The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction release_fjme6zvjivg43enezdb3qa2i4a

by Junwei Liang, Lu Jiang, Kevin Murphy, Ting Yu, Alexander Hauptmann

Released as a article .

2019  

Abstract

This paper studies the problem of predicting the distribution over multiple possible future paths of people as they move through various visual scenes. We make two main contributions. The first contribution is a new dataset, created in a realistic 3D simulator, which is based on real world trajectory data, and then extrapolated by human annotators to achieve different latent goals. This provides the first benchmark for quantitative evaluation of the models to predict multi-future trajectories. The second contribution is a new model to generate multiple plausible future trajectories, which contains novel designs of using multi-scale location encodings and convolutional RNNs over graphs. We refer to our model as Multiverse. We show that our model achieves the best results on our dataset, as well as on the real-world VIRAT/ActEV dataset (which just contains one possible future). We will release our data, models and code.
In text/plain format

Archived Files and Locations

application/pdf  8.0 MB
file_slxopbkx7jesjfdtips33zi76u
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2019-12-17
Version   v2
Language   en ?
arXiv  1912.06445v2
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 17b35552-e60f-4205-9fcd-5ba90b8d0005
API URL: JSON