News
- “The 3rd Large-scale Video Object Segmentation Challenge” has started on Feb. 16, 2021. Call for participants!
- We will hold “The 3rd Large-scale Video Object Segmentation Challenge” in conjunction with CVPR 2021 virtually. Stay tuned!
What is YouTube-VOS
YouTube-VOS is the first large-scale benchmark that supports multiple video object segmentation tasks.
- Semi-supervised Video Object Segmentation
- Video Instance Segmentation
It also has the following features.
- 4000+ high-resolution YouTube videos
- 90+ semantic categories
- 7800+ unique objects
- 190k+ high-quality manual annotations
- 340+ minutes duration
Research paper
Please cite the following papers if you find our dataset is useful.
Semi-supervised video object segmentation
- Download the paper that describes the initial YouTube-VOS dataset.
- Download the paper that describes a RNN method trained on YouTube-VOS.
Video instance segmentation
Dataset examples
 |
 |
 |
 |
 |
 |
 |
 |