The  Weizmann  Institute  of  Science
                  Faculty of Mathematics and Computer Science

                          Vision and Robotics Seminar

                                  Shai Avidan
                            Interdisciplinary Center

                                 will speak on

                            Support Vector Tracking

Support Vector Tracking (SVT) integrates the Support Vector Machine (SVM)
classifier into an optic-flow based tracker.  Instead of minimizing an
intensity difference function between successive frames, SVT maximizes the SVM
classification score. To account for large motions between successive frames we
build pyramids from the support vectors and use a coarse-to-fine approach in
the classification stage. We show results of using a homogeneous quadratic
polynomial kernel-SVT for vehicle tracking in image sequences.

                      The lecture will take place in the
                     Lecture Hall, Room 1, Ziskind Building
                         on Thursday, November 29, 2001
                                    at noon