MCG-NJU/MeMOTR

[ICCV 2023] MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking

46
/ 100
Emerging

This project helps computer vision practitioners accurately track multiple moving objects over long periods in video footage. You provide video data, and the system identifies individual objects and assigns them persistent IDs, even if they disappear and reappear. This is designed for researchers or engineers working on video analysis tasks.

218 stars.

Use this if you need to reliably track many objects in complex, dynamic video scenes like dance performances, sports, or crowded street views, where objects might be temporarily obscured.

Not ideal if you are looking for a simple, off-the-shelf application for basic object detection or short-term tracking without complex re-identification needs.

multi-object-tracking video-analytics computer-vision activity-analysis surveillance
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

218

Forks

20

Language

Python

License

MIT

Last pushed

Oct 15, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/MCG-NJU/MeMOTR"

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