FlowRVS
FlowRVS is a referring video object segmentation method that learns a text-conditioned continuous flow to deform a video’s spatiotemporal representation into the target object mask.
- Type
- Multimodal
- Weights
- Open
- Likes
- 1
- License
- mit
Model hub
xmz111/FlowRVS
- Repo
- xmz111/FlowRVS
- Access
- Public
Papers
1
More from xmz111
2