Ryan Walsh

TL;DR: The Visual Object Tracking challenge VOT2016 goes beyond its predecessors by introducing a new semi-automatic ground truth bounding box annotation methodology and extending the evaluation system with the no-reset experiment.

TL;DR: An algorithm is proposed that uses the mean and entropy of this response map to prevent bad target model updates caused by problems such as occlusions and motion blur as well as to determine the size of the target search area.

TL;DR: A hierarchical Bayesian fusion approach is proposed, which outperforms individual trackers by using redundant measurements and relies on each measurement's local statistics and a global softened majority voting.

TL;DR: This work proposes a general hierarchical Bayesian data fusion framework that allows any number of vision-based tracking algorithms to cooperate in the task of estimating the target position and shows that it can significantly improve the performance of individual trackers.