UVOSAM: A Mask-free Paradigm for Unsupervised Video Object Segmentation via Segment Anything Model

Unsupervised video object segmentation has made significant progress in recent years, but the manual annotation of video mask datasets is expensive and limits the diversity of available datasets.

Data and Resources

Cite this as

Zhenghao Zhang, Zhichao Wei, Shengfan Zhang, Zuozhuo Dai, Siyu Zhu (2024). Dataset: UVOSAM: A Mask-free Paradigm for Unsupervised Video Object Segmentation via Segment Anything Model. https://doi.org/10.57702/rohks306

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2305.12659
Author Zhenghao Zhang
More Authors
Zhichao Wei
Shengfan Zhang
Zuozhuo Dai
Siyu Zhu
Homepage https://arxiv.org/abs/2304.02643