Representing Spatial Trajectories as DistributionsDownload PDF

Published: 31 Oct 2022, Last Modified: 17 Sept 2023NeurIPS 2022 AcceptReaders: Everyone
Keywords: representation learning, human pose, video
TL;DR: We present a representation learning framework for trajectories that models segments of trajectories as distributions in a learned latent space.
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 superiority over baselines in prediction tasks.
Supplementary Material: zip
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](
12 Replies