TrajGANR: Trajectory-Centric Urban Multimodal Learning via Geospatially Aligned Neural Representations
cs.CV, cs.LG
Submitted: 2026-05-07
Updated: 2026-09-27
License: http://creativecommons.org/licenses/by/4.0/
The gist: Many urban prediction tasks depend not only on the static attributes of a location, such as the visual appearance of its built environment, but also on its dynamic function: how people navigate and
Terminology
Abstract
Many urban prediction tasks depend not only on the static attributes of a location, such as the visual appearance of its built environment, but also on its dynamic function: how people navigate and use it over time. Predicting congestion, travel demand, or road safety risks, for instance, requires mobility information that imagery and geographic coordinates alone cannot provide. Trajectories carry this signal, yet current trajectory representations are difficult to align with static geospatial observations: sparse, irregular GPS samples rarely coincide with street-view image coordinates, and existing encoders produce either a single embedding per trajectory or road segment, or embeddings only at the observed GPS samples. We introduce TrajGANR, a trajectory-centric multimodal self-supervised learning framework that represents each trajectory as a continuous, path-conditioned neural field. Reconstructed from the observed GPS samples, this representation can be queried at arbitrary coordinates (including the off-path locations where street-view images were captured), yielding localized mobility embeddings that align with street-view image and location representations at the same coordinate. Across four fine-grained road-level tasks in San Francisco and Porto, TrajGANR consistently outperforms recent geospatial and trajectory foundation models, with ablations attributing the gains to both the mobility signal and the fine granularity at which it is aligned. TrajGANR's location encoder further generalizes beyond the road network to areas where neither street-view imagery nor trajectories are available.
Sources
- GeoLink: Empowering Remote Sensing Foundation Model with OpenStreetMap Data
- AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Time2Vec: Learning a Vector Representation of Time
- From Lagging to Leading: Validating Hard Braking Events as High-Density Indicators of Segment Crash Risk
- GAIR: Location-Aware Self-Supervised Contrastive Pre-Training with Geo-Aligned Implicit Representations
- Representation Learning with Contrastive Predictive Coding
- Prithvi WxC: Foundation Model for Weather and Climate
- Mobility-Embedded POIs: Learning What A Place Is and How It Is Used from Human Movement
- Deep Learning for Classification Tasks on Geospatial Vector Polygons
- DOFA-CLIP: Multimodal Vision-Language Foundation Models for Earth Observation
- A Trajectory K-Anonymity Model Based on Point Density and Partition
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models