Awesome
Tracking Persons-of-Interest via Adaptive Discriminative Features (ECCV 2016)
This is the research code for the paper:
Shun Zhang, Yihong Gong, Jia-Bin Huang, Jongwoo Lim, Jinjun Wang, Narendra Ahuja and Ming-Hsuan Yang. "Tracking Persons-of-Interest via Adaptive Discriminative Features", in Proceedings of European Conference on Computer Vision (ECCV), 2016.
We take the T-ara sequence as an example to evaluate our adaptive feature learning approach in this code. Our project website can be found here:
Citation
If you find the code and pre-trained models useful in your research, please consider citing:
@inproceedings{Zhang-ECCV-2016,
author = {Zhang, Shun and Gong, Yihong and Huang, Jia-Bin and Lim, Jongwoo and Wang, Jinjun and Ahuja, Narendra and Yang, Ming-Hsuan},
title = {Tracking Persons-of-Interest via Adaptive Discriminative Features},
booktitle = {European Conference on Computer Vision},
year = {2016},
pages = {415-433}
}
System Requirements
- MATLAB (tested with R2014b on 64-bit Linux)
- Caffe
Installation
-
Download and unzip the project code.
-
Install Caffe. Please follow the Caffe installation instructions to install dependencies and then compile Caffe:
# We call the root directory of the project code `AFL_ROOT`. cd $AFL_ROOT/external/caffe-Triplet-New make all -j8 make pycaffe make matcaffe
-
Download the T-ara images and extract all images into
AFL/data/Tara
. -
Download the AlexNet model:
cd $AFL_ROOT/external/caffe-Triplet-New scripts/download_model_binary.py models/bvlc_reference_caffenet
-
Download the VGG-Face Model and put it in
$AFL_ROOT/external/caffe-Triplet-New/models/VGG
. Download the pre-trained face model and put it in$AFL_ROOT/external/caffe-Triplet-New/models/pretrained_web_face
.
Usage
Directly run the script run_Tara_example.sh
.
Or run the following commands step by step:
-
Mine constraints:
cd $AFL_ROOT # Start MATLAB matlab >> genTracklet('Tara')
-
Learn adaptive discriminative features:
cd $AFL_ROOT sh shell_scripts/Tara/adapt_Triplet.sh
-
Extract features:
sh shell_scripts/Tara/extract_All_Feas.sh
-
Perform hierarchical agglomerative clustering algorithm (you can get Fig. 6(a) in our supplementary materials):
matlab >> clustering_tracklets('Tara')
-
Perform a simple multi-face tracking:
matlab >> facetracking('Tara')