FoundationVision/GLEE
A foundation model for unified object detection, segmentation, and tracking across images and videos.
Not currently ranked — collecting fresh signals.
star history
GLEE is a general object foundation model designed to handle multiple computer vision tasks at scale including object detection, segmentation, referring expression comprehension, multi-object tracking, and video instance segmentation. It supports open-vocabulary capabilities for zero-shot detection and segmentation, enabling generalization to unseen object categories without additional training.
Frequently asked
- What is FoundationVision/GLEE?
- A foundation model for unified object detection, segmentation, and tracking across images and videos.
- Is GLEE open source?
- Yes — FoundationVision/GLEE is open source, released under the MIT license.
- What language is GLEE written in?
- FoundationVision/GLEE is primarily written in Python.
- How popular is GLEE?
- FoundationVision/GLEE has 1.2k stars on GitHub.
- Where can I find GLEE?
- FoundationVision/GLEE is on GitHub at https://github.com/FoundationVision/GLEE.