DoctorKey 的博客

SAIL-VOS

SAIL-VOS (Semantic Amodal Instance Level Video Object Segmentation)是一个非模态物体分割的数据集。

• 主页
• 下载页面
• 论文

@inproceedings{HuCVPR2019,
  author = {Y.-T. Hu and H.-S. Chen and K. Hui and J.-B. Huang and A.~G. Schwing},
  title = { {SAIL-VOS: Semantic Amodal Instance Level Video Object Segmentation -- A Synthetic Dataset and Baselines} },
  booktitle = {Proc. CVPR},
  year = {2019},
}

数据集统计

• 共包含201视频序列，即111654帧
• The training set contains 160 video sequences (84,781 images, 1,388,389 objects)
• the validation set contains 41 video sequences (26,873 images, 507,906 objects)
• 类别：162