作者
Matej Kristan, Jiří Matas, Aleš Leonardis, Michael Felsberg, Roman Pflugfelder, Joni-Kristian Kämäräinen, Hyung Jin Chang, Martin Danelljan, Luka Cehovin, Alan Lukežič, Ondrej Drbohlav, Jani Käpylä, Gustav Häger, Song Yan, Jinyu Yang, Zhongqun Zhang, Gustavo Fernández
发表日期
2021
研讨会论文
Proceedings of the IEEE/CVF international conference on computer vision
页码范围
2711-2738
简介
The Visual Object Tracking challenge VOT2021 is the ninth annual tracker benchmarking activity organized by the VOT initiative. Results of 71 trackers are presented; many are state-of-the-art trackers published at major com-puter vision conferences or in journals in recent years. The VOT2021 challenge was composed of four sub-challenges focusing on different tracking domains:(i) VOT-ST2021 challenge focused on short-term tracking in RGB,(ii) VOT-RT2021 challenge focused on" real-time" short-term track-ing in RGB,(iii) VOT-LT2021 focused on long-term track-ing, namely coping with target disappearance and reap-pearance and (iv) VOT-RGBD2021 challenge focused on long-term tracking in RGB and depth imagery. The VOT-ST2021 dataset was refreshed, while VOT-RGBD2021 in-troduces a training dataset and sequestered dataset for win-ner identification. The source code for most of the trackers, the datasets, the evaluation kit and the results along with the source code for most trackers are publicly available at the challenge website.
引用总数
学术搜索中的文章
M Kristan, J Matas, A Leonardis, M Felsberg… - Proceedings of the IEEE/CVF international conference …, 2021