Hauptseminar/Master Seminar:
Machine Learning Methods for Computer Vision Applications
Nassir Navab, Olivier Pauly, 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 See schedule below.
Course Language: English
Announcements
- Introduction information meeting on Thursday 10th May at 11.00 in MI 03.13.010
- The detailed schedule will be announced soon.
- The list of topics is available.
- All participants, please register for the seminar in TUMonline and send a mail to Olivier Pauly () including your name, your birthday, program of study and Matrikelnummer.
- Maximum number of participants: 20
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 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 wont be tolerated. Both handout and presentation have to be done in
English.
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.
Please send a mail to Olivier Pauly () as soon as possible with your preferred topic.
Medical Image Analysis
- (taken) Lee, Hofmann et al.: Learning Similarity Measure for Multi-Modal 3D Image Registration, CVPR (2009)
- Lucchi, Smith et al.a: Supervoxel-Based Segmentation of Mitochondria in EM Image Stacks with Learned Shape Features, TMI (2011)
- (taken) Geremia, Clatz et al.: Spatial Decision Forests for MS Lesion Segmentation in Multi-Channel Magnetic Resonance, Neuroimage (2011)
- (taken) Huh, Ker, Bise et al.: Automated Mitosis Detection of Stem Cell Populations in Phase-Contrast Microscopy Images, IEEE TMI (2011)
- (taken) Zheng, Barbu, Georgescu et al.: Four-Chamber Heart Modeling and Automatic Segmentation for 3D Cardiac CT Volumes using Marginal Space Learning and Steerable Features, IEEE TMI (2008)
- (taken) Montillo, Shotton et al.: Entangled Decision Forests and their Application for Semantic Segmentation of CT Images, IPMI (2011)
- Iglesias, Konukoglu et al.: Combining Generative and Discriminative Models for Semantic Segmentation of CT Scans via Active learning, IPMI (2011)
- (taken) Turetken, Blum et al.: Reconstructing Geometrically Consistent Tree Structures from Noisy Images, MICCAI (2010)
- (taken) Smith, Carleton et al.: Fast Ray Features for Learning Irregular Shapes, ICCV (2009)
- (taken) Kohlberger, Zhang et al.: Automatic Multi-Organ Segmentation Using Learning-based Segmentation and Level Set Optimization, MICCAI (2011)
Dimensionality Reduction
- (taken) Carreira-Perpiñán and Lu: Parametric Dimensionality Reduction by Unsupervised Regression, CVPR (2010)
Image Analysis
- (taken) Kim, Lee and Lee: Learning Full Pairwise Affinities for Spectral Segmentation, CVPR (2010)
- (taken) Alzate and Suykens: Multiway spectral clustering with out-of-sample extensions through weighted kernel PCA, PAMI (2010)
Human Motion Analysis
- Jiang: Human Pose Estimation Using Consistent Max-Covering, ICCV (2009)
- (taken) Darby, Li and Costen: Tracking human pose with multiple activity models, Pattern Recognition (2010)
- Li, Fermuller et al.: Learning Shift-Invariant Sparse Representation of Actions CVPR (2010)
- Urtasun, Fleet, Hertzmann and Fua: Priors for People Tracking from Small Training Sets, ICCV (2005)
- (taken) Tian, Li and Sclaroff: Articulated Pose Estimation in a Learned Smooth Space of Feasible Solutions, CVPR (2005)
- Sigal, Black et al.: Loose-limbed People: Estimating Human Pose and Motion using Non-parametric Belief Propagation, IJCV
- (taken) Freifeld, Weiss et al.: Contour people: A parameterized model of 2D articulated human shape, CVPR (2010)
- (taken) Eichner, Marin-Jimenez et al.: Articulated Human Pose Estimation and Search in (Almost) Unconstrained Still Images, ETH Zurich (2010)
- (taken) Nowozin, Rother et al.: Decision Tree Fields, ICCV (2011)
- (taken) Girshik, Shotton et al.: Efficient Regression of General-Activity Human Poses from Depth Images, ICCV (2011)
- (taken) Kontschieder, Rota Bulo et al.: Structured Class-Labels in Random Forests for Image Labelling, ICCV (2011)
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.
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.
