학술논문
The First Visual Object Tracking Segmentation VOTS2023 Challenge Results
Document Type
Conference
Author
Kristan, M.; Matas, J.; Danelljan, M.; Felsberg, M.; Chang, H.J.; Cehovin Zajc, L.; Lukezic, A.; Drbohlav, O.; Zhang, Z.; Tran, K.-T.; Vu, X.-S.; Bjorklund, J.; Mayer, C.; Zhang, Y.; Ke, L.; Zhao, J.; Fernandez, G.; Al-Shakarji, N.; An, D.; Arens, M.; Becker, S.; Bhat, G.; Bullinger, S.; Chan, A.B.; Chang, S.; Chen, H.; Chen, X.; Chen, Y.; Chen, Z.; Cheng, Y.; Cui, Y.; Deng, C.; Dong, J.; Dunnhofer, M.; Feng, W.; Fu, J.; Gao, J.; Han, R.; Hao, Z.; He, J.-Y.; He, K.; He, Z.; Hu, X.; Huang, K.; Huang, Y.; Jiang, Y.; Kang, B.; Lan, J.-P.; Lee, H.; Li, C.; Li, J.; Li, N.; Li, W.; Li, X.; Liu, P.; Liu, Y.; Lu, H.; Luo, B.; Luo, P.; Ma, Y.; Miao, D.; Micheloni, C.; Palaniappan, K.; Park, H.; Paul, M.; Peng, H.; Qian, Z.; Rahmon, G.; Scherer-Negenborn, N.; Shao, P.; Shin, W.; Kazemi, E.S.; Song, T.; Stiefelhagen, R.; Sun, R.; Tang, C.; Tang, Z.; Toubal, I.E.; Valmadre, J.; Van de Weijer, J.; Van Gool, L.; Vira, J.; Vujasinovic, S.; Wan, C.; Wan, J.; Wang, D.; Wang, F.; Wang, H.; Wang, L.; Wang, S.; Wang, Y.; Wang, Z.; Wu, G.; Wu, J.; Wu, Q.; Wu, X.; Xiao, A.; Xie, J.; Xu, C.; Xu, M.; Xu, T.; Xu, Y.; Yan, B.; Yang, D.; Yang, M.-H.; Yang, T.; Yang, Y.; Yang, Z.; Yin, X.; Yu, F.; Yu, H.; Yu, Q.; Yu, W.; Yuan, Y.; Yuan, Z.; Zhang, J.; Zhang, L.; Zhang, T.; Zhao, G.; Zhao, S.; Zheng, Y.; Zhong, B.; Zhu, J.; Zhu, X.; Zhuang, Y.; Zong, C.; Zuo, K.
Source
2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) ICCVW Computer Vision Workshops (ICCVW), 2023 IEEE/CVF International Conference on. :1788-1810 Oct, 2023
Subject
Language
ISSN
2473-9944
Abstract
The Visual Object Tracking Segmentation VOTS2023 challenge is the eleventh annual tracker benchmarking activity of the VOT initiative. This challenge is the first to merge short-term and long-term as well as single-target and multiple-target tracking with segmentation masks as the only target location specification. A new dataset was created; the ground truth has been withheld to prevent overfitting. New performance measures and evaluation protocols have been created along with a new toolkit and an evaluation server. Results of the presented 47 trackers indicate that modern tracking frameworks are well-suited to deal with convergence of short-term and long-term tracking and that multiple and single target tracking can be considered a single problem. A leaderboard, with participating trackers details, the source code, the datasets, and the evaluation kit are publicly available at the challenge website 1 .