Details
| Original language | English |
|---|---|
| Title of host publication | MMSports 2022 - Proceedings of the 5th International ACM Workshop on Multimedia Content Analysis in Sports |
| Pages | 75-86 |
| Number of pages | 12 |
| ISBN (electronic) | 9781450394888 |
| Publication status | Published - 10 Oct 2022 |
| Event | 5th ACM International Workshop on Multimedia Content Analysis in Sports, MMSports 2022, co-located with ACM Multimedia 2022 - Lisboa, Portugal Duration: 14 Oct 2022 → … |
Abstract
The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team. In 2022, the challenges were composed of 6 vision-based tasks: (1) action spotting, focusing on retrieving action timestamps in long untrimmed videos, (2) replay grounding, focusing on retrieving the live moment of an action shown in a replay, (3) pitch localization, focusing on detecting line and goal part elements, (4) camera calibration, dedicated to retrieving the intrinsic and extrinsic camera parameters, (5) player re-identification, focusing on retrieving the same players across multiple views, and (6) multiple object tracking, focusing on tracking players and the ball through unedited video streams. Compared to last year's challenges, tasks (1-2) had their evaluation metrics redefined to consider tighter temporal accuracies, and tasks (3-6) were novel, including their underlying data and annotations. More information on the tasks, challenges and leaderboards are available on https://www.soccer-net.org. Baselines and development kits are available on https://github.com/SoccerNet.
Keywords
- challenges, computer vision, datasets, neural networks, soccer, video understanding
ASJC Scopus subject areas
- Computer Science(all)
- Computer Graphics and Computer-Aided Design
- Computer Science(all)
- Computer Vision and Pattern Recognition
- Computer Science(all)
- Software
- Engineering(all)
- Media Technology
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
MMSports 2022 - Proceedings of the 5th International ACM Workshop on Multimedia Content Analysis in Sports. 2022. p. 75-86.
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - SoccerNet 2022 Challenges Results
AU - Giancola, Silvio
AU - Cioppa, Anthony
AU - Deliège, Adrien
AU - Magera, Floriane
AU - Somers, Vladimir
AU - Kang, Le
AU - Zhou, Xin
AU - Barnich, Olivier
AU - De Vleeschouwer, Christophe
AU - Alahi, Alexandre
AU - Ghanem, Bernard
AU - Van Droogenbroeck, Marc
AU - Darwish, Abdulrahman
AU - Maglo, Adrien
AU - Clapés, Albert
AU - Luyts, Andreas
AU - Boiarov, Andrei
AU - Xarles, Artur
AU - Orcesi, Astrid
AU - Shah, Avijit
AU - Fan, Baoyu
AU - Comandur, Bharath
AU - Chen, Chen
AU - Zhang, Chen
AU - Zhao, Chen
AU - Lin, Chengzhi
AU - Chan, Cheuk Yiu
AU - Hui, Chun Chuen
AU - Li, Dengjie
AU - Yang, Fan
AU - Liang, Fan
AU - Da, Fang
AU - Yan, Feng
AU - Yu, Fufu
AU - Wang, Guanshuo
AU - Chan, H. Anthony
AU - Zhu, He
AU - Kan, Hongwei
AU - Chu, Jiaming
AU - Hu, Jianming
AU - Gu, Jianyang
AU - Chen, Jin
AU - Soares, João V.B.
AU - Theiner, Jonas
AU - De Corte, Jorge
AU - Brito, José Henrique
AU - Zhang, Jun
AU - Li, Junjie
AU - Liang, Junwei
AU - Shen, Leqi
AU - Ma, Lin
AU - Chen, Lingchi
AU - Santos Marques, Miguel
AU - Azatov, Mike
AU - Kasatkin, Nikita
AU - Wang, Ning
AU - Jia, Qiong
AU - Pham, Quoc Cuong
AU - Ewerth, Ralph
AU - Song, Ran
AU - Li, Rengang
AU - Gade, Rikke
AU - Debien, Ruben
AU - Zhang, Runze
AU - Lee, Sangrok
AU - Escalera, Sergio
AU - Jiang, Shan
AU - Odashima, Shigeyuki
AU - Chen, Shimin
AU - Masui, Shoichi
AU - Ding, Shouhong
AU - Chan, Sin Wai
AU - Chen, Siyu
AU - El-Shabrawy, Tallal
AU - He, Tao
AU - Moeslund, Thomas B.
AU - Siu, Wan Chi
AU - Zhang, Wei
AU - Li, Wei
AU - Wang, Xiangwei
AU - Tan, Xiao
AU - Li, Xiaochuan
AU - Wei, Xiaolin
AU - Ye, Xiaoqing
AU - Liu, Xing
AU - Wang, Xinying
AU - Guo, Yandong
AU - Zhao, Yaqian
AU - Yu, Yi
AU - Li, Yingying
AU - He, Yue
AU - Zhong, Yujie
AU - Guo, Zhenhua
AU - Li, Zhiheng
N1 - Funding Information: This work was supported by the Service Public de Wallonie (SPW) Recherche under the DeepSport project and Grant No. 2010235 (ARIAC by https://DigitalWallonia4.ai), the FRIA, the FNRS, and KAUST Oce of Sponsored Research through the Visual Computing Center funding.
PY - 2022/10/10
Y1 - 2022/10/10
N2 - The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team. In 2022, the challenges were composed of 6 vision-based tasks: (1) action spotting, focusing on retrieving action timestamps in long untrimmed videos, (2) replay grounding, focusing on retrieving the live moment of an action shown in a replay, (3) pitch localization, focusing on detecting line and goal part elements, (4) camera calibration, dedicated to retrieving the intrinsic and extrinsic camera parameters, (5) player re-identification, focusing on retrieving the same players across multiple views, and (6) multiple object tracking, focusing on tracking players and the ball through unedited video streams. Compared to last year's challenges, tasks (1-2) had their evaluation metrics redefined to consider tighter temporal accuracies, and tasks (3-6) were novel, including their underlying data and annotations. More information on the tasks, challenges and leaderboards are available on https://www.soccer-net.org. Baselines and development kits are available on https://github.com/SoccerNet.
AB - The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team. In 2022, the challenges were composed of 6 vision-based tasks: (1) action spotting, focusing on retrieving action timestamps in long untrimmed videos, (2) replay grounding, focusing on retrieving the live moment of an action shown in a replay, (3) pitch localization, focusing on detecting line and goal part elements, (4) camera calibration, dedicated to retrieving the intrinsic and extrinsic camera parameters, (5) player re-identification, focusing on retrieving the same players across multiple views, and (6) multiple object tracking, focusing on tracking players and the ball through unedited video streams. Compared to last year's challenges, tasks (1-2) had their evaluation metrics redefined to consider tighter temporal accuracies, and tasks (3-6) were novel, including their underlying data and annotations. More information on the tasks, challenges and leaderboards are available on https://www.soccer-net.org. Baselines and development kits are available on https://github.com/SoccerNet.
KW - challenges
KW - computer vision
KW - datasets
KW - neural networks
KW - soccer
KW - video understanding
UR - http://www.scopus.com/inward/record.url?scp=85137720519&partnerID=8YFLogxK
U2 - 10.1145/3552437.3558545
DO - 10.1145/3552437.3558545
M3 - Conference contribution
AN - SCOPUS:85137720519
SP - 75
EP - 86
BT - MMSports 2022 - Proceedings of the 5th International ACM Workshop on Multimedia Content Analysis in Sports
T2 - 5th ACM International Workshop on Multimedia Content Analysis in Sports, MMSports 2022, co-located with ACM Multimedia 2022
Y2 - 14 October 2022
ER -