VTAAN

by Xiaoping Wang.

Introduction

This implementation is based on my another repository called py-Vital, that is posted on the project home by the authors of VITAL tracker.

If you want this code for personal use, please cite:

@InProceedings{nam2016mdnet,
author = {Nam, Hyeonseob and Han, Bohyung},
title = {Learning Multi-Domain Convolutional Neural Networks for Visual Tracking},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2016}
}  
  
@inproceedings{shi-nips18-DAT,
author = {Pu, Shi and Song, Yibing and Ma, Chao and Zhang, Honggang and Yang, Ming-Hsuan},
title = {Deep Attentive Tracking via Reciprocative Learning},
booktitle = {Neural Information Processing Systems},
year = {2018},
}   
 
@inproceedings{xiaopingwang-VTAAN,
author = {Xiaoping Wang}, 
title = {VTAAN: Visual Tracking with Attentive Adversarial Network}, 
booktitle = {VTAAN tracker implemented by PyTorch}, 
month = {August},
year = {2019},
}  

Prerequisites

• python 3.6+
• opencv 3.0+
• PyTorch 1.0+ and its dependencies

Usage

Tracking

 python tracking/run_tracker.py -s DragonBaby [-d (display fig)] [-f (save fig)]

• You can provide a sequence configuration in two ways (see tracking/gen_config.py):
  • python tracking/run_tracker.py -s [seq name]
  • python tracking/run_tracker.py -j [json path]

Pretraining

• Download VGG-M (matconvnet model) and save as "models/imagenet-vgg-m.mat"
• Pretraining on VOT-OTB
  • Download VOT datasets into "datasets/VOT/vot201x"

   python pretrain/prepro_vot.py
   python pretrain/train_mdnet.py