Revisiting CNNs for Trajectory Similarity Learning
Summary: Revisits CNNs for trajectories, arguing local similarity matters more than long-range dependency and proposing ConvTraj with 1D convs for sequential patterns and 2D convs for geo-distribution. With theoretical support, ConvTraj achieves SOTA accuracy and large speedups (240× training, 2.16× inference on 1.6M Porto trajectories). (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. Zhihao Chang
- 2. Linzhu Yu
- 3. Huan Li
- 4. Sai Wu
- 5. Gang Chen
- 6. Dongxiang Zhang
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 5 of 5 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 |
| 1,776 | Distributed Trajectory Similarity Search | 2017 | VLDB | 0.00010593716 |
| 2,192 | DITA: Distributed In-Memory Trajectory Analytics | 2018 | SIGMOD | 9.3185895e-05 |
| 6,512 | Trajectory Similarity Measurement: An Efficiency Perspective | 2024 | VLDB | 5.0321577e-05 |
Previous
Page 1 / 1
Next