Online Filtering Training Samples for Robust Visual Tracking
MM '20: The 28th ACM International Conference on Multimedia Seattle WA USA October, 2020, pp. 1488-1496, 2020.
In recent years, discriminative trackers show its great tracking performance, that is mainly due to the online updating using samples collected during tracking. The model could adapt appearance changes of objects and the background well after updating. But these trackers have a serious disadvantage that wrong samples may cause severe mode...More
PPT (Upload PPT)