└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # Correlation Filter Trackers notes 2 | 3 | The notes are ordered by year ascendant. Tracker listed in each year are in no particular order 4 | 5 | Conferences names: 6 | * __CVPR__ = IEEE Conference on Computer Vision and Pattern Recognition 7 | * __ECCV__ = European Conference on Computer Vision 8 | * __ICCV__ = International Conference on Computer Vision 9 | * __IJCV__ = International Journal of Computer Vision 10 | * __TPAMI__ = IEEE Transactions on Pattern Analysis and Machine Intelligence 11 | 12 | ## 2018 13 | 14 | * _MKCFup_ 15 | * __Paper:__ ["High-speed Tracking with Multi-kernel Correlation Filters"](https://arxiv.org/pdf/1806.06418.pdf) 16 | * __Presented in:__ [arXiv](https://arxiv.org/abs/1806.06418) 17 | * __Major Contribution/s:__ Introduce the multi-kernel learning (MKL) into KCF in a different way compared to the MKCF tracker, achieving better performance with not much drop in fps. 18 | * __Code:__ - 19 | 20 | * _LCT Tracker v2_ 21 | * __Paper:__ ["Adaptive Correlation Filters with Long-Term and Short-Term Memory for Object Tracking"](https://drive.google.com/open?id=0B8-i_hZvGyZNb2I2aVVxbmpWZmM) 22 | * __Presented in:__ ICJV 23 | * __Major Contribution/s:__ Learn multiple adaptive correlation filters with both long-term memory and short-term memory of target appearance for robust object tracking. 24 | * __Code:__ [Matlab](https://github.com/chaoma99/lct-tracker) 25 | 26 | ## 2017 27 | 28 | * _ACFN_ 29 | * __Paper:__ ["Attentional Correlation Filter Network for Adaptive Visual Tracking"](https://drive.google.com/open?id=0B0ZkG8zaRQoLUHdlTGNtUWFjd1E) 30 | * __Presented in:__ CVPR 31 | * __Major Contribution/s:__ Propose a new framework in which an attention network that selects the best module (a set of Correlation Filters) to track the object in a certain frame. 32 | * __Code:__ [Matlab](https://github.com/jongwon20000/ACFN) 33 | 34 | * _CFNet_ ([Project Page](https://www.robots.ox.ac.uk/~luca/cfnet.html)) 35 | * __Paper:__ ["End-to-end representation learning for Correlation Filter based tracking"](http://openaccess.thecvf.com/content_cvpr_2017/html/Valmadre_End-To-End_Representation_Learning_CVPR_2017_paper.html) 36 | * __Presented in:__ CVPR 37 | * __Major Contribution/s:__ First work to propose training the Correlation Filter jointly with a Siamese Network in an end-to-end fashion. 38 | * __Code:__ [Matlab](https://github.com/bertinetto/cfnet) 39 | 40 | * _DCFNet_ 41 | * __Paper:__ ["DCFNet: Discriminant Correlation Filters Network for Visual Tracking"](https://arxiv.org/pdf/1704.04057.pdf) 42 | * __Presented in:__ arXiv 43 | * __Major Contribution/s:__ Another work to propose training the Correlation Filter jointly with a Siamese Network. Different from CFNet in network architecture and place of the Correlation Filter in the Tracker architecture. 44 | * __Code:__ [Matlab](https://github.com/foolwood/DCFNet) | [Python (PyTorch)](https://github.com/foolwood/DCFNet_pytorch) 45 | 46 | ## 2015 47 | 48 | * _MKCF_ 49 | * __Paper:__ ["Multi-kernel Correlation Filter for Visual Tracking"](https://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Tang_Multi-Kernel_Correlation_Filter_ICCV_2015_paper.pdf) 50 | * __Presented in:__ ICCV 51 | * __Major Contribution/s:__ Introduce multi-kernel to correlation filter based trackers. 52 | * __Code:__ [.exe file](http://vision.ia.ac.cn/Faculty/mtang/MKCF_exe.rar) 53 | 54 | * _KCF_ ([Project Page](http://www.robots.ox.ac.uk/~joao/circulant/)) 55 | * __Paper:__ ["High-Speed Tracking with Kernelized Correlation Filters"](http://www.robots.ox.ac.uk/~joao/publications/henriques_tpami2015.pdf) 56 | * __Presented in:__ TPAMI 57 | * __Major Contribution/s:__ Derive a new Kernelized Correlation Filter (KCF) and propose a fast multi-channel extension of 58 | linear correlation filters, via a linear kernel, called by authors Dual Correlation Filter (DCF). 59 | * __Code:__ [Matlab](http://www.robots.ox.ac.uk/~joao/circulant/tracker_release2.zip) | More codes in Project page 60 | 61 | * _LCT Tracker v1_ 62 | * __Paper:__ ["Long-Term Correlation Tracking"](http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Ma_Long-Term_Correlation_Tracking_2015_CVPR_paper.pdf) 63 | * __Presented in:__ CVPR 64 | * __Major Contribution/s:__ Introduced online random fern classifier as re-detection component for long-term tracking. 65 | * __Code:__ [Matlab](https://github.com/chaoma99/lct-tracker) 66 | 67 | * _CF2_ ([Project Page](https://sites.google.com/site/chaoma99/iccv15-tracking)) 68 | * __Paper:__ ["Hierarchical Convolutional Features for Visual Tracking"](https://drive.google.com/file/d/0B8-i_hZvGyZNZS1YV2tvSDVTeE0/view?usp=sharing) 69 | * __Presented in:__ ICCV 70 | * __Major Contribution/s:__ Learn a Correlation Filter on each Convolutional Layer of a pre-trained network, taking advantage of the different information of features from different layers. 71 | * __Code:__ [Matlab](https://github.com/jbhuang0604/CF2) 72 | 73 | ## 2012 74 | 75 | * _CSK_ ([Project Page](http://www.robots.ox.ac.uk/~joao/circulant/)) 76 | * __Paper:__ ["Exploiting the Circulant Structure of Tracking-by-detection with Kernels"](http://www.robots.ox.ac.uk/~joao/publications/henriques_eccv2012.pdf) 77 | * __Presented in:__ ECCV 78 | * __Major Contribution/s:__ Introduced Ridge Regression problem with circulant matrix to apply kernel methods. 79 | * __Code:__ [Matlab](http://www.robots.ox.ac.uk/~joao/circulant/tracker_release.zip) | More codes in Project page 80 | 81 | ## 2010 82 | 83 | * _MOSSE (Minimum Output Sum of Squared Errors)_ 84 | * __Paper:__ ["Visual Object Tracking using Adaptive Correlation Filters"](http://www.cs.colostate.edu/~vision/publications/bolme_cvpr10.pdf) 85 | * __Presented in:__ CVPR 86 | * __Major Contribution/s:__ Pioneering work in introducing Correlation Filters for visual tracking. Filter is single channel. 87 | * __Code:__ - 88 | 89 | --------------------------------------------------------------------------------