Region-Point Joint Representation for Effective Trajectory Similarity Learning
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (18) · 15439-15447
DOI: 10.1609/aaai.v40i18.38571 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Hao Long und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).
Abstract (Originalsprache)
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 RePo, a novel method that jointly encodes Region-wise and Point-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.
Zitieren
APA
Long, H., Zhou, S., Chen, L., & Shang, S. (2026). Region-Point Joint Representation for Effective Trajectory Similarity Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(18), 15439-15447. https://doi.org/10.1609/aaai.v40i18.38571
Vancouver
Long H, Zhou S, Chen L, Shang S. Region-Point Joint Representation for Effective Trajectory Similarity Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(18):15439-15447. doi:10.1609/aaai.v40i18.38571
BibTeX
@article{Long2026,
author = {Long, Hao and Zhou, Silin and Chen, Lisi and Shang, Shuo},
title = {Region-Point Joint Representation for Effective Trajectory Similarity Learning},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {18},
pages = {15439--15447},
doi = {10.1609/aaai.v40i18.38571}
}
EUVIMED