TeachingWs10MLCVSeminar

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, Diana Mateus, Olivier Pauly, Loren Schwarz

Type: Advanced Seminar Course Module IN8901
Type: Master Seminar Module IN2107
Type: Seminar Module IN0014
SWS: 2+0
ECTS: 4 Credits
Course Language: English

Announcements

  • Seminar Guidelines available online.
  • FIRST MEETING : October 25 at 4:00pm, in room MI 03.13.010.
  • All participants, please register for the seminar in TUMonline. (Registration in TUMonline should be now open)
  • on July 27 at 2.00 pm, a preliminary meeting will take place in room MI 03.13.010.

Requirements

In this Master Seminar (formerly Hauptseminar), each student is asked to select one topic from the list below. In order to successfully complete the seminar, participants are required to:

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 wont be tolerated. Both handout and presentation have to be done in English.

Registration

Interested students, please take a look at the papers listed below and select one you would like to base your seminar talk on. Then please send an email to Olivier Pauly (), including your paper choice, your name, your birthday, program of study and Matrikelnummer.

Presentation Topics

Please choose one of the following papers for your seminar presentation. For obtaining the full-text PDFs, please use Google and especially Google Scholar. In case you are interested in a paper but cannot find the full text, please e-mail us. You may also suggest another recent paper from the conferences below or other related ones.

Image Classification and Retrieval

  • (2007 Science) Clustering by passing messages. Brendan J. Frey and Delbert Dueck.
  • (2008 CVPR) Semantic Texton Forests for Image Categorization and Segmentation. Jamie Shotton, Matthew Johnson, Roberto Cipolla.
  • (taken) (2009 BMVC) Random Forest Clustering and Application to Video Segmentation. Frank Perbet, Björn Stenger, Atsuto Maki.
  • (taken) (2009 ICCV) On-line Random Forest. Amir Saffari Christian Leistner Jakob Santner Martin Godec Horst Bischof.
  • (2009 ICCV) Video Scene Categorization by 3D Hierarchical Histogram Matching. Paritosh Gupta, Sai Sankalp Arrabolu, Mathew Brown and Silvio Savarese.
  • (taken)(2009 PAMI) Supervised Learning of Quantizer Codebooks by Information Loss Minimization. Svetlana Lazebnik, and Maxim Raginsky.
  • (2010 CVPR) Global and Efficient Self-Similarity for Object Classification and Detection. Thomas Deselaers and Vittorio Ferrari.
  • (2008 NIPS) Supervised Dictionary Learning. Julien Mairal1,Francis Bach, Jean Ponce, Guillermo Sapiro, Andrew Zisserman.
  • (2008 CVPR) Discriminative Learned Dictionaries for Local Image Analysis. Julien Mairal1,Francis Bach, Jean Ponce, Guillermo Sapiro, Andrew Zisserman.

Learning Affinities

  • (2009 PAMI) Learning graph matching. Tiberio S. Caetano, Julian J. McAuley?, Li Cheng, Quoc V. Le, and Alex J. Smola.
  • (2010 CVPR) Learning Full Pairwise Affinities for Spectral Segmentation. Tae Hoon Kim Kyoung Mu Lee Sang Uk Lee.

Dimensionality Reduction

  • (2010 CVPR) Parametric Dimensionality Reduction by Unsupervised Regression. Miguel A. Carreira-Perpinan.

Human Pose and Activity Analysis

  • (taken) (2010 CVPR) Monocular 3D Pose Estimation and Tracking by Detection. Mykhaylo Andriluka, Stefan Roth, Bernt Schiele.
  • (2010 CVPR) Learning Shift-Invariant Sparse Representation of Actions. Yi Li, Cornelia Fermuller, and Yiannis Aloimonos, Hui Ji.
  • (2010 PR) Tracking humanpose with multiple activity models. John Darby, Baihua Li,Nicholas Costen.
  • (2009 PAMI) From Canonical Poses to 3–D Motion Capture using a Single Camera. Andrea Fossati, Miodrag Dimitrijevic, Vincent Lepetit, Pascal Fua.

Object Tracking

  • (taken) (2007 CVPR) Learning Features for Tracking. Michael Grabner, Helmut Grabner and Horst Bischof.

Medical Image Applications

  • (2010 PAMI) A Boosting Framework for Visuality-Preserving Distance Metric Learning and Its Application to Medical Image Retrieval. Liu Yang, Rahul Sukthankar and Steven C.H. Hoi.
  • (2007 MICCAI) Active-Contour-Based Image Segmentation using Machine Learning Techniques. Patrick Etyngier, Florent Segonne, and Renaud Keriven.
  • (2010 MEDIA) GRAM a framework for geodesic registration on anatomical manifolds. Jihun Hamma, Dong Hye Yeb, Ragini Vermaa, Christos Davatzikosa.

Image Processing

  • (2010 CVPR) Personalization of Image Enhancement. Sing Bing Kang, Ashish Kapoor, Dani Lischinski.
  • (taken)(2010 SIGGRAPH) Personal Photo Enhancement Using Example Images. N. Joshi, W. Matusik, E. Adelson, D. Kriegman.

Schedule

The seminar consists of a preliminary meeting, an introductory meeting and seminar sessions. Each of the sessions has two 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
25.10.10 16:00 Preliminary Meeting Tutors    
17.01.11  16:00  Random Forest Clustering and Application to Video Segmentation Florian Schulze Olivier Pauly  
  16:30 On-line Random Forest Lukas Rupprecht Olivier Pauly  
24.01.11 16:00 Personal Photo Enhancement Using Example Images Tuğba Halici Diana Mateus  
  17:00 Monocular 3D Pose Estimation and Tracking by Detection Vasileios Belagiannis Loren Schwarz  

TeachingForm
Title: Machine Learning Methods for Computer Vision Applications
Professor: Nassir Navab
Tutors: Diana Mateus; Loren Schwarz; Olivier Pauly
Type: Hauptseminar
Information: Hauptseminar, SWS: 2, ECTS: 4
Term: 2010WiSe
Abstract:  


Edit | Attach | Refresh | Diffs | More | Revision r1.18 - 24 Jan 2011 - 09:40 - LorenSchwarz

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