Tensorflow Implementation of 'Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning(CVPR 2017)'
| GIF | Description |
|---|---|
 |
tracking |
- Green : Ground Truth, Blue : ADNet-Fast Tracking Result
-
Network Architecture
-
Training Code
- Reproduce Paper Result
-
Inference Code
-
Converting Original Weights to Tensorflow
-
Online Learning(finetuning)
-
$ python experiment.py
- Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning (CVPR201) : http://openaccess.thecvf.com/content_cvpr_2017/papers/Yun_Action-Decision_Networks_for_CVPR_2017_paper.pdf
- ADNet Implmentation in Matlab : https://github.com/hellbell/ADNet/