Time Series for Generative Modeling (AAAI 2026 · similarity 0.83)
- Social-Mamba: Socially-Aware Trajectory Forecasting with State-Space Models (ECCV 2026 · similarity 0.82)
- SMamba: Sparse Mamba for Event-based Object Detection (AAAI 2025 · similarity 0.82)
- Explainable Origin-Destination Crowd Flow Interpolation via Variational Multi-Modal Recurrent Graph Auto-Encoder (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.
