This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Search for Publication

Year(s) from:  to 
Keywords (separated by spaces):

Appearances Can Be Deceiving: Learning Visual Tracking from Few Trajectory Annotations

Santiago Manen, Junseok Kwon, Matthieu Guillaumin, Luc Van Gool
European Conference on Computer Vision


Visual tracking is the task of estimating the trajectory of an object in a video given its initial location. This is usually done by combining at each step an appearance and a motion model. In this work, we learn from a small set of training trajectory annotations how the objects in the scene typically move. We learn the relative weight between the appearance and the motion model. We call this weight: visual deceptiveness. At test time, we transfer the deceptiveness and the displacement from the closest trajectory annotation to infer the next location of the object. Further, we condition the transference on an event model. On a set of 161 manually annotated test trajectories, we show in our experiments that learning from just 10 trajectory annotations halves the center location error and improves the success rate by about 10%.

Download in pdf format
  author = {Santiago Manen and Junseok Kwon and Matthieu Guillaumin and Luc Van Gool},
  title = {Appearances Can Be Deceiving: Learning Visual Tracking from Few Trajectory Annotations},
  booktitle = {European Conference on Computer Vision},
  year = {2014},
  keywords = {Visual tracking, Motion learning, Event modelling}