first commit

.gitignore

@@ -0,0 +1,12 @@
+*~
+dataset_link
+dataset/download_datasets.m
+dataset/OTB/seq_list.txt
+
+models/data_vot-otb/*
+models/data_otb-vot14/*
+models/data_otb-vot15/*
+models/mdnet_init.mat
+models/mdnet_vot-otb_new.mat
+models/mdnet_otb-vot14_new.mat
+models/mdnet_otb-vot15_new.mat

LICENSE

@@ -0,0 +1,57 @@
+Copyright Pohang University of Science and Technology. All rights reserved.
+
+Contact person:
+Hyeonseob Nam (namhs09 <at> postech.ac.kr)
+
+This software is being made available for individual research use only.
+Any commercial use or redistribution of this software requires a license from
+the Pohang University of Science and Technology.
+
+You may use this work subject to the following conditions:
+
+1. This work is provided "as is" by the copyright holder, with
+absolutely no warranties of correctness, fitness, intellectual property
+ownership, or anything else whatsoever.  You use the work
+entirely at your own risk.  The copyright holder will not be liable for
+any legal damages whatsoever connected with the use of this work.
+
+2. The copyright holder retain all copyright to the work. All copies of
+the work and all works derived from it must contain (1) this copyright
+notice, and (2) additional notices describing the content, dates and
+copyright holder of modifications or additions made to the work, if
+any, including distribution and use conditions and intellectual property
+claims.  Derived works must be clearly distinguished from the original
+work, both by name and by the prominent inclusion of explicit
+descriptions of overlaps and differences.
+
+3. The names and trademarks of the copyright holder may not be used in
+advertising or publicity related to this work without specific prior
+written permission. 
+
+4. In return for the free use of this work, you are requested, but not
+legally required, to do the following:
+
+* If you become aware of factors that may significantly affect other
+  users of the work, for example major bugs or
+  deficiencies or possible intellectual property issues, you are
+  requested to report them to the copyright holder, if possible
+  including redistributable fixes or workarounds.
+
+* If you use the work in scientific research or as part of a larger
+  software system, you are requested to cite the use in any related
+  publications or technical documentation. The work is based upon:
+
+    Hyeonseob Nam, Bohyung Han.
+    Learning Multi-Domain Convolutional Neural Networks for Visual Tracking
+    arXiv:1510.07945, 2015.
+
+    @article{nam2015mdnet,
+    title={Learning Multi-Domain Convolutional Neural Networks for Visual Tracking},
+    author={Hyeonseob Nam and Bohyung Han},
+    journal={CoRR},
+    volume={abs/1510.07945},
+    year={2015},
+    }
+
+This copyright notice must be retained with all copies of the software,
+including any modified or derived versions.

README.md

@@ -0,0 +1,80 @@
+## MDNet: Multi-Domain Convolutional Neural Network Tracker
+
+Created by [Hyeonseob Nam](http://cvlab.postech.ac.kr/~hyeonseob/) and [Bohyung Han](http://cvlab.postech.ac.kr/~bhhan/) at POSTECH
+
+Acknowledgements: This software is implemented using [MatConvNet](http://www.vlfeat.org/matconvnet/) and part of [R-CNN](https://github.com/rbgirshick/rcnn).
+
+
+### Introduction
+
+MDNet is the state-of-the-art visual tracker based on a CNN trained on a large set of tracking sequences,
+and the winner tracker of [The VOT2015 Challenge](http://www.votchallenge.net/vot2015/).
+
+Detailed description of the system is provided by our [arXiv technical report](http://arxiv.org/abs/1510.07945).
+
+
+### Citation
+
+If you're using this code in a publication, please cite our paper.
+
+	@article{nam2015mdnet,
+      title={Learning Multi-Domain Convolutional Neural Networks for Visual Tracking},
+      author={Hyeonseob Nam and Bohyung Han},
+      journal={CoRR},
+      volume={abs/1510.07945},
+      year={2015},
+    }
+
+
+### License
+
+This software is being made available for research purpose only.
+Check LICENSE file for details.
+
+
+### System Requirements
+
+This code is tested on 64 bit Linux (Ubuntu 14.04 LTS).
+
+**Prerequisites** 
+  0. MATLAB (tested with R2014a)
+  0. MatConvNet (tested with version 1.0-beta10, included in this repository)
+  0. For GPU support, a GPU (~2GB memory) and CUDA toolkit according to the [MatConvNet installation guideline](http://www.vlfeat.org/matconvnet/install/) will be needed.
+
+
+### Installation
+
+  0. Compile MatConvNet according to the [installation guideline](http://www.vlfeat.org/matconvnet/install/). An example script is provided in 'compile_matconvnet.m'.
+  0. Run 'setup_mdnet.m' to set the environment for running MDNet.
+
+
+### Online Tracking using MDNet
+
+**Pretrained Models**
+
+If you only need to run the tracker, you can use the pretrained MDNet models:
+  0. models/mdnet_vot-otb.mat (trained on VOT13,14,15 excluding OTB)
+  0. models/mdnet_otb-vot14.mat (trained on OTB excluding VOT14)
+  0. models/mdnet_otb-vot15.mat (trained on OTB excluding VOT15)
+
+**Demo**
+  0. Run 'tracking/demo_tracking.m'.
+
+The demo performs online tracking on *'Diving'* sequence using a pretrained model 'models/mdnet_vot-otb.mat'.
+
+In case of out of GPU memory, decrease *opts.batchSize_test* in 'tracking/mdnet_init.m'.
+You can also disable the GPU support by setting *opts.useGpu* in 'tracking/mdnet_init.m' to false (not recommended).
+
+
+### Learning MDNet
+
+**Preparing Datasets**
+
+You may need OTB and VOT datasets for learning MDNet models. You can also use other datasets by configuring 'utils/genConfig.m'.
+  0. Download [OTB](http://cvlab.hanyang.ac.kr/tracker_benchmark/datasets.html) and [VOT](http://www.votchallenge.net/) datasets.
+  0. Locate the OTB sequences in 'dataset/OTB' and VOT201x sequences in 'dataset/VOT/201x', or modify the variables *benchmarkSeqHome* in 'utils/genConfig.m' properly.
+
+**Demo**
+  0. Run 'pretraining/demo_pretraining.m'.
+
+The demo trains new MDNet models using OTB or VOT sequences. You will need ~2GB GPU memory for training.

compile_matconvnet.m

@@ -0,0 +1,13 @@
+%% COMPILE_MATCONVNET
+%
+% Compile MatConvNet
+%
+% Hyeonseob Nam, 2015 
+%
+
+run matconvnet/matlab/vl_setupnn ;
+cd matconvnet;
+vl_compilenn('enableGpu', true, ...
+               'cudaRoot', '/usr/local/cuda-6.5', ...
+               'cudaMethod', 'nvcc');
+cd ..;

dataset/OTB/Diving/groundtruth_rect.txt

@@ -0,0 +1,215 @@
+177,51,21,129
+178,51,21,129
+180,52,19,129
+179,52,20,130
+177,52,22,129
+176,53,23,127
+177,52,23,132
+176,52,24,128
+177,52,22,130
+178,53,21,130
+178,53,21,129
+176,53,24,130
+177,54,21,125
+176,53,23,129
+177,54,21,129
+176,55,20,127
+174,55,24,128
+175,55,23,129
+176,56,20,129
+174,56,22,128
+174,57,23,127
+174,58,22,126
+174,57,21,127
+174,57,23,128
+173,58,24,127
+174,58,21,127
+174,59,19,126
+172,60,20,125
+172,64,19,120
+170,67,22,121
+167,69,25,119
+169,70,23,118
+170,72,23,116
+168,72,23,116
+165,76,26,114
+165,71,31,119
+166,74,26,113
+165,70,28,118
+164,75,27,109
+161,73,37,111
+160,70,45,116
+159,72,46,112
+159,74,48,112
+159,74,48,110
+158,77,46,106
+158,78,46,105
+157,80,47,102
+157,82,47,101
+156,83,47,100
+157,85,46,100
+157,84,46,103
+157,87,45,102
+157,88,44,104
+157,90,45,106
+157,92,44,105
+158,92,43,110
+157,92,44,111
+159,92,43,115
+156,93,50,115
+158,96,47,113
+161,95,42,115
+161,95,42,115
+160,95,44,117
+159,94,45,115
+157,92,43,120
+157,92,45,122
+159,91,46,122
+159,89,45,122
+160,87,46,123
+160,86,46,123
+159,84,50,122
+163,83,44,121
+162,81,47,122
+162,78,49,120
+162,77,51,120
+163,75,54,118
+165,74,52,115
+166,74,56,112
+167,72,57,110
+165,73,61,106
+165,72,63,101
+165,74,67,95
+164,76,69,89
+164,79,72,85
+164,78,73,81
+164,73,73,85
+162,70,75,82
+162,70,71,80
+160,66,71,79
+157,65,68,78
+154,66,64,67
+150,64,62,66
+152,63,57,68
+149,64,64,68
+146,65,67,65
+147,67,67,62
+142,68,72,60
+143,72,76,47
+143,69,75,49
+150,64,69,47
+154,63,67,49
+151,58,67,53
+152,48,66,65
+151,52,65,63
+153,45,61,68
+153,41,58,72
+155,40,52,75
+158,39,49,77
+161,40,55,75
+165,45,58,72
+165,50,63,64
+164,51,70,63
+164,52,73,61
+163,54,76,56
+161,56,77,49
+161,61,78,41
+159,62,77,42
+158,65,75,44
+159,64,67,50
+159,62,65,56
+160,61,56,60
+162,58,52,67
+166,57,47,76
+166,56,44,72
+170,55,35,72
+167,54,38,69
+164,53,41,68
+159,54,50,62
+151,55,58,62
+153,57,55,55
+146,59,65,53
+143,61,70,49
+141,64,73,44
+138,62,77,45
+143,54,72,52
+146,47,70,56
+150,40,66,65
+151,35,63,72
+151,34,59,73
+152,31,56,76
+153,32,51,77
+157,35,46,77
+163,35,43,78
+166,40,46,73
+166,43,52,75
+164,51,61,65
+163,52,67,64
+161,60,70,52
+161,61,72,49
+159,66,74,39
+159,71,75,35
+157,71,77,40
+158,71,74,47
+158,71,66,55
+161,71,59,57
+164,70,51,65
+166,69,46,66
+168,70,39,61
+166,70,44,63
+164,71,45,65
+164,73,39,63
+166,72,42,65
+159,78,50,58
+161,79,49,53
+162,85,52,46
+156,89,59,38
+153,93,64,34
+156,91,62,38
+154,92,64,39
+153,90,62,43
+154,83,60,52
+159,77,51,60
+160,74,47,66
+163,77,43,68
+162,77,43,68
+163,74,44,74
+164,78,44,70
+163,87,37,64
+161,88,56,60
+161,92,52,54
+158,95,63,50
+157,98,57,43
+155,99,63,42
+155,100,60,45
+155,101,59,51
+154,101,63,58
+154,102,64,70
+156,103,60,74
+154,102,66,78
+157,100,64,79
+158,101,66,82
+157,101,66,81
+148,103,77,76
+141,103,88,73
+135,102,91,70
+127,104,103,61
+122,105,106,56
+117,105,112,49
+114,105,115,46
+112,107,117,40
+107,107,122,42
+107,108,121,42
+108,107,121,46
+111,103,117,50
+111,97,115,60
+114,91,113,67
+115,88,108,73
+117,83,106,79
+121,81,100,82
+126,78,95,87
+129,75,90,94
+131,73,85,98
+135,72,81,103
+138,70,76,107
+142,69,70,109