TeachingSoSe2014MLCVSeminar

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

Hauptseminar/Master Seminar:
Machine Learning Methods for Computer Vision

Nassir Navab, Loic Peter, Slobodan Ilic, Vasilis Belagiannis, Joé Lallemand, David Tan, Vladimir Haltakov

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

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.

Registration

Registration is closed.

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
27.01.2014 13:00 - 14:00 First Information Meeting Tutors    
14.04.2014 13:00 - 14:00 Introduction Meeting Tutors   Slides
26.05.2014 13:00 - 15:00 Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images

Human Pose Estimation using Body Parts Dependent Joint Regressors
Korbinian Würl

Clemens Stukenbrock
David

Vasilis
 
02.06.2014 13:00 - 15:00 Alternating Regression Forests for Object Detection and Pose Estimation

Deeppose: Human Pose Estimation via Deep Neural Networks
Marcel Schumacher

Mai Ton Nu Cam
David

Vasilis
 
16.06.2014 13:00 - 15:00 Imagenet Classification with Deep Convolutional Neural Networks

Pedestrian Detection with Unsupervised Multi-Stage Feature Learning
Kilian Batzner

Amin Ahantab
Vladimir

Vladimir
 
23.06.2014 13:00 - 15:00 Random Forests of Local Experts for Pedestrian Detection

Cosegmentation and Cosketch by Unsupervised Learning
Isnani Pramusinto

Albert Steckermeier
Joé

Loic
 
30.06.2014 13:00 - 15:00 Metric Regression Forests for Human Pose Estimation

Multi-stage Contextual Deep Learning for Pedestrian Detection
Jonathan Aldag

Jonas Uhrig
Joé

Joé
 
07.07.2014 13:00 - 15:00 Boosting Binary Keypoint Descriptors 

Towards Understanding Action Recognition
Sabahattin Giritli

Sebastian Tschöpel
Slobodan

Slobodan
 
14.07.2014 13:00 - 15:00 Unsupervised Visual Domain Adaptation Using Subspace Alignment

Domain Adaptive Classification
Sebastian Lerch

Richeek Swami
Loic

Loic
 


List of Papers

* Boosting Binary Keypoint Descriptors , Trzcinski et al, CVPR 2013

* Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images , Shotton et al, CVPR 2013

* Human Pose Estimation using Body Parts Dependent Joint Regressors , Dantone et al, CVPR 2013

* Random Forests of Local Experts for Pedestrian Detection , Marin et al, ICCV 2013

* Alternating Regression Forests for Object Detection and Pose Estimation , Schulter et al, ICCV 2013

* Domain Adaptive Classification , Mirrashed et al, ICCV 2013

* Cosegmentation and Cosketch by Unsupervised Learning , Dai et al, ICCV 2013

* Metric Regression Forests for Human Pose Estimation , Pons-Moll et al, BMVC 2013

* Deeppose: Human Pose Estimation via Deep Neural Networks , Toshev et al, arXiV / CVPR 2014

* Imagenet Classification with Deep Convolutional Neural Networks , Krizhevsky et al, NIPS 2012

* Unsupervised Visual Domain Adaptation Using Subspace Alignment , Fernando et al, ICCV 2013

* Towards Understanding Action Recognition , Jhuang et al, ICCV 2013

* Multi-stage Contextual Deep Learning for Pedestrian Detection , Zeng et al, ICCV 2013

* Pedestrian Detection with Unsupervised Multi-Stage Feature Learning , Sermanet et al, CVPR 2013



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 for Computer Vision
Professor: Nassir Navab
Tutors: Loic Peter, Slobodan Ilic, Vasilis Belagiannis, Joé Lallemand, David Tan, Vladimir Haltakov
Type: Hauptseminar
Information: Hauptseminar, SWS: 2, ECTS: 4
Term: 2014SoSe
Abstract:  


Edit | Attach | Refresh | Diffs | More | Revision r1.23 - 12 Jun 2014 - 09:28 - LoicPeter

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