You're currently viewing an old version of this dataset. To see the current version, click here.

YouTube-VIS

Video instance segmentation task requires classifying, segmenting instances in each frame, and tracking the same instance across frames.

Data and Resources

Cite this as

Sudhir Yarram, Jialian Wu, Pan Ji, Yi Xu, Junsong Yuan (2024). Dataset: YouTube-VIS. https://doi.org/10.57702/jwryzg46

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2203.16966
Author Sudhir Yarram
More Authors
Jialian Wu
Pan Ji
Yi Xu
Junsong Yuan
Homepage https://github.com/skrya/DefVIS