Code for "Recurrent Filter Learning for Visual Tracking"
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.
data_preprocessing frist commit Feb 7, 2018
rfl_net frist commit Feb 7, 2018
tracking fix demo image reading Apr 11, 2018 small fix Feb 7, 2018 frist commit Feb 7, 2018 frist commit Feb 7, 2018 frist commit Feb 7, 2018

Recurrent Filter Learning for Visual Tracking

This is the implementation of our RFL tracker published in ICCV2017 workshop on VOT. Our code is written in python3(3.5) using Tensorflow(>=1.2) toolbox

For easy comparison, we upload our OTB100 results files to the main directory ./


You use our pretrained model to test our tracker first.

  1. Download the model from the link:
  2. Put the model into directory ./output/models
  3. Run python3 in directory ./tracking


  1. Download the ILSRVC data from the official website and set proper paths for ISLVRC and their tfrecords in
  2. Then run the in ./data_preprocssing directory to convert ILSVRC data to tfrecords.
  3. Run python3 to train the model.

If you find the code is helpful, please cite

    author = {Yang, Tianyu and Chan, Antoni B.},
    booktitle = {ICCV Workshop on VOT},
    title = {Recurrent Filter Learning for Visual Tracking},
    url = {},
    year = {2017}