# DETECT: Deep Trajectory Clustering for Mobility-Behavior Analysis

arXiv: https://arxiv.org/abs/2003.01351 · HTML: https://mlsanity.com/paper/2003.01351/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Mar 2020.

## Built on by (most cited first, 11 of 11)

- [Self-supervised Trajectory Representation Learning with Temporal Regularities and Travel Semantics](https://mlsanity.com/paper/2211.09510/) (2022)
- [SpaBERT: A Pretrained Language Model from Geographic Data for Geo-Entity Representation](https://mlsanity.com/paper/2210.12213/) (2022)
- [Trajectory Data Management and Mining: A Survey from Deep Learning to the LLM Era](https://mlsanity.com/paper/2403.14151/) (2024)
- [CGC: Contrastive Graph Clustering for Community Detection and Tracking](https://mlsanity.com/paper/2204.08504/) (2022)
- [UVTM: Universal Vehicle Trajectory Modeling with ST Feature Domain Generation](https://mlsanity.com/paper/2402.07232/) (2024)
- [Clustering Human Mobility with Multiple Spaces](https://mlsanity.com/paper/2301.08524/) (2023)
- [Context-Aware Trajectory Anomaly Detection](https://mlsanity.com/paper/2410.19136/) (2024)
- [BeSTAD: Behavior-Aware Spatio-Temporal Anomaly Detection for Human Mobility Data](https://mlsanity.com/paper/2510.12076/) (2025)
- [Fitting Multiple Machine Learning Models with Performance Based Clustering](https://mlsanity.com/paper/2411.06572/) (2024)
- [Deep Clustering Evaluation: How to Validate Internal Clustering Validation Measures](https://mlsanity.com/paper/2403.14830/) (2024)
- [From Mobile Data to Business Insights: An End-to-End Analytics Framework for Large-Scale Urban Mobility Analysis and Decision Support](https://mlsanity.com/paper/2607.03394/) (2026)

## Abstract (arXiv)

Identifying mobility behaviors in rich trajectory data is of great economic and social interest to various applications including urban planning, marketing and intelligence. Existing work on trajectory clustering often relies on similarity measurements that utilize raw spatial and/or temporal information of trajectories. These measures are incapable of identifying similar moving behaviors that exhibit varying spatio-temporal scales of movement. In addition, the expense of labeling massive trajectory data is a barrier to supervised learning models. To address these challenges, we propose an unsupervised neural approach for mobility behavior clustering, called the Deep Embedded TrajEctory ClusTering network (DETECT). DETECT operates in three parts: first it transforms the trajectories by summarizing their critical parts and augmenting them with context derived from their geographical locality (e.g., using POIs from gazetteers). In the second part, it learns a powerful representation of trajectories in the latent space of behaviors, thus enabling a clustering function (such as k-means) to be applied. Finally, a clustering oriented loss is directly built on the embedded features to jointly perform feature refinement and cluster assignment, thus improving separability between mobility behaviors. Exhaustive quantitative and qualitative experiments on two real-world datasets demonstrate the effectiveness of our approach for mobility behavior analyses.