RED: Effective Trajectory Representation Learning with Comprehensive Information
Summary: RED: Transformer MAE for trajectories with road-aware masking, spatio-temporal-user joint embeddings, and attention modified for spatial–temporal correlations. Dual-objective (next-segment prediction + reconstruction) training improves accuracy >5% vs nine SOTA methods across 4 tasks and 3 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. Silin Zhou
- 2. Shuo Shang
- 3. Lisi Chen
- 4. Christian S. Jensen
- 5. Panos Kalnis
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 2 of 2 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 251 | Robust and Fast Similarity Search for Moving Object Trajectories | 2005 | SIGMOD | 0.00030644658 |
| 358 | On The Marriage of Lp-norms and Edit Distance | 2004 | VLDB | 0.0002599481 |
Previous
Page 1 / 1
Next