Representing Spatial Trajectories as Distributions

2022/10/04 by Dídac Surís, Surís, Dídac, Carl Vondrick +1
Computer Science · Social Sciences · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Data Management and Algorithms #FOS: Computer and information sciences #Geographic Information Systems Studies #Machine Learning (cs.LG) #Time Series Analysis and Forecasting

paper · pdf · doi:10.48550/arxiv.2210.01322

openalex publication_date 2022/10/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We introduce a representation learning framework for spatial trajectories. We represent partial observations of trajectories as probability distributions in a learned latent space, which characterize the uncertainty about unobserved parts of the trajectory. Our framework allows us to obtain samples from a trajectory for any continuous point in time, both interpolating and extrapolating. Our flexible approach supports directly modifying specific attributes of a trajectory, such as its pace, as well as combining different partial observations into single representations. Experiments show our method's advantage over baselines in prediction tasks.

Related

• RED: Effective Trajectory Representation Learning with Comprehensive Information
• Towards Robust Trajectory Representations: Isolating Environmental Confounders with Causal Learning
• Schrödinger's Cat: Probabilistic Representation and Prediction of Potential Scene Kinematics
• Representation Learning of Pedestrian Trajectories Using Actor-Critic Sequence-to-Sequence Autoencoder
• The Traveling Observer Model: Multi-task Learning Through Spatial Variable Embeddings