English

Back to square one: probabilistic trajectory forecasting without bells and whistles

Machine Learning 2018-12-10 v1 Computer Vision and Pattern Recognition Machine Learning

Abstract

We introduce a spatio-temporal convolutional neural network model for trajectory forecasting from visual sources. Applied in an auto-regressive way it provides an explicit probability distribution over continuations of a given initial trajectory segment. We discuss it in relation to (more complicated) existing work and report on experiments on two standard datasets for trajectory forecasting: MNISTseq and Stanford Drones, achieving results on-par with or better than previous methods.

Keywords

Cite

@article{arxiv.1812.02984,
  title  = {Back to square one: probabilistic trajectory forecasting without bells and whistles},
  author = {Ehsan Pajouheshgar and Christoph H. Lampert},
  journal= {arXiv preprint arXiv:1812.02984},
  year   = {2018}
}

Comments

4 pages, 3 figures, Workshop on Modeling and Decision-Making in the Spatiotemporal Domain, 32nd Conference on Neural Information Processing Systems (NIPS 2018), Montreal, Canada

R2 v1 2026-06-23T06:35:15.613Z