TRAJGANR: Trajectory-Centric Urban Multimodal Learning via Geospatially Aligned Neural Representations
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913101209665536 |
|---|---|
| author | Siampou, Maria Despoina Mai, Gengchen Lao, Ni Rao, Jinmeng Arora, Neha Shahabi, Cyrus Choudhury, Shushman |
| author_facet | Siampou, Maria Despoina Mai, Gengchen Lao, Ni Rao, Jinmeng Arora, Neha Shahabi, Cyrus Choudhury, Shushman |
| contents | Multimodal self-supervised learning (MSSL) has emerged as a key paradigm for pretraining geospatial foundation models. However, existing geospatial MSSL methods are mainly designed for static pairs of modalities, such as satellite imagery, street-view imagery, and text, where learning is driven by aligning observations from the same or nearby locations. This assumption breaks down for human mobility trajectories, which represent continuous movement along paths rather than discrete observations at individual locations. Although trajectories are important for urban understanding through their ability to capture human activity across roads, neighborhoods, and places over time, they remain largely underexplored in current geospatial MSSL frameworks. We present TrajGANR, a novel trajectory-centric geospatial MSSL framework that aligns continuous movement patterns with static, location-based observations. TrajGANR learns a continuous neural representation of trajectories at arbitrary points along each path, which enables fine-grained alignment with nearby street-view images, even when they are not co-located with any trajectory waypoints. We leverage this capability to introduce an MSSL objective that jointly aligns three modalities: trajectories, street-view images, and their geographic locations. We evaluate TrajGANR on four urban mobility and road understanding tasks. Across these tasks, TrajGANR consistently outperforms existing geospatial MSSL frameworks and a trajectory-specific foundation model. Ablation studies further demonstrate that our proposed MSSL objective and the multimodal learning framework are the primary drivers of these improvements, highlighting the importance of fine-grained geospatial alignment over coarser aggregation, as well as geospatial multimodal learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_06990 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TRAJGANR: Trajectory-Centric Urban Multimodal Learning via Geospatially Aligned Neural Representations Siampou, Maria Despoina Mai, Gengchen Lao, Ni Rao, Jinmeng Arora, Neha Shahabi, Cyrus Choudhury, Shushman Computer Vision and Pattern Recognition Machine Learning Multimodal self-supervised learning (MSSL) has emerged as a key paradigm for pretraining geospatial foundation models. However, existing geospatial MSSL methods are mainly designed for static pairs of modalities, such as satellite imagery, street-view imagery, and text, where learning is driven by aligning observations from the same or nearby locations. This assumption breaks down for human mobility trajectories, which represent continuous movement along paths rather than discrete observations at individual locations. Although trajectories are important for urban understanding through their ability to capture human activity across roads, neighborhoods, and places over time, they remain largely underexplored in current geospatial MSSL frameworks. We present TrajGANR, a novel trajectory-centric geospatial MSSL framework that aligns continuous movement patterns with static, location-based observations. TrajGANR learns a continuous neural representation of trajectories at arbitrary points along each path, which enables fine-grained alignment with nearby street-view images, even when they are not co-located with any trajectory waypoints. We leverage this capability to introduce an MSSL objective that jointly aligns three modalities: trajectories, street-view images, and their geographic locations. We evaluate TrajGANR on four urban mobility and road understanding tasks. Across these tasks, TrajGANR consistently outperforms existing geospatial MSSL frameworks and a trajectory-specific foundation model. Ablation studies further demonstrate that our proposed MSSL objective and the multimodal learning framework are the primary drivers of these improvements, highlighting the importance of fine-grained geospatial alignment over coarser aggregation, as well as geospatial multimodal learning. |
| title | TRAJGANR: Trajectory-Centric Urban Multimodal Learning via Geospatially Aligned Neural Representations |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2605.06990 |