As a continuous effort to push forward the research on video object segmentation tasks, we plan to host a second workshop with a challenge based on the YouTube-VOS dataset, targeting at more diversified problem settings, i.e., we plan to provide two challenge tracks in this workshop. The first track targets at semi-supervised video object segmentation, which is the same setting as in the first workshop. The second track will be a new task named video instance segmentation, which targets at automatically segmenting all object instances of pre-defined object categories from videos. For example, the video instance segmentation algorithm is required to segment both the person and the skateboard in the figure below, and it is required to give predictions of object categories. Video instance segmentation is a natural extension of image instance segmentation, which not only requires a per-image instance segmentation, and also the correspondence of object instances across the whole video. The new task is described in detail in our tech report.


  • The 2nd Large-scale Video Object Segmentation Challenge has finished. Congrats Zhishan Zhou’s team for winning the VOS track and Jonathon Luiten’s team for winning the VIS track! Leaderboard has been updated. Technical reports of all the teams will be uploaded soon. Thanks all for your participation!
  • Due to recent CodaLab’s malfunction, we lost all the history. Please register and submit on the new servers (Track1, Track2).
  • Codalab server is online now!
  • Codalab server will be ready soon. Stay tuned!


  • Sep 5th: The final competition results will be announced and high-performance teams will be invited to give oral/poster presentations at our ICCV 2019 workshop.
  • Aug 15th - 30th: Release test data and open the submission of the test results.
  • May 20th: Codalab websites open for registration. Training and validation data released.




Ning Xu Linjie Yang Yuchen Fan Thomas S. Huang Jianchao Yang Honghui Shi
Ning Xu
Adobe Research
Linjie Yang
ByteDance AI Lab
Yuchen Fan
Thomas S. Huang
Jianchao Yang
ByteDance AI Lab
Honghui Shi


For dataset related questions, please feel free to contact For challenge related questions, you can also use codalab forums.


ByteDance Adobe UIUC Snap
ByteDance Adobe UIUC Snap