# HiT-JEPA: A Hierarchical Self-supervised Trajectory Embedding Framework for Similarity Computation

arXiv: https://arxiv.org/abs/2507.00028 · HTML: https://mlsanity.com/paper/2507.00028/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 48 references that are in the map.
- First posted on arXiv 17 Jun 2025.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting](https://mlsanity.com/paper/2007.02842/) (2020)
- [Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning](https://mlsanity.com/paper/2206.02647/) (2022)
- [HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization](https://mlsanity.com/paper/1905.06566/) (2019)
- [Contrastive Trajectory Similarity Learning with Dual-Feature Attention](https://mlsanity.com/paper/2210.05155/) (2022)
- [Understanding Masked Autoencoders via Hierarchical Latent Variable Models](https://mlsanity.com/paper/2306.04898/) (2023)
- [Pre-training General Trajectory Embeddings with Maximum Multi-view Entropy Coding](https://mlsanity.com/paper/2207.14539/) (2022)
- [Hierarchical Self-supervised Representation Learning for Movie Understanding](https://mlsanity.com/paper/2204.03101/) (2022)
- [UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Traces](https://mlsanity.com/paper/2411.03859/) (2024)
- [T-JEPA: A Joint-Embedding Predictive Architecture for Trajectory Similarity Computation](https://mlsanity.com/paper/2406.12913/) (2024)
- [HiCLRE: A Hierarchical Contrastive Learning Framework for Distantly Supervised Relation Extraction](https://mlsanity.com/paper/2202.13352/) (2022)
- [SIMformer: Single-Layer Vanilla Transformer Can Learn Free-Space Trajectory Similarity](https://mlsanity.com/paper/2410.14629/) (2024)
- [Context-Enhanced Multi-View Trajectory Representation Learning: Bridging the Gap through Self-Supervised Models](https://mlsanity.com/paper/2410.13196/) (2024)

## Built on by (most cited first, 6 of 6)

- [TrajDLM: Topology-Aware Block Diffusion Language Model for Trajectory Generation](https://mlsanity.com/paper/2605.10020/) (2026)
- [Learn from your own latents and not from tokens: A sample-complexity theory](https://mlsanity.com/paper/2605.27734/) (2026)
- [TrajPrism: A Multi-Task Benchmark for Language-Grounded Urban Trajectory Understanding](https://mlsanity.com/paper/2605.10782/) (2026)
- [MoCo-AIS: A Contrastive Learning Framework for Similarity Computation of Vessel Trajectories](https://mlsanity.com/paper/2606.17978/) (2026)
- [Learning Spatio-Temporal Foundation Models from Pure Synthetic Data](https://mlsanity.com/paper/2607.16251/) (2026)
- [Does Joint-Embedding Predictive Architecture Pretraining Help Time Series Forecasting?](https://mlsanity.com/paper/2609.31680/) (2026)

## Abstract (arXiv)

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.