Hauptseminar/Master Seminar:
Machine Learning Methods for Computer Vision Applications
Nassir Navab, Diana Mateus, Loren Schwarz, Olivier Pauly
Type: Advanced Seminar Course
Module IN8901
Type: Master Seminar
Module IN2107
Type: Seminar
Module IN0014
SWS: 2+0
ECTS: 4 Credits
Time/Location: Mondays (selected dates), 16:00-18:00,
MI 03.13.010
Course Language: English
Announcements
- Attention: on June 28, the seminar will take place in room MI 01.06.011 due to a collision with another event at our regular seminar room.
- All participants, please register for the seminar in TUMonline during this or next week.
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:
- Submit a written handout (8 pages maximum). Please download the llncs2e.zip latex format.
- Attend all seminar sessions and participate.
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
Loren Schwarz (), including your paper choice, your name, your birthday, program of study and Matrikelnummer.
Registration is closed!
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.
Dimensionality Reduction
- (taken) Carreira-Perpinan and Lu: Dimensionality Reduction by Unsupervised Regression, CVPR (2008)
- (taken) Hadsell, Chopra and Lecun: Dimensionality Reduction by Learning an Invariant Mapping, CVPR (2006)
- Frey and Dueck: Clustering by Passing Messages Between Data Points, Science (2007)
- Konolige, Bowman, Chen, Mihelich, Calonder, Lepetit and Fua: View-Based Maps, Proc. Rob. Sc. Sys
- Lu, Bi, Yu, Peng, Krishnan and Zhou: Hierarchical Learning for Tubular Structure Parsing in Medical Imaging: A Study on Coronary Arteries Using 3D CV Angiography, ICCV (2009)
- Ramanan and Baker: Local Distance Functions: A Taxonomy, New Algorithms and an Evaluation, CVPR (2009)
- (taken) Talwalkar, Kumar and Rowley: Large-Scale Manifold Learning, CVPR (2009)
Metric Learning
- (taken) Caetano, Mcauley, Cheng, Le and Smola: Learning Graph Matching, PAMI (2009)
- (taken) Nguyen and de la Torre: Metric Learning for Image Alignment, IJCV (2009)
Image Processing
- (taken) Duchenne, Audibert, Keriven, Ponce and Ségonne: Segmentation by Transduction, CVPR (2008)
- (taken) Glasner, Bagon and Irani: Super-Resolution from a Single Image, ICCV (2009)
- (taken) Takeda, Farsiu and Milanfar: Kernel Regression for Image Processing and Reconstruction, IEEE TIP (2007)
Object Recognition
- (taken) Calonder, Lepetit and Fua: Keypoint Signatures for Fast Learning and Recognition, ECCV (2008)
- Chin, Wang and Suter: Robust Fitting of Multiple Structures: The Statistical Learning Approach, ICCV (2009)
- Jurie and Triggs: Creating Efficient Codebooks for Visual Recognition, ICCV (2005)
- (taken) Leistner, Saffari, Santner and Bischof: Semi-Supervised Random Forests, ICCV (2009)
- (taken) Özuysal, Calonder, Lepetit and Fua: Fast Keypoint Recognition using Random Ferns, PAMI (2009)
Object Tracking
- (taken) Jurie and Dhome: Hyperplane Approximation for Template Matching, PAMI (2002)
- Lepetit and Fua: Keypoint Recognition using Randomized Trees, PAMI (2006)
- Kokkinos and Yuille: Unsupervised Learning of Object Deformation Models, ICCV (2007)
- Reiterer, Lehmann, Miljanovic, Ali, Paar, Egly, Eiter and Kahmen: A 3D Optical Deformation Measurement System Supported by Knowledge-Based and Learning Techniques, JAG (2009)
- (taken) Salzmann, Urtasun and Fua: Local Deformation Models for Monocular 3D Shape Recovery, CVPR (2008)
Human Recognition
- (taken) Duchenne, Laptev, Sivic, Bach and Ponce: Automatic Annotation of Human Actions in Video, ICCV (2009)
- (taken) Guillaumin, Verbeek and Schmid: Is that you? Learning Approaches for Face Identification, CVPR (2009)
- Turaga, Chellappa, Subrahmanian and Udrea: Machine Recognition of Human Activities: A Survey, IEEE TCSVT (2008)
Human Tracking
- Agarwal and Triggs: Recovering 3D Human Pose from Monocular Images, PAMI (2006)
- (taken) Jaeggli, Koller-Meier and Van Gool: Learning Generative Models for Multi-Activity Body Pose Estimation, IJCV (2009)
- (taken) Poppe: Vision-based Human Motion Analysis: An Overview, CVIU (2007)
- (taken) Grochow, Martin, Hertzmann and Popovic: Style-Based Inverse Kinematics, ACM TOG (2004)
- Lu, Carreira-Perpinan and Sminchisescu: People Tracking with the Laplacian Eigenmaps Latent Variable Model, NIPS (2007)
- Sun, Bray, Thayananthan, Yuan and Torr: Regression-Based Human Motion Capture from Voxel Data, BMVC (2006)
- Tian, Li and Sclaroff: Articulated Pose Estimation in a Learned Smooth Space of Feasible Solutions, CVPRW (2005)
- Urtasun, Fleet, Hertzmann and Fua: Priors for People Tracking from Small Training Sets, ICCV (2005)
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.