AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Region-Point Joint Representation for Effective Trajectory Similarity Learning

Hao Long, Silin Zhou, Lisi Chen, Shuo Shang

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 4 citations (OpenAlex)

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 changedWhereMeasuredEffect
add locality-aware CNN encoding (ablation)RePo · Porto, DFDHR@1: 0.374 -> 0.483Improved
add node2vec structural embedding (ablation)RePo · Chengdu, DFDHR@1: 0.273 -> 0.392Improved
add ResNet satellite visual embedding (ablation)RePo · Chengdu, DFDHR@1: 0.332 -> 0.392Improved
add correlation-aware graph encoding (ablation)RePo · Chengdu, DFDHR@1: 0.310 -> 0.392Improved
add continuity-preserving CDE encoding (ablation)RePo · Porto, DTWHR@1: 0.462 -> 0.532Improved
add continuity-preserving CDE encoding (ablation)RePo · Chengdu, DTWHR@1: 0.403 -> 0.428Improved
add locality-aware CNN encoding (ablation)RePo · Chengdu, DTWHR@1: 0.344 -> 0.428Improved
use region plus point-wise features instead of grid-only baselinesRePo vs SIMformer · Porto, DTWHR@1: 0.300 -> 0.532Improved
RePo versus best baseline under DFDRePo · Geolife, DFDHR@1: 0.316 -> 0.325No clear effect
evaluate on larger candidate pool (200k) without retrainingRePo · Porto, DTW (trained on 10k)HR@1: 0.300 -> 0.192Hurt
increase embedding dimension beyond 512 (ablation)RePo · HR@50 sensitivityHR@50No clear effect
use more than one hard negative sample (ablation)RePo · HR@50 sensitivityHR@50Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy