LVOS

LVOS is a long-term video object segmentation benchmark dataset, consisting of 220 videos with a total duration of 421 minutes.

Data and Resources

Cite this as

Lingyi Hong, Wenchao Chen, Zhongying Liu, Wei Zhang, Pinxue Guo, Zhaoyu Chen, Wenqiang Zhang (2024). Dataset: LVOS. https://doi.org/10.57702/8vd5fqsg

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Author Lingyi Hong
More Authors
Wenchao Chen
Zhongying Liu
Wei Zhang
Pinxue Guo
Zhaoyu Chen
Wenqiang Zhang
Homepage https://lingyihongfd.github.io/lvos.github.io/