Wangbiao2/R1-Track

R1-Track: Direct Application of MLLMs to Visual Object Tracking via Reinforcement Learning.

35
/ 100
Emerging

This tool helps you automatically track a specific object across a video, even if it moves, changes size, or is temporarily obscured. You provide the initial location of the target in the first frame, either by drawing a box around it or describing it with text. The system then outputs the exact coordinates of that object in every subsequent frame. It's ideal for anyone who needs to monitor individual subjects in visual recordings, like in security analysis or sports tracking.

No commits in the last 6 months.

Use this if you need to continuously follow a single object throughout a video sequence and automatically get its precise location in each frame.

Not ideal if you need to track multiple objects simultaneously or detect new objects appearing in the video.

video-surveillance motion-tracking object-localization visual-analytics sports-analysis
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

66

Forks

5

Language

Python

License

MIT

Last pushed

May 14, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Wangbiao2/R1-Track"

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