Skip to yearly menu bar Skip to main content


Representing Spatial Trajectories as Distributions

Didac Suris Coll-Vinent · Carl Vondrick

Hall J (level 1) #514

Keywords: [ human pose ] [ Video ] [ Representation Learning ]


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 superiority over baselines in prediction tasks.

Chat is not available.