Enhanced MIL tracker with distribution field-based features and temporal fusion framework

A new tracker based on multiple instance learning (MIL) with distribution field (DF)-based features and a novel temporal fusion framework is presented. DF-based features make the representations less sensitive to the object´s appearance variation. In addition, the tracker introduces a new temporal fusion framework based on the randomised policy, aiming at adding robustness against outliers during the tracking. Experimental results on challenging video sequences show the effectiveness of the proposed method.