MCG-NJU/MeMOTR
[ICCV 2023] MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking
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.
Stars
218
Forks
20
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
roboflow/rf-detr
[ICLR 2026] RF-DETR is a real-time object detection and segmentation model architecture...
stereolabs/zed-sdk
⚡️The spatial perception framework for rapidly building smart robots and spaces
mikel-brostrom/boxmot
BoxMOT: Pluggable SOTA multi-object tracking modules with support for axis-aligned and oriented...
RizwanMunawar/yolov7-object-tracking
YOLOv7 Object Tracking Using PyTorch, OpenCV and Sort Tracking
google-deepmind/tapnet
Tracking Any Point (TAP)