TY - GEN
T1 - The Second Visual Object Tracking Segmentation VOTS2024 Challenge Results
AU - 94 authors, including
AU - Kristan, Matej
AU - Chang, Hyung Jin
AU - Fernández, Gustavo
AU - Attari, Minasadat
AU - Chan, Antoni
AU - Chen, Liang
AU - Chen, Xin
AU - Collins, Jaired
AU - Cui, Yutao
AU - Devarapu, Ganesh Sai Manas
AU - Du, Yinglong
AU - Matas, Jiir
AU - Fan, Heng
AU - Fan, Wan-Cyuan
AU - Feng, Zhenhua
AU - Gao, Mingqi
AU - Gorthi, Rama Krishna Sai
AU - Goyal, Raghav
AU - Han, Jungong
AU - Hatuwal, Bijaya
AU - He, Zhenyu
AU - Hu, Xiantao
AU - Tokmakov, Pavel
AU - Huang, Xingsen
AU - Huang, Yuqing
AU - Jiang, Dongmei
AU - Kang, Ben
AU - Kannappan, Palaniappan
AU - Kittler, Josef
AU - Lai, Simiao
AU - Li, Ning
AU - Li, Xiaohai
AU - Li, Xin
AU - Felsberg, Michael
AU - Liang, Cheng
AU - Lin, Liting
AU - Ling, Haibin
AU - Liu, Ting
AU - Liu, Ziquan
AU - Lu, Huchuan
AU - Luo, Yifei
AU - Miao, Deshui
AU - Mogollon, Juan
AU - Pang, Ziqi
AU - Zajc, Luka Cehovin
AU - Pochimireddy, Jaswanth Reddy
AU - Rahmon, Gani
AU - Shi, Liangtao
AU - Siam, Mennatullah
AU - Sigal, Leonid
AU - Wu, Qiangqiang
PY - 2025
Y1 - 2025
N2 - The Visual Object Tracking Segmentation VOTS2024 challenge is the twelfth annual tracker benchmarking activity of the VOT initiative. This challenge consolidates the new tracking setup proposed in VOTS2023, which merges short-term and long-term as well as single-target and multiple-target tracking with segmentation masks as the only target location specification. Two sub-challenges are considered. The VOTS2024 standard challenge, focusing on classical objects and the VOTSt2024, which considers objects undergoing a topological transformation. Both challenges use the same performance evaluation methodology. Results of 28 submissions are presented and analyzed. A leaderboard, with participating trackers details, the source code, the datasets, and the evaluation kit are publicly available on the website (https://www.votchallenge.net/vots2024/). © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
AB - The Visual Object Tracking Segmentation VOTS2024 challenge is the twelfth annual tracker benchmarking activity of the VOT initiative. This challenge consolidates the new tracking setup proposed in VOTS2023, which merges short-term and long-term as well as single-target and multiple-target tracking with segmentation masks as the only target location specification. Two sub-challenges are considered. The VOTS2024 standard challenge, focusing on classical objects and the VOTSt2024, which considers objects undergoing a topological transformation. Both challenges use the same performance evaluation methodology. Results of 28 submissions are presented and analyzed. A leaderboard, with participating trackers details, the source code, the datasets, and the evaluation kit are publicly available on the website (https://www.votchallenge.net/vots2024/). © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
KW - VOTS
KW - tracking and segmentation
KW - transformative object tracking
KW - performance evaluation
UR - https://www.webofscience.com/wos/woscc/full-record/WOS:001544981600024
UR - http://www.scopus.com/inward/record.url?scp=105007227161&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-105007227161&origin=recordpage
U2 - 10.1007/978-3-031-91767-7_24
DO - 10.1007/978-3-031-91767-7_24
M3 - RGC 32 - Refereed conference paper (with host publication)
SN - 978-3-031-91766-0
T3 - Lecture Notes in Computer Science
SP - 357
EP - 383
BT - Computer Vision – ECCV 2024 Workshops
A2 - Del Bue, Alessio
A2 - Canton, Cristian
A2 - Pont-Tuset, Jordi
A2 - Tommasi, Tatiana Tommasi
PB - Springer, Cham
T2 - 18th European Conference on Computer Vision (ECCV 2024)
Y2 - 29 September 2024 through 4 October 2024
ER -