Region-Point Joint Representation for Effective Trajectory Similarity Learning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Long, Hao, Zhou, Silin, Chen, Lisi, Shang, Shuo
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917085398958080
author Long, Hao
Zhou, Silin
Chen, Lisi
Shang, Shuo
author_facet Long, Hao
Zhou, Silin
Chen, Lisi
Shang, Shuo
contents Recent learning-based methods have reduced the computational complexity of traditional trajectory similarity computation, but state-of-the-art (SOTA) methods still fail to leverage the comprehensive spectrum of trajectory information for similarity modeling. To tackle this problem, we propose \textbf{RePo}, a novel method that jointly encodes \textbf{Re}gion-wise and \textbf{Po}int-wise features to capture both spatial context and fine-grained moving patterns. For region-wise representation, the GPS trajectories are first mapped to grid sequences, and spatial context are captured by structural features and semantic context enriched by visual features. For point-wise representation, three lightweight expert networks extract local, correlation, and continuous movement patterns from dense GPS sequences. Then, a router network adaptively fuses the learned point-wise features, which are subsequently combined with region-wise features using cross-attention to produce the final trajectory embedding. To train RePo, we adopt a contrastive loss with hard negative samples to provide similarity ranking supervision. Experiment results show that RePo achieves an average accuracy improvement of 22.2\% over SOTA baselines across all evaluation metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2511_13125
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Region-Point Joint Representation for Effective Trajectory Similarity Learning
Long, Hao
Zhou, Silin
Chen, Lisi
Shang, Shuo
Computer Vision and Pattern Recognition
Information Retrieval
Machine Learning
Recent learning-based methods have reduced the computational complexity of traditional trajectory similarity computation, but state-of-the-art (SOTA) methods still fail to leverage the comprehensive spectrum of trajectory information for similarity modeling. To tackle this problem, we propose \textbf{RePo}, a novel method that jointly encodes \textbf{Re}gion-wise and \textbf{Po}int-wise features to capture both spatial context and fine-grained moving patterns. For region-wise representation, the GPS trajectories are first mapped to grid sequences, and spatial context are captured by structural features and semantic context enriched by visual features. For point-wise representation, three lightweight expert networks extract local, correlation, and continuous movement patterns from dense GPS sequences. Then, a router network adaptively fuses the learned point-wise features, which are subsequently combined with region-wise features using cross-attention to produce the final trajectory embedding. To train RePo, we adopt a contrastive loss with hard negative samples to provide similarity ranking supervision. Experiment results show that RePo achieves an average accuracy improvement of 22.2\% over SOTA baselines across all evaluation metrics.
title Region-Point Joint Representation for Effective Trajectory Similarity Learning
topic Computer Vision and Pattern Recognition
Information Retrieval
Machine Learning
url https://arxiv.org/abs/2511.13125