Need help with CFWCR?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

129 Stars 62 Forks MIT License 14 Commits 8 Opened issues


5th visual object tracking(VOT) tracker CFWCR

Services available


Need anything else?

Contributors list

# 503,259
2 commits

Correlation Filters with Weighted Convolution Responses(ICCV2017W)

By Zhiqun He, Yingruo Fan, Junfei Zhuang, Yuan Dong, Hongliang Bai



We derive a continuous convolution operator based tracker which fully exploits the discriminative power in the CNN feature representations. In our work, we normalize each individual feature extracted from different layers of the deep pretrained CNN first, and after that, the weighted convolution responses from each feature block are summed to produce the final confidence score. By this weighted sum operation, the empirical evaluations demonstrate clear improvements by our proposed tracker based on the Efficient Convolu- tion Operators Tracker (ECO).


1、Download the CFWCR code and the pretrained models

git clone
cd ./feature_extraction/networks
mv  imagenet-vgg-m-2048.mat imagenet-vgg-m-2048-cut.mat

2、Downloading MatConvNet and compile it

cd ./external_libs
git clone

More install details

3、Install all the dependencies

Fill the cuda(>=7.5) path in the install.m first.

run install.m

4*、Setting export CUDACACHEMAXSIZE=8000000000" in the ./~bash_profile so that gpuDevice(1) will take fewer time.


1、 run demo_CFWCR.m()


2、[VOT Intergration] ./vot2017_trax

Citing DCFNet

If you find CFWCR useful in your research, please consider citing:

    Author = {hiqun He, Yingruo Fan, Junfei Zhuang, Yuan Dong, Hongliang Bai},
    Title = {Correlation Filters with Weighted Convolution Responses},
    Journal = {IEEE International Conference on Computer Vision},
    Year = {2017}

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.