EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Self-Supervised Contrastive Learning for Individual and Collective Outlier Detection in Semantic Trajectories

Xingzu Zhan, Hossein Amiri, Zheng Zhang, Dazhou Yu, Yuntong Hu, Honghang Chen, Liang Zhao, Andreas Züfle

ACM Transactions on Spatial Algorithms and Systems · 31.12.2026 · 12 (4) · 1-27

DOI: 10.1145/3809184 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Spatial Algorithms and Systems, online erschienen am 13.07.2026. Verfasst von Xingzu Zhan und 7 weiteren Autor:innen. Die Arbeit nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Intelligence Advanced Research Projects Activity, Department of Interior/Interior Business Center, NSF.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Semantic trajectories enrich spatiotemporal data with textual semantics such as trip purposes and activities at points of interest, enabling the discovery of outlier behaviors relevant to public health, social security, and urban planning. Existing detectors often depend on hand crafted rules and rarely fuse space, time, and text in a transferable way. We propose TOD4Traj , an unsupervised and transfer ready framework for human semantic trajectories that detects anomalies at both the individual and collective levels. TOD4Traj first unifies modalities through spatiotemporal to semantic contrastive alignment so heterogeneous signals share a common representation. It then learns regular mobility via temporal contrastive learning that aligns the same weekday and separates different weekdays. Deviations are scored by combining a consistency score against a user’s own history with a population score based on a small set of learned centroids that capture low rank mobility regularities. For group analysis, we introduce a population level contrastive objective and a collective outlier score that compare a date’s population embedding with historical weekday prototypes, revealing collective abnormality. Across simulated cities and a GeoLife derived dataset, TOD4Traj consistently outperforms strong baselines on both tasks and shows robust zero shot transfer across cities, demonstrating effectiveness, robustness, and adaptability for outlier detection in human semantic trajectories.

Förderung

  • Intelligence Advanced Research Projects Activity
  • Department of Interior/Interior Business Center
  • NSF

Zitieren

APA

Zhan, X., Amiri, H., Zhang, Z., Yu, D., Hu, Y., Chen, H., Zhao, L., & Züfle, A. (2026). Self-Supervised Contrastive Learning for Individual and Collective Outlier Detection in Semantic Trajectories. ACM Transactions on Spatial Algorithms and Systems, 12(4), 1-27. https://doi.org/10.1145/3809184

Vancouver

Zhan X, Amiri H, Zhang Z, Yu D, Hu Y, Chen H, et al. Self-Supervised Contrastive Learning for Individual and Collective Outlier Detection in Semantic Trajectories. ACM Transactions on Spatial Algorithms and Systems. 2026;12(4):1-27. doi:10.1145/3809184

BibTeX
@article{Zhan2026,
  author = {Zhan, Xingzu and Amiri, Hossein and Zhang, Zheng and Yu, Dazhou and Hu, Yuntong and Chen, Honghang and Zhao, Liang and Züfle, Andreas},
  title = {Self-Supervised Contrastive Learning for Individual and Collective Outlier Detection in Semantic Trajectories},
  journal = {ACM Transactions on Spatial Algorithms and Systems},
  year = {2026},
  volume = {12},
  number = {4},
  pages = {1--27},
  doi = {10.1145/3809184}
}
Kostenlos starten →