Multimodal Interactive Systems
Department of Computer Science
Darmstadt University of Technology

room B106
Tel: +49 6151 16 34 13
Fax: +49 6151 16 41 17
Email: lastname at mis dot tu-darmstadt dot de
http://www.mis.informatik.tu-darmstadt.de/mfritz

Mario Fritz

PhD Candidate in Computer Science

Education

• diploma in computer science: Diplom-Informatiker, University of Erlangen, Germany, 2004

Research Interests:

• categorization
• machine learning
• local features

 

• Paul Schnitzspan: Application of Conditional Random Fields in Computer Vision
• Nikodem Majer: Pictorial Structure based Spatial Models for Object Categorization
• Sandra Ebert: Dirichlet Process Mixture Models for Object Categorization (in progress)
  

My Theses supervised by:

• Barbara Caputo: Categorization by Local Information using Support Vector Machines, diploma thesis performed at CVAP-KTH Stockholm
• Matthias Zobel: 3d Object Tracking using Light-Fields, student thesis performed at LME Erlangen

Previous Work as student assistent of:

• Eric Hayman: material classification by texture
• Elmar Nöth/Heinz Hertlein: speaker identification
• Paul Baggenstoss: class-specific approach
• Jan Buckow: recognition of prosodic features with neuronal networks

• Exercises to Machine Learning 2007
• Exercises to Machine Learning 2005/2006
  
• Seminar: Computer Vison and Machine Learning 2005
  
• Seminar: Machine Learning and Data Mining in Practice 2004/2005
  
• Exercises to Statistical Pattern Recognition 2004/2005

Publications:

• Paul Schnitzspan, Mario Fritz and Bernt Schiele, Hierarchical Support Vector Random Fields: Joint Training to Combine Local and Global Features, To appear in: ECCV'08, Marseille, France
• Tâm Huynh, Mario Fritz and Bernt Schiele. Discovery of Activity Patterns using Topic Models. To appear in UbiComp'08, Seoul, South Korea.
• M. Fritz; B. Schiele: Decomposition, Discovery and Detection of Visual Categories Using Topic Models, accepted at CVPR'08, Anchorage, 2008 (pdf)
  
• E. Seemann; M. Fritz; B. Schiele: Towards Robust Pedestrian Detection in Crowded Image Sequences, CVPR'07, Minneapolis, 2007 (pdf)
  
• M. Fritz; G.-J. Kruijff; B. Schiele: Cross-Modal Learning of Visual Categories using Different Levels of Supervision, ICVS'07, Bielefeld, 2007 (pdf)
  
• M. Fritz; B. Schiele: Towards Unsupervised Discovery of Visual Categories, DAGM'06, Berlin, 2006 (pdf)
  
• M. Fritz; B. Leibe; B. Caputo; B. Schiele: Integrating Representative and Discriminant Models for Object Category Detection, ICCV'05, Beijing, China, 2005 (pdf)
  

• M. Fritz: Categorization by Local Information using Support Vector Machines, diploma thesis, University of Erlangen and CVAP-KTH Stockholm

• E. Hayman; M. Fritz; B. Caputo; J.-O. Eklundh: Material Classification in the Real World, Swedish Symposium on Image Analysis 2004, Uppsala, Sweden

• M. Fritz; E. Hayman; B. Caputo; J.-O. Eklundh: The KTH-TIPS database. Available at http://www.nada.kth.se/cvap/databases/kth-tips

• E. Hayman; B. Caputo; M. Fritz; J.-O. Eklundh: On the Significance of Real-World Conditions for Material Classification, ECCV'04, Prague, Czech Republic

• M. Zobel; M. Fritz; I. Scholz : Object Tracking and Pose Estimation Using Light-Field Object Models, Workshop on Vision, Modeling and Visualization VMV'02, Erlangen, Germany, 2002 (pdf)
  

• M. Fritz: 3-D Objektverfolgung mit Lichtfeldern (3d object tracking using light-fields), student thesis, University of Erlangen , groundTruthVideo.mpg, tracking1.mpg, trackingLiveDemo.mpg

 

Other Interests:

• sports: hiking, mountain biking, volley ball
• music: guitar & (double) bass → http://www.lovelikeanelephant.de
• photography