Presence-aware multi-target open-vocabulary video segmentation with Sa2VA, SAM 2, CLIP re-identification, and a React/FastAPI research workspace.
-
Updated
Sep 3, 2026 - Python
#
sa2va
Here is 1 public repository matching this topic...
Add this topic to your repo
To associate your repository with the sa2va topic, visit your repo's landing page and select "manage topics."