The Ninth Visual Object Tracking VOT2021 Challenge Results

Matej Kristan, Jiri Matas, Ales Leonardis, Michael Felsberg, Roman Pflugfelder, Joni Kristian Kamarainen, Hyung Jin Chang, Martin Danelljan, Luka Cehovin Zajc, Alan Lukezic, Ondrej Drbohlav, Jani Kapyla, Gustav Hager, Song Yan, Jinyu Yang, Zhongqun Zhang, Gustavo Fernandez, Mohamed Abdelpakey, Goutam Bhat, Llukman CerkeziHakan Cevikalp, Shengyong Chen, Xin Chen, Miao Cheng, Ziyi Cheng, Yu Chen Chiu, Ozgun Cirakman, Yutao Cui, Kenan Dai, Mohana Murali Dasari, Qili Deng, Xingping Dong, Daniel K. Du, Matteo Dunnhofer, Zhen Hua Feng, Zhiyong Feng, Zhihong Fu, Shiming Ge, Rama Krishna Gorthi, Yuzhang Gu, Bilge Gunsel, Qing Guo, Filiz Gurkan, Wencheng Han, Yanyan Huang, Felix Jaremo Lawin, Shang Jhih Jhang, Rongrong Ji, Cheng Jiang, Yingjie Jiang, Felix Juefei-Xu, Yin Jun, Xiao Ke, Fahad Shahbaz Khan, Byeong Hak Kim, Josef Kittler, Xiangyuan Lan, Jun Ha Lee, Bastian Leibe, Hui Li, Jianhua Li, Xianxian Li, Yuezhou Li, Bo Liu, Chang Liu, Jingen Liu, Li Liu, Qingjie Liu, Huchuan Lu, Wei Lu, Jonathon Luiten, Jie Ma, Ziang Ma, Niki Martinel, Christoph Mayer, Alireza Memarmoghadam, Christian Micheloni, Yuzhen Niu, Danda Paudel, Houwen Peng, Shoumeng Qiu, Aravindh Rajiv, Muhammad Rana, Andreas Robinson, Hasan Saribas, Ling Shao, Mohamed Shehata, Furao Shen, Jianbing Shen, Kristian Simonato, Xiaoning Song, Zhangyong Tang, Radu Timofte, Philip Torr, Chi Yi Tsai, Bedirhan Uzun, Luc Van Gool, Paul Voigtlaender, Dong Wang, Guangting Wang, Liangliang Wang, Lijun Wang, Limin Wang, Linyuan Wang, Yong Wang, Yunhong Wang, Chenyan Wu, Gangshan Wu, Xiao Jun Wu, Fei Xie, Tianyang Xu, Xiang Xu, Wanli Xue, Bin Yan, Wankou Yang, Xiaoyun Yang, Yu Ye, Jun Yin, Chengwei Zhang, Chunhui Zhang, Haitao Zhang, Kaihua Zhang, Kangkai Zhang, Xiaohan Zhang, Xiaolin Zhang, Xinyu Zhang, Zhibin Zhang, Shaochuan Zhao, Ming Zhen, Bineng Zhong, Jiawen Zhu, Xue Feng Zhu

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

79 Citations (Scopus)

Abstract

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 computer 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 tracking in RGB, (iii) VOT-LT2021 focused on long-term tracking, namely coping with target disappearance and reappearance and (iv) VOT-RGBD2021 challenge focused on long-term tracking in RGB and depth imagery. The VOT-ST2021 dataset was refreshed, while VOT-RGBD2021 introduces a training dataset and sequestered dataset for winner 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 website1.

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2711-2738
Number of pages28
ISBN (Electronic)9781665401913
DOIs
Publication statusPublished - 2021
Event18th IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021 - Virtual, Online, Canada
Duration: 11 Oct 202117 Oct 2021

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
Volume2021-October
ISSN (Print)1550-5499

Conference

Conference18th IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021
Country/TerritoryCanada
CityVirtual, Online
Period11/10/2117/10/21

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Funding

This work was supported in part by the following research programs and projects: Slovenian research agency research program P2-0214 and projects J2-2506, J2-9433, Z2-1866. The challenge was sponsored by the Faculty of Computer Science, University of Ljubljana, Slovenia. This work was partially supported by the Wallenberg AI, Autonomous Systems and Software Program (WASP) and the Berzelius cluster at NSC, both funded by the Knut and Alice Wallenberg Foundation, as well as by ELLIIT, a strategic research environment funded by the Swedish government and Institute of Information and communications Technology Planning and evaluation (IITP) grant funded by the Korea government (MSIT) (2021-0-00537). Roman Pflugfelder and Gustavo Fernández were supported by the AIT Strategic Research Programme 2021 Visual Surveillance and Insight. Paul Voigtlaender, Jonathon Luiten and Bastian Leibe were supported by ERC Consolidator Grant DeeViSe (ERC-2017-COG-773161) and a Google Faculty Award.

FundersFunder number
ELLIIT
Faculty of Computer Science, University of Ljubljana
Institute of Information and communications Technology Planning
Slovenian research agency research programJ2-9433, P2-0214, Z2-1866, J2-2506
Swedish government
Google
Ashikaga Institute of TechnologyERC-2017-COG-773161
National Science Council
Knut och Alice Wallenbergs Stiftelse
Institute for Information and Communications Technology Promotion
Ministry of Science and ICT, South Korea2021-0-00537

    Fingerprint

    Dive into the research topics of 'The Ninth Visual Object Tracking VOT2021 Challenge Results'. Together they form a unique fingerprint.

    Cite this