PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

FlowBoost - Appearance Learning from Sparsely Annotated Video
Karim Ali, David Hasler and Francois Fleuret
In: CVPR 2011(2011).


We propose a new learning method which exploits temporal consistency to successfully learn a complex appearance model from a sparsely labeled training video. Our approach consists in iteratively improving an appearance-based model, built with a Boosting procedure, and the reconstruction of trajectories corresponding to the motion of multiple targets throughout the video sequence. We demonstrate the efficiency of such a procedure on both pedestrian detection in videos and cell detection in microscopic images. In both cases, our method is demonstrated to reduce the labeling requirement by one to two orders of magnitude. Surprisingly, we show that in some cases, our method trained with sparse labels on a video sequence is able to outperform a standard learning procedure trained with the fully labeled sequence.

EPrint Type:Conference or Workshop Item (Oral)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:7325
Deposited By:Francois Fleuret
Deposited On:17 March 2011