학술논문
The First Visual Object Tracking Segmentation VOTS2023 Challenge Results
Document Type
Author
Kristan, Matej; Matas, Jiri; Danelljan, Martin; Felsberg, Michael; Chang, Hyung Jin; Zajc, Luka Cehovin; Lukezic, Alan; Drbohlav, Ondrej; Zhang, Zhongqun; Tran, Khanh-Tung; Vu, Xuan-Son; Bjorklund, Johanna; Mayer, Christoph; Zhang, Yushan; Ke, Lei; Zhao, Jie; Fernandez, Gustavo; Al-Shakarji, Noor; An, Dong; Arens, Michael; Becker, Stefan; Bhat, Goutam; Bullinger, Sebastian; Chan, Antoni B.; Chang, Shijie; Chen, Hanyuan; Chen, Xin; Chen, Yan; Chen, Zhenyu; Cheng, Yangming; Cui, Yutao; Deng, Chunyuan; Dong, Jiahua; Dunnhofer, Matteo; Feng, Wei; Fu, Jianlong; Gao, Jie; Han, Ruize; Hao, Zeqi; He, Jun-Yan; He, Keji; He, Zhenyu; Hu, Xiantao; Huang, Kaer; Huang, Yuqing; Jiang, Yi; Kang, Ben; Lan, Jin-Peng; Lee, Hyungjun; Li, Chenyang; Li, Jiahao; Li, Ning; Li, Wangkai; Li, Xiaodi; Li, Xin; Liu, Pengyu; Liu, Yue; Lu, Huchuan; Luo, Bin; Luo, Ping; Ma, Yinchao; Miao, Deshui; Micheloni, Christian; Palaniappan, Kannappan; Park, Hancheol; Paul, Matthieu; Peng, HouWen; Qian, Zekun; Rahmon, Gani; Scherer-Negenborn, Norbert; Shao, Pengcheng; Shin, Wooksu; Kazemi, Elham Soltani; Song, Tianhui; Stiefelhagen, Rainer; Sun, Rui; Tang, Chuanming; Tang, Zhangyong; Toubal, Imad Eddine; Valmadre, Jack; van de Weijer, Joost; Van Gool, Luc; Vira, Jash; Vujasinovic, Stephane; Wan, Cheng; Wan, Jia; Wang, Dong; Wang, Fei; Wang, Feifan; Wang, He; Wang, Limin; Wang, Song; Wang, Yaowei; Wang, Zhepeng; Wu, Gangshan; Wu, Jiannan; Wu, Qiangqiang; Wu, Xiaojun; Xiao, Anqi; Xie, Jinxia; Xu, Chenlong; Xu, Min; Xu, Tianyang; Xu, Yuanyou; Yan, Bin; Yang, Dawei; Yang, Ming-Hsuan; Yang, Tianyu; Yang, Yi; Yang, Zongxin; Yin, Xuanwu; Yu, Fisher; Yu, Hongyuan; Yu, Qianjin; Yu, Weichen; Yuan, YongSheng; Yuan, Zehuan; Zhang, Jianlin; Zhang, Lu; Zhang, Tianzhu; Zhao, Guodongfang; Zhao, Shaochuan; Zheng, Yaozong; Zhong, Bineng; Zhu, Jiawen; Zhu, Xuefeng; Zhuang, Yueting; Zong, ChengAo; Zuo, Kunlong
Source
2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS, ICCVW IEEE International Conference on Computer Vision Workshops. :1788-1810
Subject
Language
English
ISSN
2473-9936
2473-9944
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).