CACFNet

Introduction

This project is a pytorch implementation of CACF, aimed to make the CACF filter as a differentiable layer to learn the convolutional features and perform the correlation tracking process simultaneously.

I referred the implmentations, DCFNet by Qiang Wang and the sorce code from the CACF.

What we are doing and going to do

• [X] track with got10k toolkit.
• [X] train from scratch.
• [ ] the result of the CACFNet on the benchmark.

Paper

1 DCFNet: Qiang Wang, Jin Gao, Junliang Xing, Mengdan Zhang, Weiming Hu. "DCFNet: Discriminant Correlation Filters Network for Visual Tracking." arXiv (2017). [paper] [code].

2 CACF: Matthias Mueller, Neil Smith, Bernard Ghanem. "Context-Aware Correlation Filter Tracking." CVPR (2017 oral).[paper] [supp] [projectcode].