学习计划2017

Machine-Learning

到 学术工具网站 学习使用Latex进行论文撰写相关工作。

一 前言

建议代码基础部分不要单独看太久，了解基本思想理论即可。关键要掌握理论算法的技术细节以及尽量尝试让自己通过代码独立实现这些理论。

二 基础知识课程

课程	机构	参考书	Notes等其他资料
单变量微积分	MIT	Calculus with Analytic Geometry	链接
多变量微积分	MIT	Multivariable Calculus	链接
线性代数	MIT	Introduction to Linear Algebra	链接
统计入门	可汗学院	暂无	暂无
概率论入门: 链接1,链接2	NTU	暂无	暂无
概率与统计	MIT	Introduction to Probability	链接
矩阵论	暂无	矩阵论	暂无
凸优化1	Stanford	Convex Optimization	链接
凸优化2	Stanford	暂无	链接
统计学习入门	Stanford	An Introduction to Statistical Learning	链接
机器学习基石	NTU	Learning from Data	链接
机器学习技法	NTU	暂无	链接
机器学习	Caltech	Learning from Data	链接
机器学习(matlab)	Stanford	暂无	链接

三 学习路线

1.数学基础初级

课程	机构	参考书	Notes等其他资料
单变量微积分	MIT	Calculus with Analytic Geometry	链接
多变量微积分	MIT	Multivariable Calculus	链接
线性代数	MIT	Introduction to Linear Algebra	链接
统计入门	可汗学院	暂无	暂无
概率论入门: 链接1,链接2	NTU	暂无	暂无
概率与统计	MIT	Introduction to Probability	链接

2.机器学习课程初级

课程	机构	参考书	Notes等其他资料
统计学习入门	Stanford	An Introduction to Statistical Learning	链接
机器学习入门	Coursera	暂无	链接

3.程序语言能力

程序语言目前主要是帮助完成课后作业以及实现自己的一些想法，仅给出推荐的参考学习链接，只需要掌握一些常用的模块即可。

课程	参考学习链接	描述
MatConvNet教程	链接	适用于Matlab语言环境(重点阅读)
廖雪峰Python教程	链接	Python语言基础 (重点阅读)
莫凡Python教程	链接	Python基础
吴恩达机器学习课程Python实现(源码+教程）	链接	使用Python实现基础算法(重点阅读)
莫凡Python数据处理（Pandas+Numpy+Matplotlib）	链接	Python数据处理，可视化操作
莫凡Pytorch教程	链接	Pytorch深度学习框架(重点阅读)
Linux操作系统教程	链接	开发环境的学习

4.数学基础中级

课程	机构	参考书	Notes等其他资料
矩阵论	暂无	矩阵论	暂无
凸优化1	Stanford	Convex Optimization	链接
凸优化2	Stanford	暂无	链接

5.机器学习课程中级

此处NTU和Caltech两个大学的课程是由《Learning from Data》一书的两个不同的作者讲的，所以仅仅只需选择一个完成即可，注意：如果选择完成NTU的机器学习课程，则 NTU的“机器学习基石”和“机器学习技法”需同时完成。。

课程	机构	参考书	Notes等其他资料
机器学习基石	NTU	Learning from Data	链接
机器学习技法	NTU	暂无	链接
机器学习	Stanford	暂无	链接
机器学习	Caltech	Learning from Data	链接

6.推荐书籍

建议一般难度的书籍至少详细阅读一本，建议看两本，而较难的书籍不做任何要求，仅供自我提高。

书名	难度
统计学习方法	一般
An Introduction to Statistical Learning	一般
Machine Learning	一般
Learning from Data	一般，配套讲义
Pattern Recognition and Machine Learning	较难(偏贝叶斯)
The Elements of Statistical Learning	较难
Understanding Machine Learning:From Theory to Algorithms	较难

7.机器学习专项领域学习

7.1一些专项领域资料

名称	描述
深度学习	一般指深度神经网络下的各种分类、分割、跟踪等学习方法
图模型	暂无
强化学习	非监督学习的一种，比较有名的有AlphaGo Zero
Hash	暂无

7.2领域会议期刊

名称	描述
PAMI	PAMI是IEEE旗下，模式识别和机器机器学习领域最重要的学术性汇刊之一。在各种统计中，PAMI被认为有着很强的影响因子和很高的排名。
NIPS	NIPS，全称神经信息处理系统大会(Conference and Workshop on Neural Information Processing Systems)，是一个关于机器学习和计算神经科学的国际会议。该会议固定在每年的12月举行,由NIPS基金会主办。NIPS是机器学习领域的顶级会议 。在中国计算机学会的国际学术会议排名中，NIPS为人工智能领域的A类会议 。
ICML	ICML 是 International Conference on Machine Learning的缩写，即国际机器学习大会。ICML如今已发展为由国际机器学习学会（IMLS）主办的年度机器学习国际顶级会议。
AAAI	美国人工智能协会（American Association for Artificial Intelligence）美国人工智能协会是人工智能领域的主要学术组织之一。该协会主办的年会（AAAI, The National Conference on Artificial Intelligence）是一个主要的人工智能学术会议。
IJCAI	国际人工智能联合会议（International Joint Conference on Artificial Intelligence, 简称为IJCAI）是人工智能领域中最主要的学术会议之一，原为单数年召开，自2015年起改为每年召开。
KDD
ICDM
COLT
CVPR	CVPR是IEEE Conference on Computer Vision and Pattern Recognition的缩写，即IEEE国际计算机视觉与模式识别会议。该会议是由IEEE举办的计算机视觉和模式识别领域的顶级会议。
…	…

7.3 目标跟踪领域

论文以及代码：

1.效果较好的基准方法（之后的很多方法都是基于这些方法做的改进）：

• MOSSE: David S. Bolme, J. Ross Beveridge, Bruce A. Draper, Yui Man Lui.
  “Visual Object Tracking using Adaptive Correlation Filters.” ICCV (2010).[paper][project](重点阅读)
• CSK: João F. Henriques, Rui Caseiro, Pedro Martins, Jorge Batista.
  “Exploiting the Circulant Structure of Tracking-by-detection with Kernels.” ECCV (2012).[paper][project]
• STC: Kaihua Zhang, Lei Zhang, Ming-Hsuan Yang, David Zhang.
  “Fast Tracking via Spatio-Temporal Context Learning.” ECCV (2014).[paper][project]
• KCF/DCF: João F. Henriques, Rui Caseiro, Pedro Martins, Jorge Batista.
  “High-Speed Tracking with Kernelized Correlation Filters.” TPAMI (2015).[paper][project](重点阅读)

2.基于颜色信息的目标跟踪方法

• CN: Martin Danelljan, Fahad Shahbaz Khan, Michael Felsberg and Joost van de Weijer.
  “Adaptive Color Attributes for Real-Time Visual Tracking.” CVPR (2014).[paper][project]
• MOCA: Guibo Zhu, Jinqiao Wang, Yi Wu, Xiaoyu Zhang, Hanqing Lu.
  “MC-HOG Correlation Tracking with Saliency Proposal.” AAAI (2016).[paper]
• Staple: Luca Bertinetto, Jack Valmadre, Stuart Golodetz, Ondrej Miksik, Philip H.S. Torr.
  “Staple: Complementary Learners for Real-Time Tracking.” CVPR (2016).[paper][project][github]

3.多尺度的目标跟踪方法

• DSST: Martin Danelljan, Gustav Häger, Fahad Shahbaz Khan and Michael Felsberg.
  “Accurate Scale Estimation for Robust Visual Tracking.” BMVC (2014).[paper][project]
• fDSST: Martin Danelljan, Gustav Häger, Fahad Khan, Michael Felsberg.
  “Discriminative Scale Space Tracking.” TPAMI (2017).[paper][project]
• SAMF: Yang Li, Jianke Zhu.
  “A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration.” ECCV workshop (2014).[paper][github]
• SKCF: Solis Montero, Andres, Jochen Lang, Robert Laganiere.
  “Scalable Kernel Correlation Filter with Sparse Feature Integration.” ICCV workshop (2015).[paper][project][github]
• KCFDP/KCFDPT: Dafei Huang, Lei Luo, Mei Wen, Zhaoyun Chen and Chunyuan Zhang.
  “Enable Scale and Aspect Ratio Adaptability in Visual Tracking with Detection Proposals.” BMVC (2015).[paper][github1][github2]

4.Multi kernel & feature & template & task

• MKCF: Ming Tang, Jiayi Feng.
  “Multi-kernel Correlation Filter for Visual Tracking.” ICCV (2015).[paper][exe]
• CF+MT: Adel Bibi, Bernard Ghanem.
  “Multi-Template Scale Adaptive Kernelized Correlation Filters.” ICCV workshop (2015).[paper][github]
• SCT: Jongwon Choi, Hyung Jin Chang, Jiyeoup Jeong, Yiannis Demiris, and Jin Young Choi.
  “Visual Tracking Using Attention-Modulated Disintegration and Integration.” CVPR (2016).[paper][project]
• MvCFT: Xin Li, Qiao Liu, Zhenyu He, Hongpeng Wang, Chunkai Zhang, Wen-Sheng Chen.
  “A Multi-view Model for Visual Tracking via Correlation Filters.” KNOSYS (2016).[paper][exe]
• MCPF: Tianzhu Zhang, Changsheng Xu, Ming-Hsuan Yang.
  “Multi-task Correlation Particle Filter for Robust Visual Tracking.” CVPR (2017).[paper][exe]

5.基于局部信息

• RPAC: Liu Ting, Gang Wang, Qingxiong Yang.
  “Real-time part-based visual tracking via adaptive correlation filters.” CVPR (2015).[paper]
• RPAC+: Liu Ting, Gang Wang, Qingxiong Yang, Li Wang.
  “Part-based Tracking via Discriminative Correlation Filters.” TCSVT (2016).[paper]
• RPT: Yang Li, Jianke Zhu and Steven C.H. Hoi.
  “Reliable Patch Trackers: Robust Visual Tracking by Exploiting Reliable Patches.” CVPR (2015).[paper][github]
• DPCF: Osman Akina, Erkut Erdema, Aykut Erdema, Krystian Mikolajczykb.
  “Deformable Part-based Tracking by Coupled Global and Local Correlation Filters.” JVCIR (2016).[paper][code]
• DPT: Alan Lukežič, Luka Čehovin, Matej Kristan.
  “Deformable Parts Correlation Filters for Robust Visual Tracking.” CVPR (2016).[paper]
• StructCF: Si Liu, Tianzhu Zhang, Changsheng Xu, Xiaochun Cao.
  “Structural Correlation Filter for Robust Visual Tracking.” CVPR (2016).[paper]
• Rui Yao, Shixiong Xia, Zhen Zhang, Yanning Zhang.
  “Real-time Correlation Filter Tracking by Efficient Dense Belief Propagation with Structure Preserving.” TMM (2016).[paper]
• LGCF: Heng Fan, Jinhai Xiang.
  “Robust Visual Tracking via Local-Global Correlation Filter.” AAAI (2017).[paper]

6.长时间序列跟踪（ Long-term）

• LCT: Chao Ma, Xiaokang Yang, Chongyang Zhang, Ming-Hsuan Yang.
  “Long-term Correlation Tracking.” CVPR (2015).[paper][project][github]
• LCT+: Chao Ma, Jia-Bin Huang, Xiaokang Yang, Ming-Hsuan Yang.
  “Adaptive Correlation Filters with Long-Term and Short-Term Memory for Object Tracking.” IJCV (under review)[project]
• MUSTer: Zhibin Hong, Zhe Chen, Chaohui Wang, Xue Mei, Danil Prokhorov, and Dacheng Tao.
  “MUlti-Store Tracker (MUSTer): a Cognitive Psychology Inspired Approach to Object Tracking.” CVPR (2015).[paper][project][code]
• CCT: Guibo Zhu, Jinqiao Wang, Yi Wu, Hanqing Lu.
  “Collobarative Correlation Tracking.” BMVC (2015).[paper][code]

7.自适应响应(Response adaptation)

• CF+AT: Adel Bibi, Matthias Mueller, and Bernard Ghanem.
  “Target Response Adaptation for Correlation Filter Tracking.” ECCV (2016).[paper][github]
• RCF: Yao Sui, Ziming Zhang, Guanghui Wang, Yafei Tang, Li Zhang.
  “Real-Time Visual Tracking: Promoting the Robustness of Correlation Filter Learning.” ECCV (2016).[paper]
• OCT-KCF: Baochang Zhang, Zhigang Li, Xianbin Cao, Qixiang Ye, Chen Chen, Linlin Shen, Alessandro Perina, Rongrong Ji.
  “Output Constraint Transfer for Kernelized Correlation Filter in Tracking.” TSMC (2016).[paper][github]
• Yao Sui, Guanghui Wang, Li Zhang.
  “Correlation Filter Learning Toward Peak Strength for Visual Tracking.” TCYB (2017).[paper]

8. Training set adaptation-在训练集的获取方面有改进的算法

• SRDCFdecon: Martin Danelljan, Gustav Häger, Fahad Khan, Michael Felsberg.
  “Adaptive Decontamination of the Training Set: A Unified Formulation for Discriminative Visual Tracking.” CVPR (2016).[paper][project](重点阅读)
• ECO: Martin Danelljan, Goutam Bhat, Fahad Shahbaz Khan, Michael Felsberg.
  “ECO: Efficient Convolution Operators for Tracking.” CVPR (2017).[paper][project](重点阅读)

9.Bound effect-边界效应解决方案比较好的文章

• SRDCF: Martin Danelljan, Gustav Häger, Fahad Khan, Michael Felsberg.
  “Learning Spatially Regularized Correlation Filters for Visual Tracking.” ICCV (2015).[paper][project](重点阅读)
• CFLB Hamed Kiani Galoogahi, Terence Sim, Simon Lucey.
  “Correlation Filters with Limited Boundaries.” CVPR (2015).[paper][project][code]
• SWCF: Erhan Gundogdu, A. Aydın Alatan.
  “Spatial Windowing for Correlation Filter based Visual Tracking.” ICIP (2016).[paper][code]
• CF+CA: Matthias Mueller, Neil Smith, Bernard Ghanem.
  “Context-Aware Correlation Filter Tracking.” CVPR (2017).[paper][project][github]
• CSR-DCF: Alan Lukežič, Tomáš Vojíř, Luka Čehovin, Jiří Matas, Matej Kristan.
  “Discriminative Correlation Filter with Channel and Spatial Reliability.” CVPR (2017).[paper][github]
• MRCT: Hongwei Hu, Bo Ma, Jianbing Shen, Ling Shao.
  “Manifold Regularized Correlation Object Tracking.” TNNLS (2017).[paper][github]
• BACF: Hamed Kiani Galoogahi, Ashton Fagg, Simon Lucey.
  “Learning Background-Aware Correlation Filters for Visual Tracking.” arXiv (2017).[paper]

10.Continuous-将离散空间的计算转换到连续空间

• C-COT: Martin Danelljan, Andreas Robinson, Fahad Khan, Michael Felsberg.
  “Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking.” ECCV (2016).[paper][project][github](重点阅读)

11. SVM-利用支持向量机做分类的跟踪算法

• SCF: Wangmeng Zuo, Xiaohe Wu, Liang Lin, Lei Zhang, Ming-Hsuan Yang.
  “Learning Support Correlation Filters for Visual Tracking.” arXiv (2016).[paper][project]
• LMCF: Mengmeng Wang, Yong Liu, Zeyi Huang.
  “Large Margin Object Tracking with Circulant Feature Maps.” CVPR (2017).[paper][zhihu]

12. Deep-基于深度学习的目标跟踪算法

• CF2: Chao Ma, Jia-Bin Huang, Xiaokang Yang and Ming-Hsuan Yang.
  “Hierarchical Convolutional Features for Visual Tracking.” ICCV (2015)[paper][project][github]
• CF2+: Chao Ma, Yi Xu, Bingbing Ni, Xiaokang Yang.
  “When Correlation Filters Meet Convolutional Neural Networks for Visual Tracking.” SPL (2016).[paper]
• DeepSRDCF: Martin Danelljan, Gustav Häger, Fahad Khan, Michael Felsberg.
  “Convolutional Features for Correlation Filter Based Visual Tracking.” ICCV workshop (2015).[paper][project](重点阅读)
• HDT: Yuankai Qi, Shengping Zhang, Lei Qin, Hongxun Yao, Qingming Huang, Jongwoo Lim, Ming-Hsuan Yang.
  “Hedged Deep Tracking.” CVPR (2016).[paper][project]
• ACFN: Jongwon Choi, Hyung Jin Chang, Sangdoo Yun, Tobias Fischer, Yiannis Demiris.
  “Attentional Correlation Filter Network for Adaptive Visual Tracking.” CVPR (2017).[paper][project]
• CFNet: Jack Valmadre, Luca Bertinetto, João Henriques, Andrea Vedaldi, Philip Torr.
  “End-to-end Representation Learning for Correlation Filter based Tracking.” CVPR (2017).[paper][project][github](重点阅读)
• DCFNet: Qiang Wang, Jin Gao, Junliang Xing, Mengdan Zhang, Weiming Hu.
  “DCFNet: Discriminant Correlation Filters Network for Visual Tracking.” arXiv (2017).[paper][github](重点阅读)
• CFCF Erhan Gundogdu, A. Aydin Alatan.
  “Good Features to Correlate for Visual Tracking.” arXiv (2017).[paper]