Program
| 09:30 - 09:45 |
Welcome and Opening Helmut Grabner, and Fatih Porikli |
|
| . | ||
| Session 1: Theory (On-line Boosting) | ||
| . | ||
| 09:45 - 10:10 |
A Family
of Online Boosting Algorithms Boris Babenko, Ming-Hsuan Yang, and Serge Belongie |
|
| 10:10 - 10:35 |
Online
Coordinate Boosting Raphael Pelossof, Michael Jones, Ilia Vovsha, Cynthia Rudin |
|
| 10:35 - 11:00 |
On Robustness of On-line Boosting
- A Competitive Study Christian Leistner, Amir Saffari, Peter M. Roth, and Horst Bischof |
|
| . | ||
| 11:00 - 11:30 | Coffee Break | |
| . | ||
| Session 2: Active Learning | ||
| . | ||
| 11:30 - 11:55 |
Inter-Active
Learning of Randomized Tree Ensembles for Object Detection Thomas J. Fuchs, and Joachim M. Buhmann |
|
| 11:55 - 12:20 |
Generalized
Query by Transduction for Online Active Learning Vineeth Balasubramanian, Shayok Chakraborty, and Sethuraman Panchanathan |
|
| . | ||
| 12:20 - 14:00 | Lunch Break | |
| . | ||
| 14:00 - 14:45 |
Invited Talk Visipedia and Implications for On-line Learning Pietro Perona |
|
| . | ||
| Session 3: Tracking I | ||
| . | ||
| 14:45 - 15:10 |
Online
Learning of Robust Facial Feature Trackers Tim Sheerman-Chase, Eng-Jon Ong, and Richard Bowden |
|
| 15:10 - 15:35 |
On-line
Random Forests for Visual Tracking Amir Saffari, Christian Leistner, and Horst Bischof |
|
| . | ||
| 15:35 - 16:05 | Coffee Break | |
| . | ||
| Session 4: Tracking II | ||
| . | ||
| 16:05 - 16:30 |
Combining
Online and Offline Learning for Tracking a Talking Face in Video Quoc Dinh Nguyen, and Maurice Milgram |
|
| 16:30 - 16:55 |
Beyond
Semi-Supervised Tracking: Detection Should Be as Simple as Tracking,
but not Simpler than Recognition Severin Stalder, Helmut Grabner, and Luc Van Gool |
|
| 16:55 - 17:20 |
Online
learning of robust object detectors during unstable tracking Zdenek Kalal, Krystian Mikolajczyk, and Jiri Matas |
|
| . | ||
| 17:20
- 17:45 |
Closing
and Discussion Helmut Grabner, and Fatih Porikli |
|
Invited Speaker
Pietro
Perona
Vision Group-Vision Laboratory
California Institute of Technology (CALTECH)
http://www.vision.caltech.edu/Perona.html
Title: Visipedia and implications for on-line learning
Pietro Perona graduated in electrical engineering from the Universita di Padova in 1985. He received the PhD degree from the University of California at Berkeley in 1990. He was a postdoctoral fellow at the Laboratory for Information and Decision Systems at MIT in 1990-1991 and became an assistant professor of electrical engineering at the California Institute of Technology in 1991. In 1996, he became professor of electrical engineering and of computation and neural systems. Since 1999, he has been the director of the National Science Foundation Engineering Research Center in Neuromorphic Systems Engineering at Caltech. He has served on the editorial board of the International Journal of Machine Vision, the Journal of Machine Learning Research, Vision Research, and as co-general chair of the IEEE Conference of Computer Vision and Pattern Recognition (CVPR 2003).
He is interested in the computational aspects of vision; his current research focus is visual recognition. He has worked on PDEs for image analysis and segmentation (anisotropic diffusion), multiresolution-multiorientation filtering for early vision, human texture perception and segmentation, dynamic vision, grouping, detection and analysis of human motion, human perception of 3D shape from shading, learning and recognition of object categories, human categorization of scenes, interaction of attention, and recognition. He is a member of the IEEE.
Vision Group-Vision Laboratory
California Institute of Technology (CALTECH)
http://www.vision.caltech.edu/Perona.html
Title: Visipedia and implications for on-line learning
Pietro Perona graduated in electrical engineering from the Universita di Padova in 1985. He received the PhD degree from the University of California at Berkeley in 1990. He was a postdoctoral fellow at the Laboratory for Information and Decision Systems at MIT in 1990-1991 and became an assistant professor of electrical engineering at the California Institute of Technology in 1991. In 1996, he became professor of electrical engineering and of computation and neural systems. Since 1999, he has been the director of the National Science Foundation Engineering Research Center in Neuromorphic Systems Engineering at Caltech. He has served on the editorial board of the International Journal of Machine Vision, the Journal of Machine Learning Research, Vision Research, and as co-general chair of the IEEE Conference of Computer Vision and Pattern Recognition (CVPR 2003).
He is interested in the computational aspects of vision; his current research focus is visual recognition. He has worked on PDEs for image analysis and segmentation (anisotropic diffusion), multiresolution-multiorientation filtering for early vision, human texture perception and segmentation, dynamic vision, grouping, detection and analysis of human motion, human perception of 3D shape from shading, learning and recognition of object categories, human categorization of scenes, interaction of attention, and recognition. He is a member of the IEEE.
Acceptance Rate
- We have received 22 high quality papers out of which we have selected 10 for oral presentation. This correspond to an acceptance rate of 45%.