---
title: cv_mivos-stcn_video-object-segmentation
canonical_url: "https://www.modelscope.cn/models/damo/cv_mivos-stcn_video-object-segmentation"
md_url: "https://www.modelscope.cn/models/damo/cv_mivos-stcn_video-object-segmentation.md"
repository: damo/cv_mivos-stcn_video-object-segmentation
chinese_name: "MiVOS-STCN视频目标分割"
last_updated: 2023-03-08
license: "Apache License 2.0"
pipeline_tag: video-object-segmentation
tasks:
  - video-object-segmentation
library_name:
  - pytorch
frameworks:
  - pytorch
domain:
  - cv
downloads: 141
stars: 2
tags:
  - "Video Object Segmentation"
  - VOS
  - MiVOS
  - STCN
  - Tracking
  - "视频目标分割"
  - "视频目标跟踪"
---

# cv_mivos-stcn_video-object-segmentation

> cv_mivos-stcn_video-object-segmentation - damo 在 ModelScope 开源的模型。MiVOS-STCN 视频目标分割 该模型为视频目标分割模型，输入一个视频和首帧mask，返回视频后续帧中对应的mask。 将backbone替换为STCN，更快更好

damo/cv_mivos-stcn_video-object-segmentation 是 ModelScope 魔搭社区上的video-object-segmentation模型，采用 Apache License 2.0 许可。

- **Repository**: damo/cv_mivos-stcn_video-object-segmentation
- **License**: Apache License 2.0
- **Tasks**: video-object-segmentation
- **Tags**: Video Object Segmentation, VOS, MiVOS, STCN, Tracking, 视频目标分割, 视频目标跟踪
- **Downloads**: 141
- **Stars**: 2
- **Last updated**: 2023-03-08

Source: https://www.modelscope.cn/models/damo/cv_mivos-stcn_video-object-segmentation

---

# MiVOS-STCN 视频目标分割
该模型为视频目标分割模型，输入一个视频和首帧mask，返回视频后续帧中对应的mask。
将backbone替换为STCN，更快更好

```
@inproceedings{cheng2021stcn,
  title={Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation},
  author={Cheng, Ho Kei and Tai, Yu-Wing and Tang, Chi-Keung},
  booktitle={NeurIPS},
  year={2021}
}

@inproceedings{cheng2021mivos,
  title={Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion},
  author={Cheng, Ho Kei and Tai, Yu-Wing and Tang, Chi-Keung},
  booktitle={CVPR},
  year={2021}
}
```