On this page
Jan Sochman
- Research Fellow at the Computer Vision Group, University of Leeds
- 2005-2009 Research Fellow, Centre for Machine Perception, Czech Technical University
- 2002-2009 PhD candidate, Centre for Machine Perception, Czech Technical University
Research interests: Learning for sequential classification, boosting, object detection, online learning, activity analysis.
Currently involved in the SUBITO project.
Contact:
Selected publications
Updated 02.2010
J. Sochman, Learning for Sequential
Classification, PhD thesis, 2009.
[
PDF]
J. Sochman and J. Matas, Learning Fast Emulators of Binary
Decision Processes, IJCV 2009.
[ PDF]
[BibTeX]
H. Grabner, J. Sochman, H. Bischof, and
J. Matas, Training
Sequential On-line Boosting Classifier for Visual Tracking, ICPR 2008.
[ PDF]
[BibTeX]
J. Sochman and
J. Matas, Learning
A Fast Emulator of a Binary Decision Process, ACCV
2007.
(This article obtained Best paper award)
[ PDF]
[BibTeX]
J. Sochman and J. Matas, WaldBoost -- Learning for Time
Constrained Sequential Detection, CVPR 2005.
[ PDF]
[BibTeX]
J. Sochman and
J. Matas, Inter-stage Feature Propagation in Cascade Building
with AdaBoost, ICPR 2004.
[PS.GZ]
[BibTeX]
J. Sochman and
J. Matas, AdaBoost
with Totally Corrective Updates for Fast Face Detection, FGR
2004.
[ PDF]
[BibTeX]
Other resources
Updated 02.2010
WaldBoost talk, November 2009
AdaBoost talk, last update 2008
WaldBoost-based face detection demo
Tales page (mostly in Czech)