bertinetto/cfnet
[CVPR'17] Training a Correlation Filter end-to-end allows lightweight networks of 2 layers (600 kB) to high performance at fast speed..
This project helps computer vision researchers or engineers track specific objects across video sequences. You provide a video and a trained model, and it outputs the precise location of the target object in each frame. It's designed for practitioners working with video analysis who need high performance.
524 stars. No commits in the last 6 months.
Use this if you need to accurately and quickly track objects in video using compact, efficient deep learning models.
Not ideal if you prefer to work outside of a Matlab environment or do not have access to a GPU.
Stars
524
Forks
151
Language
Matlab
License
MIT
Category
Last pushed
May 31, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/bertinetto/cfnet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
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)