We propose a new long-term tracking performance evaluation methodology and present a new challenging dataset of carefully selected sequences with many target disappearances. We perform an extensive evaluation of six long-term and nine short-term state-of-the-art trackers, using new performance measures, suitable for evaluating long-term tracking - tracking precision, recall and F-score. The evaluation shows that a good model update strategy and the capability of image-wide re-detection are critical for long-term tracking performance. We integrated the methodology in the VOT toolkit to automate experimental analysis and benchmarking and to facilitate the development of long-term trackers.
@article{arxiv.1804.07056,
title = {Now you see me: evaluating performance in long-term visual tracking},
author = {Alan Lukežič and Luka Čehovin Zajc and Tomáš Vojíř and Jiří Matas and Matej Kristan},
journal= {arXiv preprint arXiv:1804.07056},
year = {2018}
}