Navigation

Samuel Schulter

Samuel Schulter


E-Mail schulter(at)icg.tugraz.at
Phone +43 316 873-5035
Office Room E3.11 (IE02120)
Inffeldgasse 16, 2nd floor
8010 Graz, Austria

Contents

| News | Short CV | Publications | Software |

News

September 2015: I successfully defended my PhD (with the title "Loss Minimization for Random Forests in Computer Vision") and I will be joining the Media Analytics group at NEC-Labs in Cupertino, CA as a researcher.
September 2015: Our paper "Conditioned Regression Models for Non-Blind Single Image Super-Resolution" got accepted at ICCV'15.
April 2015: Our CVPR'15 paper got accepted: "Fast and Accurate Image Upscaling with Super-Resolution Forests". Code is also provided, see Software
March 2014: Our paper "Accurate Object Detection with Joint Classification-Regression Random Forests" got accepted for CVPR'14.
September 2013: Our ICCV'13 paper got accepted.
July 2013: Papers accepted at GCPR'13 (DAGM) and BMVC'13.
June 2013: Code for Alternating Decision Forests is online, see Software
March 2013: Our paper "Alternating Decision Forests" got accepted for CVPR'13


Short CV

I received my MSc Degree in Telematics from Graz University of Technology in 2011. I'm currently a PhD student and university assistant at the Institute for Computer Graphics and Vision. My research is focused on Machine Learning, Random Forests, Object Detction & Tracking, and Learning from Videos.

Publications

2016

  1. Interactive 3D Segmentation of Rock-Art by Enhanced Depth Maps and Gradient Preserving Regularization (bib)Matthias Zeppelzauer, Georg Poier, Markus Seidl, Christian Reinbacher, Samuel Schulter, Christian Breiteneder, and Horst Bischof ACM Journal on Computing and Cultural Heritage 9 (4): 19:1-19:30, 2016
    (The original publication is available at http://dx.doi.org/10.1145/2950062)

2015

  1. Conditioned Regression Models for Non-Blind Single Image Super-Resolution (bib)Gernot Riegler, Samuel Schulter, Matthias Rüther, and Horst Bischof In Proc. International Conference on Computer Vision (ICCV), 2015
  2. Hybrid One-Shot 3D Hand Pose Estimation by Exploiting Uncertainties (bib) (project)Georg Poier, Konstantinos Roditakis, Samuel Schulter, Damien Michel, Horst Bischof, and Antonis A. Argyros In Proc. British Machine Vision Conference (BMVC), 2015
    (oral presentation)
  3. Interactive Segmentation of Rock-Art in High-Resolution 3D Reconstructions (bib)Matthias Zeppelzauer, Georg Poier, Markus Seidl, Christian Reinbacher, Christian Breiteneder, Horst Bischof, and Samuel Schulter In Proc. Digital Heritage Conference (DH), 2015
    (oral presentation; winner of the best paper price)
  4. You Should Use Regression to Detect Cells (bib)Philipp Kainz, Martin Urschler, Samuel Schulter, Paul Wohlhart, and Vincent Lepetit In Proceedings of the Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2015
  5. Fast and Accurate Image Upscaling with Super-Resolution Forests (bib)Samuel Schulter, Christian Leistner, and Horst Bischof In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
    (Supplemental Material, Code)

2014

  1. Hough Forests Revisited: An Approach to Multiple Instance Tracking from Multiple Cameras (bib)Georg Poier, Samuel Schulter, Sabine Sternig, Peter M. Roth, and Horst Bischof In Proc. German Conference on Pattern Recognition (GCPR/DAGM), 2014
    (The original publication is available at www.springer.com)
  2. Accurate Object Detection with Joint Classification-Regression Random Forests (bib)Samuel Schulter, Christian Leistner, Paul Wohlhart, Peter M. Roth, and Horst Bischof In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014

2013

  1. Alternating Regression Forests for Object Detection and Pose Estimation (bib)Samuel Schulter, Christian Leistner, Paul Wohlhart, Peter M. Roth, and Horst Bischof In Proc. International Conference on Computer Vision (ICCV), 2013
  2. Unsupervised Object Discovery and Segmentation in Videos (bib)Samuel Schulter, Christian Leistner, Peter M. Roth, and Horst Bischof In Proc. British Machine Vision Conference (BMVC), 2013
  3. Ordinal Random Forests for Object Detection (bib)Samuel Schulter, Peter M. Roth, and Horst Bischof In Proc. German Conference on Pattern Recognition (GCPR/DAGM), 2013
  4. Alternating Decision Forests (bib)Samuel Schulter, Paul Wohlhart, Christian Leistner, Amir Saffari, Peter M. Roth, and Horst Bischof In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013

2012

  1. Discriminative Hough Forests for Object Detection (bib)Paul Wohlhart, Samuel Schulter, Martin Koestinger, Peter M. Roth, and Horst Bischof In Proc. British Machine Vision Conference (BMVC), 2012

2011

  1. OUTLIER -- Online Learning and Visualization of Unusual Events (bib)Josef Birchbauer, Samuel Schulter, Rene Schuster, Georg Poier, Martin Winter, Peter Schallauer, Peter M. Roth, and Horst Bischof In Proc. IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS, Demo Session), 2011
  2. Improving Classifiers with Unlabeled Weakly-Related Videos (bib)Christian Leistner, Martin Godec, Samuel Schulter, Amir Saffari, Manuel Werlberger, and Horst Bischof In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011
  3. On-line Hough Forests (bib)Samuel Schulter, Christian Leistner, Peter M. Roth, Luc Van Gool, and Horst Bischof In Proc. British Machine Vision Conference (BMVC), 2011
  4. Multi-Cue Learning and Visualization of Unusual Events (bib)Rene Schuster, Samuel Schulter, Georg Poier, Martin Hirzer, Josef Birchbauer, Peter M. Roth, Horst Bischof, Martin Winter, and Peter Schallauer In Proc. 11th IEEE Workshop on Visual Surveillance (ICCV), 2011

2015

  1. Loss Minimization for Random Forests in Computer Vision (bib)Samuel Schulter Ph.D. Thesis, Graz University of Technology, Faculty of Computer Science, 2015

2011

  1. A Transformation Invariant Learning Approach for Detection and Tracking using Weakly-Related Videos (bib)Samuel Schulter MSc. Thesis, Graz University of Technology, Faculty of Computer Science, 2011


Software

Fast and Accurate Image Upscaling with Super-Resolution Forests: Code including some data sets (.tar.gz; 24.8MB)
Upon request, I can also provide some pre-trained models (the model files are not included as they are pretty large). However, re-training the models takes little time.
Related Publications:
  1. Fast and Accurate Image Upscaling with Super-Resolution Forests (bib)Samuel Schulter, Christian Leistner, and Horst Bischof In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
    (Supplemental Material, Code)
Alternating Decision and Regression Forests: Code including some data sets (.tar.gz; 36.7MB)
Related Publications:
  1. Alternating Decision Forests (bib)Samuel Schulter, Paul Wohlhart, Christian Leistner, Amir Saffari, Peter M. Roth, and Horst Bischof In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013
  1. Alternating Regression Forests for Object Detection and Pose Estimation (bib)Samuel Schulter, Christian Leistner, Paul Wohlhart, Peter M. Roth, and Horst Bischof In Proc. International Conference on Computer Vision (ICCV), 2013
On-line Hough Forests: Download Code (.zip; 60 kB)
Related Publications:
  1. On-line Hough Forests (bib)Samuel Schulter, Christian Leistner, Peter M. Roth, Luc Van Gool, and Horst Bischof In Proc. British Machine Vision Conference (BMVC), 2011
Video Hough Forests: Download Code (.zip; 380 kB)
Related Publications:
  1. Improving Classifiers with Unlabeled Weakly-Related Videos (bib)Christian Leistner, Martin Godec, Samuel Schulter, Amir Saffari, Manuel Werlberger, and Horst Bischof In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011

Copyright 2010 ICG

Valid XHTML 1.1 Valid CSS