Argoverse 1 Motion Forecasting

Argoverse 1 Motion Forecasting is a dataset that allows us to train a model on a vast collection of 323, 557 scenarios of 5 seconds each. Each scenario is a 2D bird-eye-view of the scene, tracking the sampled object at 10Hz.

Data and Resources

Cite this as

Adrien Lafage, Mathieu Barbier, Gianni Franchi, David Filliat (2024). Dataset: Argoverse 1 Motion Forecasting. https://doi.org/10.57702/l1rj5q21

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Author Adrien Lafage
More Authors
Mathieu Barbier
Gianni Franchi
David Filliat
Homepage https://arxiv.org/abs/2106.09441