TERI: An Effective Framework for Trajectory Recovery with Irregular Time Intervals
Summary: TERI tackles trajectory recovery with irregular time intervals and unknown missing positions via a two-stage pipeline that first detects recovery positions and then imputes missing points, removing the unrealistic prior assumption. Each stage employs RETE, a Transformer encoder with learnable Fourier encodings plus collective transition-pattern and trajectory contrastive learning, yielding large gains over baselines on three real-world datasets. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Yile Chen
- 2. Gao Cong
- 3. Cuauhtemoc Anda
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Outgoing Citations (Sorted by Pagerank)
Showing 3 of 3 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 1,115 | Finding Time Period-Based Most Frequent Path in Big Trajectory Data | 2013 | SIGMOD | 0.00013894562 |
| 3,618 | Calibrating Trajectory Data for Similarity-based Analysis | 2013 | SIGMOD | 6.9085505e-05 |
| 9,353 | Points-of-Interest Relationship Inference with Spatial-enriched Graph Neural Networks | 2022 | VLDB | 4.3519095e-05 |