提出分层自监督轨迹表示框架，同时捕捉细节与全局模式。
HiT-JEPA: A Hierarchical Self-supervised Trajectory Embedding Framework for Similarity Computation
- 构建三层分层结构，逐级捕获点级细节、中间模式和高层抽象
- 在多个真实数据集上实现更优的轨迹相似性计算效果
- 适合需要多尺度轨迹分析的交通行为研究者
城市轨迹数据的表示在有效分析空间移动模式中起关键作用。尽管已有显著进展，但设计能捕捉多样且互补信息的轨迹表示仍是开放问题。现有方法难以在同一模型中融合轨迹细粒度细节与高层摘要，限制了其对长期依赖和局部细微特征的关注。为此，我们提出HiT-JEPA（基于联合嵌入预测架构的轨迹语义分层交互），一种统一框架，用于学习跨语义抽象层次的多尺度城市轨迹表示。该框架采用三层分层结构，逐步捕获点级细粒度细节、中间模式及高层轨迹抽象，使模型能在单一结构中整合局部动态与全局语义。在多个真实数据集上的轨迹相似性计算实验表明，HiT-JEPA的分层设计生成了更丰富、多尺度的表示。代码已公开：https://anonymous.4open.science/r/HiT-JEPA。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。