TeachingSoSe2013MLCVSeminar

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

THIS WEBPAGE IS DEPRECATED - please visit our new website

Hauptseminar/Master Seminar:
Machine Learning Methods for Computer Vision Applications

Nassir Navab, Loic Peter, Diana Mateus, Slobodan Ilic

Type: Advanced Seminar Course Module IN8901
Type: Master Seminar Module IN2107
Type: Seminar Module IN0014
SWS: 2+0
ECTS: 4 Credits
Location: MI 03.13.010
Time: Mondays 13.00 - 15.00
Course Language: English

Announcements

  • Registration on TUMOnline is open Once you registered, please send a mail to Loic Peter () including your name, your birthday, program of study and Matrikelnummer.
  • The list of papers will be made available after the introduction meeting (15.04.2013).
  • Maximum number of participants: 20

Requirements

In this Master Seminar (formerly Hauptseminar), each student is asked to select one paper from a list. In order to successfully complete the seminar, participants have to fulfill these requirements:

  • Presentation: The selected paper is presented to the other participants (20 minutes presentation 10 minutes questions). Use the CAMP templates for PowerPoint CAMPmaster.pot, or Latex: CAMP-latex-template.zip.
  • Written Handout: A document of maximum 8 pages is written and submitted one week after the presentation. Please download and use the llncs2e.zip Latex template.
  • Attendance: Participants have to participate actively in all seminar sessions.

Each presentation is followed by a discussion and everyone is encouraged to actively participate. The handout must include all references used and must be written completely in your own words. Copy and paste will not be tolerated. Both handout and presentation have to be done in English.

Schedule

The seminar consists of a preliminary meeting, an introductory meeting and seminar sessions. Each of the sessions will consist of several student presentations. All seminar participants are expected to be present at every session and to actively participate in the discussion.

Date Time Topic By Supervision Material
06.02.2013 14:00-15.00 First Information Meeting Tutors    
15.04.2013 13:00-14.00 Introduction Meeting Tutors    
10.06.2013 13:00-15:00 Random Forest for Image Annotation

GMCP-Tracker: Global Multi-Object Tracking Using Generalized Minimum Clique Graphs
Chen-Hsuan Shih

Nawal Alqurashi
Joé

Vasilis
 
17.06.2013 13:00-15:00 Neighborhood Approximation Forests

Context-Sensitive Decision Forests for Object Detection

Conditional Regression Forests for Human Pose Estimation
Stavroula Timioteraki

Ganglu Wu

Lars Kipferl
Vasilis

Slobodan

Joé
 
24.06.2013 13:00-15:00 Structured Image Segmentation using Kernelized Features

Sparsity Model for Robust Optical Flow Estimation at Motion Discontinuities

Patchmatchgraph: Building a Graph of Dense Patch Correspondences for Label Transfer
Faisal Ibne Mozher

Patricia Vitoria Carrera

Daniela Bayer
Sebastian

Loic

Loic
 
01.07.2013 13:00-15:00 Segmentation of Brain MR Images via Sparse Patch Representation

Dictionary Learning on Riemannian Manifolds

Identifying Sub-Populations via Unsupervised Cluster Analysis on Multi-Edge Similarity Graphs

(Postponed) Multi-organ Abdominal CT Segmentation using hierarchically weighted Subject-specific Atlases
Stefan Winzeck

Alexander Zhdanov

Robert Maier

Burcu Altinkaya
Diana

Diana

Sebastian

Sebastian
 
08.07.2013 13:00-15:00 Background Subtraction using Group Sparsity and Low Rank Constraint

Automatic Detection and Segmentation of Kidneys in 3D CT Images Using Random Forests

Hierarchical Manifold Learning
Ahmed Omrane

Piotr Wojewnik

Nicola Leucht
Loic

Loic

Loic
 
15.07.2013 13:00-15:00 Building High-Level Features Using Large Scale Unsupervised Learning

An Analysis of Single-Layer Networks in Unsupervised Feature Learning

The Vitruvian Manifold: Inferring dense Correspondences for One-Shot Human Pose estimation
Mehrdad Salehi

Alina Roitberg

Florian Weigand
Diana

Diana

Joé
 


List of Papers

Please find below the list of topics for this semester. Send your choice by email to Loic Peter (). First-come, first-served!

* (Taken) Automatic Detection and Segmentation of Kidneys in 3D CT Images Using Random Forests , R. Cuingnet, R. Prevost, D. Lesage, L. Cohen, B. Mory, R. Ardon, MICCAI 2012
* (Taken) Conditional Regression Forests for Human Pose Estimation , Min Sun, Pushmeet Kohli, Jamie Shotton, CVPR 2012
* (Taken) The Vitruvian Manifold: Inferring dense Correspondences for One-Shot Human Pose estimation , Jonathan Taylor, Jamie Shotton, Toby Sharp, Andrew Fitzgibbon, CVPR 2012
* (Taken) GMCP-Tracker: Global Multi-Object Tracking Using Generalized Minimum Clique Graphs , Amir Roshan Zamir, Afshin Dehghan, Mubarak Shah, ECCV 2012
* (Taken) Building High-Level Features Using Large Scale Unsupervised Learning , Quoc Le, Marc Aurelio Ranzato, Rajat Monga, Matthieu Devin, Kal Chen, Greg Corrado, Jeff Dean, Andrew Ng, ICML 2012
* (Taken) An Analysis of Single-Layer Networks in Unsupervised Feature Learning , Adam Coates, Honglak Lee, Andrew Ng, AISTATS 2011
* Deformable Segmentation via Sparse Representation and Dictionary Learning , Shaoting Zhang, Yiqiang Zhan, Dimitris Metaxas, MIA 2012
* Towards Robust and Effective Shape Modeling: Sparse Shape Composition , Shaoting Zhang, Yiqiang Zhan, Maneesh Dewan, Junzhou Huang, Dimitrix Metaxas, MIA 2011
* (Taken) Segmentation of Brain MR Images via Sparse Patch Representation , Tong Tong, Robin Wolz, Joseph V. Hajnal, Daniel Rueckert, MICCAI 2012 Workshop
* Learning Adaptive and Sparse representations of Medical Images , Alessandra Stagliano, Gabriele Chiusano, Curzio Basso, Matteo Santoro, MICCAI 2010 Workshop
* Shape Prior Modeling using Sparse Representation and Online Dictionary Learning , Shaoting Zhang, Yiqiang Zhan, Yan Zhou, Mustafa Uzunbas, Dimitris N. Metaxas, MICCAI 2012
* (Taken) Dictionary Learning on Riemannian Manifolds , Yuchen Xie, Baba C., Vemuri. MICCAI 2012 Workshop
* (Taken) Sparsity Model for Robust Optical Flow Estimation at Motion Discontinuities , Xiaohui Shen and Yin Wu, CVPR 2010
* Segmentation Propagation in Imagenet , D. Kuettel, M. Guillaumin, V. Ferrari, ECCV 2012
* (Taken) Context-Sensitive Decision Forests for Object Detection , Peter Kontschieder, Samuel Rota Bulo, Antonio Criminisi, Pushmeet Kohli, Marcello Pelillo, Horst Bischof, NIPS 2012
* Domain Transfer Learning for MCI Conversion Prediction , B. Cheng, D. Zhang, D. Shen, MICCAI 2012
* Hierarchical Conditional Random Fields for Detection of Gad-enhancing Lesions in Multiple Sclerosis , Z. Karimaghaloo, D. L. Arnold, D. L. Collins, T. Arbel, MICCAI 2012
* (Taken) Multi-organ Abdominal CT Segmentation using hierarchically weighted Subject-specific Atlases , Robin Wolz, Chu Chengwen, Kazunari Misawa, Kensaku Mori, Daniel Rueckert, MICCAI 2012
* (Taken) Identifying Sub-Populations via Unsupervised Cluster Analysis on Multi-Edge Similarity Graphs , Madhura Ingalhalikar, Alex R Smith, William A Parker, Luke Bloy, Ruben Gur, Timothy P.L Roberts, Ragini Verma, MICCAI 2012
* (Taken) Hierarchical Manifold Learning , Kanwal Bhatia, Anil Rao, Anthony Price, Robin Wolz, Joseph Hajnal, Daniel Rueckert, MICCAI 2012
* (Taken) Neighborhood Approximation Forests , Ender Konukoglu, Ben Glocker, Darko Zikic, Antonio Criminisi, MICCAI 2012
* Meta-analysis of Image Databases by Transfer-learning: Prediction and Inference , Yannick Schwartz, Gael Varoquaux, Philippe Pinel, Christophe Pallier, Jean-Baptiste Poline, Bertrand Thirion, MICCAI 2012
* (Taken) Structured Image Segmentation using Kernelized Features , Aurelien Lucchi, Yunpeng Li, Kevin Smith, Pascal Fua, ECCV 2012
* Attributes for Classifier Feedback , Amar Prakash, Devi Parikh, ECCV 2012
* (Taken) Random Forest for Image Annotation , Hao Fu ; Qian Zhang, Guoping Qiu, ECCV 2012
* 3D PM – 3D Deformable Part Models , Bojan Pepik, Peter Gehler, Michael Stark; Bernt Schiele, ECCV 2012
* Incorporating Parameter Uncertainty in Bayesian Segmentation Models: Application to Hippocampal Subfield Volumetry , Juan Eugenio Iglesias, Mert Rory Sabuncu, Koen Van Leemput, MICCAI 2012
* Patchmatchgraph: Building a Graph of Dense Patch Correspondences for Label Transfer , Stephen Gould and Yuhang Zhang, ECCV 2012
* Dimensionality Reduction and Principal Surfaces via Kernel Map Manifolds , Gerber, S, Tasdizen, T, Whitaker, R, ICCV 2011
* (Taken) Background Subtraction using Group Sparsity and Low Rank Constraint , Xinyi Cui, Junzhou Huang, Shaoting Zhang, Dimitris N. Metaxas, ECCV 2012


Literature and Helpful Links

A lot of scientific publications can be found online.

The following list may help you to find some further information on your particular topic:

Some publishers:

Libraries (online and offline):

Some further hints for working with references:

  • JabRef is a Java program for comfortable working with Bibtex literature databases. Handy feature: if you know the PubMed ID for an article, JabRef can import data from there (via "Web Search/Medline").
  • Mendeley is a cross-platform program for organising your references.

If you find useful resources that are not already listed here, please tell us, so we can add them for others. Thanks.


TeachingForm
Title: Machine Learning Methods for Computer Vision Applications
Professor: Nassir Navab
Tutors: Loic Peter , Slobodan Ilic , Diana Mateus , Sebastian Poelsterl , Joé Lallemand , Vasilis Belagiannis
Type: Hauptseminar
Information: Hauptseminar, SWS: 2, ECTS: 4
Term: 2013SoSe
Abstract:  


Edit | Attach | Refresh | Diffs | More | Revision r1.34 - 01 Jul 2013 - 09:53 - LoicPeter

Lehrstuhl für Computer Aided Medical Procedures & Augmented Reality    rss.gif