uncbiag/LiVOS

LiVOS: Light Video Object Segmentation with Gated Linear Matching (CVPR 2025)

33
/ 100
Emerging

This tool helps researchers and computer vision engineers accurately identify and track specific objects across a series of video frames. You input a video and an initial mask or annotation for an object, and it outputs a sequence of frames with the object precisely outlined. It is ideal for those working on tasks requiring detailed object tracking in video content.

No commits in the last 6 months.

Use this if you need to precisely segment and track a specific object through an entire video sequence, especially in research or advanced computer vision applications.

Not ideal if you need a user-friendly interface for general video editing or if you only need coarse object detection rather than pixel-level segmentation.

video-analysis computer-vision object-tracking image-segmentation AI-research
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

45

Forks

3

Language

Python

License

MIT

Last pushed

Sep 01, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/uncbiag/LiVOS"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.