News
- We have a joint challenge track with Multiple Object Tracking and Segmentation in Complex Environments Workshop in ECCV 2022 on long video VIS. Call for participation!
- Due to maintainance issues of the old Codalab website, we have migrated the VOS and VIS evaluation servers of the 2019 challenge to the new codalab site. Details
- The video recording of our workshop in conjunction with CVPR 2022 will be released 3 months after the conference. All tech reports have been updated.
- “The 4th Large-scale Video Object Segmentation Challenge” has finished. Congrats to all top teams! Leaderboard
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
- Referring Video Object Segmentation
It also has the following features.
- 5000+ 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
- YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark. arXiv 2018
- YouTube-VOS: Sequence-to-Sequence Video Object Segmentation. ECCV 2018
Video instance segmentation
Referring Video Object Segmentation
Dataset examples
 |
 |
 |
 |
 |
 |
 |
 |