Densely Annotated Video Segmentation (DAVIS)

The Davis dataset contains fifty high-resolution videos with pixel-accurate ground truth.

Data and Resources

Cite this as

F Perazzi, J Pont-Tuset, B McWilliams, L Van Gool, M Gross, A Sorkine-Hornung (2024). Dataset: Densely Annotated Video Segmentation (DAVIS). https://doi.org/10.57702/7pcubam7

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.1606.00487
Author F Perazzi
More Authors
J Pont-Tuset
B McWilliams
L Van Gool
M Gross
A Sorkine-Hornung
Homepage https://www.isb.inrialpes.fr/cvlab/davis/