Dr.-Ing. Michele Fenzi
Michele Fenzi left the Institut für Informationsverabeitung.
Publications and research activities from the time after the departure are not listed here.

I obtained both my bachelor and master degrees in Telecommunications Engineering from the University of Florence, Italy. In 2009, I wrote my master's thesis during a six-month internship at the Center for Advanced Security Research Darmstadt (CASED), Germany. Since September 2010, I have been working towards a PhD degree at the Institut für Informationsverarbeitung.

My main research interest focuses on feature-based pose estimation problems for object classes. I have been researching on methods for finding a continuous solution by relying only on 2D information without using 3D training data or model. I investigated the use of artificial neural networks to model the relation between viewpoint and feature descriptor. Furthermore, I have studied how to apply graph matching techniques to enforce geometrical consistency, as well as Linear Programming to integrate temporal information in this framework. In parallel to my main research track, I am also interested in multiple people tracking problems and video surveillance problems.

My updated profile on Google Scholar.

Research Interest


  • Pose Estimation
  • Object Detection
  • Object Classification
  • Video Surveillance Applications

News


Supervised Theses


  • Sergi Segura Morros, "3D Object Recognition and Pose Estimation using Feature Descriptor Regression in a Bayes' Framework", March-August 2012
Show selected publications only
  • Michele Fenzi, Laura Leal-Taixé, Jörn Ostermann, Tinne Tuytelaars
    Continuous Pose Estimation with a Spatial Ensemble of Fisher Regressors
    IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, December 2015
  • Michele Fenzi, Laura Leal-Taixé, Konrad Schindler, Jörn Ostermann
    Pose Estimation of Object Categories in Videos Using Linear Programming
    IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa Beach, Hawaii, USA, January 2015
  • Michele Fenzi, Jörn Ostermann
    Embedding Geometry in Generative Models for Pose Estimation of Object Categories
    British Machine Vision Conference (BMVC), accepted as oral presentation, Nottingham, United Kingdom, September 2014
  • Michele Fenzi, Nico Mentzer, Guillermo Payá-Vayá, Tu Ngoc Nguyen, Thomas Risse, Holger Blume, Jörn Ostermann
    Automatic Situation Assessment for Event-driven Video Analysis
    IEEE International Conference on Advanced Video Signal-Based Surveillance (AVSS), accepted as oral presentation , Seoul, South Korea, August 2014
  • Laura Leal-Taixé, Michele Fenzi, Alina Kuznetsova, Bodo Rosenhahn, Silvio Savarese
    Learning an Image-based Motion Context for Multiple People Tracking
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, Ohio, USA, June 2014
  • Laura Leal-Taixé, Michele Fenzi, Alina Kuznetsova, Bodo Rosenhahn, Silvio Savarese
    Multi-target tracking with context from interaction feature strings
    SUNw: Scene Understanding Workshop at IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, Ohio, USA, June 2014
  • Michele Fenzi, Laura Leal-Taixé, Bodo Rosenhahn, Jörn Ostermann
    Class Generative Models based on Feature Regression for Pose Estimation of Object Categories
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Portland, Oregon, USA, June 2013
  • Michele Fenzi, Ralf Dragon, Laura Leal-Taixé, Bodo Rosenhahn, Jörn Ostermann
    3D Object Recognition and Pose Estimation for Multiple Objects using Multi-Prioritized RANSAC and Model Updating
    Annual Symposium of the German Association for Pattern Recognition (DAGM), accepted as oral presentation , Graz, Austria, August 2012
  • Ralf Dragon, Michele Fenzi, Wolf Siberski, Bodo Rosenhahn, Jörn Ostermann
    Towards Feature-Based Situation Assessment for Airport Apron Video Surveillance
    Theoretic Foundations of Computer Vision: Outdoor and Large-Scale Real-World Scene Analysis, April 2012
  • Michele Fenzi, Huajian Liu, Martin Steinebach, Roberto Caldelli
    Markov Random Fields Pre-Warping to Prevent Collusion in Image Transaction Watermarking
    IASTED International Conference on Signal Processing, Pattern Recognition and Applications (SPPRA), Best Paper Award, Innsbruck, Austria, February 2010
Other activities