CUED Publications database

The Visual Object Tracking VOT2017 Challenge Results

Kristan, M and Leonardis, A and Matas, J and Felsberg, M and Pflugfelder, R and Zajc, LČ and Vojír, T and Häger, G and Lukežič, A and Eldesokey, A and Fernández, G and García-Martín, Á and Muhic, A and Petrosino, A and Memarmoghadam, A and Vedaldi, A and Manzanera, A and Tran, A and Alatan, A and Mocanu, B and Chen, B and Huang, C and Xu, C and Sun, C and Du, D and Zhang, D and Du, D and Mishra, D and Gundogdu, E and Velasco-Salido, E and Khan, FS and Battistone, F and Subrahmanyam, GRKS and Bhat, G and Huang, G and Bastos, G and Seetharaman, G and Zhang, H and Li, H and Lu, H and Drummond, I and Valmadre, J and Jeong, JC and Cho, JI and Lee, JY and Noskova, J and Zhu, J and Gao, J and Liu, J and Kim, JW and Henriques, JF and Martínez, JM and Zhuang, J and Xing, J and Gao, J and Chen, K and Palaniappan, K and Lebeda, K and Gao, K and Kitani, KM and Zhang, L and Wang, L and Yang, L and Wen, L and Bertinetto, L and Poostchi, M and Danelljan, M and Mueller, M and Zhang, M and Yang, MH and Xie, N and Wang, N and Miksik, O and Moallem, P and Pallavi Venugopal, M and Senna, P and Torr, PHS and Wang, Q and Yu, Q and Huang, Q and Martín-Nieto, R and Bowden, R and Liu, R and Tapu, R and Hadfield, S and Lyu, S and Golodetz, S and Choi, S and Zhang, T and Zaharia, T and Santopietro, V and Zou, W and Hu, W and Tao, W and Li, W and Zhou, W and Yu, X and Bian, X and Li, Y and Xing, Y (2017) The Visual Object Tracking VOT2017 Challenge Results. In: UNSPECIFIED pp. 1949-1972..

Full text not available from this repository.

Abstract

The Visual Object Tracking challenge VOT2017 is the fifth annual tracker benchmarking activity organized by the VOT initiative. Results of 51 trackers are presented; many are state-of-the-art published at major computer vision conferences or journals in recent years. The evaluation included the standard VOT and other popular methodologies and a new 'real-time' experiment simulating a situation where a tracker processes images as if provided by a continuously running sensor. Performance of the tested trackers typically by far exceeds standard baselines. The source code for most of the trackers is publicly available from the VOT page. The VOT2017 goes beyond its predecessors by (i) improving the VOT public dataset and introducing a separate VOT2017 sequestered dataset, (ii) introducing a realtime tracking experiment and (iii) releasing a redesigned toolkit that supports complex experiments. The dataset, the evaluation kit and the results are publicly available at the challenge website1.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Subjects: UNSPECIFIED
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 27 Feb 2019 20:25
Last Modified: 15 Apr 2021 06:56
DOI: 10.1109/ICCVW.2017.230