HiT-JEPA: A Hierarchical Self-supervised Trajectory Embedding Framework for Similarity Computation
This addresses the challenge of designing trajectory representations that incorporate both fine-grained details and high-level summaries for analyzing spatial movement patterns, though it appears incremental as it builds on existing self-supervised and hierarchical methods.
The paper tackles the problem of representing urban trajectory data by proposing HiT-JEPA, a hierarchical self-supervised framework that captures multi-scale information, resulting in richer representations for trajectory similarity computation as shown in experiments on real-world datasets.
The representation of urban trajectory data plays a critical role in effectively analyzing spatial movement patterns. Despite considerable progress, the challenge of designing trajectory representations that can capture diverse and complementary information remains an open research problem. Existing methods struggle in incorporating trajectory fine-grained details and high-level summary in a single model, limiting their ability to attend to both long-term dependencies while preserving local nuances. To address this, we propose HiT-JEPA (Hierarchical Interactions of Trajectory Semantics via a Joint Embedding Predictive Architecture), a unified framework for learning multi-scale urban trajectory representations across semantic abstraction levels. HiT-JEPA adopts a three-layer hierarchy that progressively captures point-level fine-grained details, intermediate patterns, and high-level trajectory abstractions, enabling the model to integrate both local dynamics and global semantics in one coherent structure. Extensive experiments on multiple real-world datasets for trajectory similarity computation show that HiT-JEPA's hierarchical design yields richer, multi-scale representations. Code is available at: https://anonymous.4open.science/r/HiT-JEPA.