YouTube-VIS Dataset

The YouTube-VIS dataset is a large-scale dataset for instance segmentation, containing 2,883 videos and 131K instance masks.

Data and Resources

Cite this as

Linjie Yang, Yuchen Fan, Ning Xu (2024). Dataset: YouTube-VIS Dataset. https://doi.org/10.57702/vbjchu0m

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.2103.08808
Author Linjie Yang
More Authors
Yuchen Fan
Ning Xu
Homepage https://arxiv.org/abs/1904.07850