Machine Learning for Graphics, Vision and Multimedia

Recently, machine learning techniques have been proven and widely used in the fields of computer graphics, computer vision and multimedia. In this course, we will study these algorithms and their applications.

Time: 2:20pm-5:20pm Thursday

Classroom:CSIE Room 111

Presentation Guidelines:

Note that the paper list here only means to suggest the topic and scope of your presentation, you are free to change the paper list for your presentation acccording to your own taste. However, please keep me updated and send out the required reading to the group a week before your presentation.
We are mostly users for these methods. Hence, try to concentrate on key ideas, intuition and usage of these methods, not the math. So, do not suffer too much on the details and math if they are too difficult. Furthermore, for most methods, you can find their matlab implementation online. It would be a good idea to trace and demo these codes to illustrate implementation issues.
For the application papers, try to focus on the key concept not the details since these papers are diverse in fields. Of course, you are free to replace them with other related papers as well.
I have created a Wiki page for each topic, please add any related material there including example codes, papers and people's webpages.
Start early. Some of these topics are much more diccicult than you could imagine.
All class participants should read the required reading before the class.

Topics

Date	Topic	Tutorial	References
03/16	Principal Component Analysis 姜任遠文宗麟	PCA	Max Wellings, Linear Models. Sam Roweis, EM Algorithms for PCA and SPCA, NIPS 1997. Michael Tipping, Christopher Bishop, Probabilistic Principal Component Analysis, Journal of the Royal Statistical Society, Series, 1999. Matthew Turk, Alex Pentland, Eigenfaces for recognition, Journal of Cognitive Neuroscience, 1991. Tim Cootes, C. J. Taylor, Chapter 4 Statistical Shape Models, from Statistical Models of Appearance for Computer Vision. Volker Blanz, Thomas Vetter, A Morphable Model for the Synthesis of 3D Faces, SIGGRAPH, 1999. Brett Allen, Brian Curless, Zoran Popovic, The Space of Human Body Shapes: Reconstruction and Parameterization from Range Scans, SIGGRAPH, 2003.
03/23	PCA Extensions 葉冠麟黃輔中	PCA missing data Robust PCA	Haifeng Chen, Principal Component Analysis with Missing Data and Outliers. Fernando De la Torre, Michael Black, Robust Principal Component Analysis for Computer Vision, CVPR, 2001. Chakra Chennubhotla, Allan Hepson, SparsePCA Extracting Multi-Scale Structure from Data, ICCV, 2001. Rene Vidal, Yi Ma, Shankar Sastry, Generalized Principal Component Analysis (GPCA), CVPR, 2003. Rene Vidal, Yi Ma, Shankar Sastry, Algebraic Methods for Multiple-Subspace Segmentation.
03/30	Isomap Locally Linear Embedding 謝昌熹許平	ISOMAP & LLE	Stephen Borgatti, Multidimensional Scaling. Joshua Tenenbaum, Vin de Silva, John Langford, A Global Geometric Framework for Nonlinear Dimensionality Reduction, Science, 2000. Sam Roweis, Lawrence Saul, Nonlinear Dimensionality Reduction by Locally Linear Embedding, Science, 2000. Lawrence Saul, Sam Roweis, An Introduction to Locally Linear Embedding. Lawrence Saul, Sam Roweis, Think Globally, Fit Locally: Unsupervised Learning of Low Dimensional Manifolds, Journal of Machine Learning Research, 2003. Robert Pless, Image Spaces and Video Trajectories: Using Isomap to Explore Video Sequences, ICCV, 2003. Jackie Assa, Yaron Caspi, Daniel Cohen-Or, Action synopsis: Pose Selection and Illustration, ICCV, 2003.
04/06	Laplacian Eigenmaps Linear Discriminant Analysis 黃俊翔陳駿丞蕭淳澤	LDA LDA applications	Mikhail Belkin, Partha Niyogi, Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering, NIPS, 2001. Lawrence Saul, Kilian Weinberger, Fei Sha, Jihun Ham, Daniel Lee, Spectral Methods for Dimensionality Reduction. Max Wellings, Fisher Linear Discriminant Analysis. Peter Belhumeur, Joao Hespanha, David Kriegman, Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection, PAMI, 1997. Jieping Ye, Ravi Janardan, Qi Li, Two-Dimensional Linear Discriminant Analysis, NIPS, 2004.
04/13	Locality Preserving Projection Local Discriminant Embedding 蕭志傑翁仲毅潘振銘	LPP	Xiaofei He, Partha Niyogi, Locality Preserving Projection, NIPS, 2003. Xiaofei He, Shuicheng Yan, Yuxiao Hu, Hong-Jiang Zhang, Learning a Locality Preserving Subspace for Visual Recognition, ICCV, 2003. Xiaofei He, Incremental Semi-Supervised Subspace Learning for Image Retrieval, ACM Multimedia, 2004. Xiaofei He, Shuicheng Yan, Yuxiao Hu, Partha Niyogi, Hong-Jiang Zhang, Face Recognition Using Laplacianfacesl, PAMI, 2005. Hwann-Tzong Chen, Huang-Wei Chang, Tyng-Luh Liu, Local Discriminant Embedding and Its Variants, CVPR, 2005.
04/27 05/04	Support Vector Machines 李根逸林宗勳林宏儒何昇舫	SVM SVM SVM libsvm	Christopher Burges, A Tutorial on Support Vector Machines for Pattern Recognition, Data Mining and Knowledge Discovery, 1998. Max Wellings, Support Vector Machines. Edgar Osuna, Robert Freund, Federico Girosi, Training Support Vector Machines: an Application to Face Detection, CVPR, 1997. Sami Romdhani, Philip Torr, Bernhard Scholkopf, Andrew Blake, Computationally Efficient Face Detection, ICCV, 2001. Shai Avidan, Support Vector Tracking, PAMI, 2004. Apostol Natsev, Milind Naphade, Jelena Tesic, Learning the Semantics of Multimedia Queries and Concepts from a Small Number of Examples, ACM Multimedia, 2005.
	Support Vector Regression 黃子桓	SVR	Alex Smola, Bernhard Scholkopf, A Tutorial on Syupport Vector Regression, 2003. Max Wellings, Support Vector Regression.
	Relevance Vector Machine 楊善詠	RVM	Michael Tipping, The Relevance Vector Machine, NIPS, 2000. Michael Tipping, Sparse Bayesian Learning and the Relevance Vector Machine, Journal of Machine Lerning Research, 2001. Oliver Williams, Andrew Blake, Roberto Cipolla, Sparse Bayesian Learning for Efficient Visual Tracking, PAMI, 2005.
05/11	Boosting 翁明昉陳宏暐黃信騫鄭鎧尹	Ensemble Learning AdaBoost binary AdaBoost extensions AdaBoost applications	Yoav Freund, Robert Schapire, A Decision-Theoretic eneralization of On-Line Learning and an Application to Boosting, European Conference on Computational Learning Theory 1995. Eric Bauer, Ron Kohavi, An Empirical Comparison of Voting Classification Algorithms: Bagging, Boosting, and Variants, Machine Learning, 1999. Paul Viola, Michael Jones, Robust Real-Time Face Detetion, International Journal of Computer Vision, 2004. Paul Viola, Michael Jones, Detecting Pedestrians Using Patterns of Motion and Appearance, International Journal of Computer Vision, 2005. Shai Avidan, Ensemble Tracking, CVPR, 2005.
05/18 05/25	Graphical Models 朱威達	Graphical Model	Kevin Murphy, An Introduction to Graphical Models. Michael Jordan, Yair Weiss, Probabilistic Inference in Graphical Models.
	Belief Propagation 鄭文皇謝致仁謝永桓	low-level learning Applications	Max Wellings, Belief Popagation. Jonathan Yedidia, William Freeman, Yair Weiss, Understanding Belief Propagation and its Generalizations, IJCAI, 2001. Pedro Felzenszwalb, Daniel Huttenlocher, Efficient Belief Propagation for Early Vision, CVPR, 2004. William Freeman, Egon Pasztor, Owen Carmichael, Learning Low-Level Vision, IJCV, 2001. William Freeman, Thouis Jones, Egon Pasztor, Example-Based Super-Resolution, IEEE CG&A, 2002. Jue Wang, Michael Cohen, An Iterative Optimization Approach for Unified Image Segmentation and Matting, ICCV, 2005.
05/25 06/01 06/08	Approximate Inference		Max Wellings, Approximate Inference.
	Expectation Maximization 莊上墀郭煜楓劉治杰楊恕先	EM	Max Wellings, EM-Algorithm. Carlo Tomasi, Estimating Gaussian Mixture Densities with EM - A Tutorial Radford Neal, Geoffrey Hinton, A View of the EM algorithm that Justifies Incremental, Sparse, and Other Variants. Jeff Bilmes, A Gentle Tutorial of the EM Algorithm and its Application to Parameter Estimation for Gaussian Mixture and Hidden Markov Models. Frank Dellaert, The Expectation Maximization Algorithm. Yair Weiss, Motion Segmentation using EM - a Short Tutorial. M. Weber, Max Welling, P. Perona, Unsupervised Learning of Models for Recognition, ECCV 2000. M. Weber, Max Welling, P. Perona, Towards Automatic Discovery of Object Categories, CVPR 2000.
	Variational Learning 林蓉珊周亮瑜呂旺洲	Variational Learning Variational Learning Variational Learning	Michael Jordan, Zoubin Ghahramani, Tommis Jaakkola, Lawrence Saul, An Introduction to Variational Methods for Graphical Models, Machine Learning, 1999. Nebojsa Jojic, Brendan Frey, Learning Flexible Sprites in Video Layers, CVPR, 2001. Brendan Frey, Nebojsa Jojic, Anitha Kannan, Learning Appearance and Transparency Manifolds of Occluded Objects in Layers, CVPR, 2003. Nebojsa Jojic, Brendan Frey, A Generative Model for 2.5D Vision: Estimation Appearance, Transformation, Illumination, Transparency and Occlusion. Brendan Frey, Nebojsa Jojic, A Comparison of Algorithms for Inference and Learning in Probabilistic Graphical Models, PAMI, 2005. Li Fei-Fei, Rob Fergus, Pietro Perona, A Bayesian Approach to Unsupervised One-Shot Learning of Object Categories, PAMI, 2005.

Resources

Advanced Topics in Learning and Vision, National Taiwan University, 2005, This course is very similar to ours. Actually, we will pretty much follow this course. Strongly recommended!
Vision Algorithms, University of Washington, 2004, This page includes tutorials and videos for some topics we might cover, including belief propagation, variational inference, supervised learning and dimensionality reduction. Strongly recommended!
ICCV Course on Learning and Vision 2003, A short course taught by experts of applying learning to vision. Strongly recommended!
Machine Learning for Computer Graphics, University of Washington, 2002, mostly focus on graphics allpications.
The Matrix Cookbook, A useful reference for matrix.
The Matrix Reference Manual, Another useful reference for matrix.