jcdidi / cf2

Hierarchical Convolutional Features for Visual Tracking (ICCV 2015)

Hierarchical Convolutional Features for Visual Tracking (ICCV 2015)

Introduction

This is the research code for the paper:

Chao Ma, Jia-Bin Huang, Xiaokang Yang and Ming-Hsuan Yang, "Hierarchical Convolutional Features for Visual Tracking", ICCV 2015

• PDF
• Supplementary material
• Project page
• Result visualization

The correlation filters with convolutional features (CF2) is a state-of-the-art tracker that exploits rich feature hierarchy from deep convolutional neural networks for visual tracking. For more details, please visit our Project page.

Citation

If you find the code and dataset useful in your research, please consider citing:

@inproceedings{Ma-ICCV-2015,
    title={Hierarchical Convolutional Features for Visual Tracking},
    Author = {Ma, Chao and Huang, Jia-Bin and Yang, Xiaokang and Yang, Ming-Hsuan},
    booktitle = {Proceedings of the IEEE International Conference on Computer Vision},
    pages={},
    Year = {2015}
}

Contents

Folder	description

Feedbacks and comments are welcome! Feel free to contact us via [email protected] or [email protected].

Enjoy!

Results on visual tracking benchmark

One-pass evaluation (OPE) on the 50 tracking sequences in Wu et al. CVPR 2013

Spatial robustness evaluation (SRE) on the 50 tracking sequences in Wu et al. CVPR 2013

Temporal robustness evaluation (TRE) on the 50 tracking sequences in Wu et al. CVPR 2013

One-pass evaluation (OPE) on the 100 tracking sequences in Wu et al. PAMI 2015

Spatial robustness evaluation (SRE) on the 100 tracking sequences in Wu et al. PAMI 2015

Temporal robustness evaluation (TRE) on the 100 tracking sequences in Wu et al. PAMI 2015