文献类型：期刊文献

英文题名：SoccerNet 2022 Challenges Results

作者：Giancola, Silvio[1]; Cioppa, Anthony[2]; Deliège, Adrien[2]; Magera, Floriane[3]; Somers, Vladimir[4]; Kang, Le[5]; Zhou, Xin[5]; Barnich, Olivier[6]; De Vleeschouwer, Christophe[7]; Alahi, Alexandre[8]; Ghanem, Bernard[1]; Van Droogenbroeck, Marc[2]; Darwish, Abdulrahman[9]; Maglo, Adrien[10]; Clapés, Albert[11]; Luyts, Andreas[12]; Boiarov, Andrei[13]; Xarles, Artur[14]; Orcesi, Astrid[10]; Shah, Avijit[15]; Fan, Baoyu[16]; Comandur, Bharath[17]; Chen, Chen[18]; Zhang, Chen[18]; Zhao, Chen[19]; Lin, Chengzhi[20]; Chan, Cheuk-Yiu[21]; Hui, Chun Chuen[21]; Li, Dengjie[22]; Yang, Fan[23]; Liang, Fan[22]; Da, Fang[24]; Yan, Feng[22]; Yu, Fufu[25]; Wang, Guanshuo[25]; Chan, H. Anthony[21]; Zhu, He[26]; Kan, Hongwei[16]; Chu, Jiaming[27]; Hu, Jianming[26]; Gu, Jianyang[28]; Chen, Jin[29]; Soares, Jo?o V. B.[15]; Theiner, Jonas[30]; De Corte, Jorge[12]; Brito, José Henrique[31]; Zhang, Jun[25]; Li, Junjie[32]; Liang, Junwei[25]; Shen, Leqi[26]; Ma, Lin[22]; Chen, Lingchi[29]; Santos Marques, Miguel[31]; Azatov, Mike[33]; Kasatkin, Nikita[13]; Wang, Ning[34]; Jia, Qiong[25]; Pham, Quoc Cuong[10]; Ewerth, Ralph[35]; Song, Ran[36]; Li, Rengang[16]; Gade, Rikke[11]; Debien, Ruben[12]; Zhang, Runze[16]; Lee, Sangrok[37]; Escalera, Sergio[38]; Jiang, Shan[23]; Odashima, Shigeyuki[23]; Chen, Shimin[18]; Masui, Shoichi[23]; Ding, Shouhong[25]; Chan, Sin-Wai[21]; Chen, Siyu[22]; El-Shabrawy, Tallal[9]; He, Tao[26]; Moeslund, Thomas B.[11]; Siu, Wan-Chi[39]; Zhang, Wei[37]; Li, Wei[18]; Wang, Xiangwei[19]; Tan, Xiao[40]; Li, Xiaochuan[16]; Wei, Xiaolin[22]; Ye, Xiaoqing[40]; Liu, Xing[19]; Wang, Xinying[29]; Guo, Yandong[18]; Zhao, Yaqian[16]; Yu, Yi[29]; Li, Yingying[40]; He, Yue[40]; Zhong, Yujie[22]; Guo, Zhenhua[16]; Li, Zhiheng[38]

机构：[1] Kaust, Thuwal, Saudi Arabia; [2] University of Liège, Liège, Belgium; [3] University of Liège, Evs Broadcast Equipment, Liège, Belgium; [4] Sportradar, UCLouvain, Epfl, London, United Kingdom; [5] Baidu Research, Sunnyvale, United States; [6] Evs Broadcast Equipment, Liège, Belgium; [7] UCLouvain, Louvain-la-Neuve, Belgium; [8] Epfl, Lausanne, Switzerland; [9] German University in Cairo, New Cairo City, Egypt; [10] Université Paris-Saclay, Cea, List, Paris, France; [11] Aalborg University, Aalborg, Denmark; [12] ReBatch, Kontich, Belgium; [13] Schahausen Institute of Technology, Schahausen, Switzerland; [14] Universitat de Barcelona, Barcelona, Spain; [15] Yahoo Research, Sunnyvale, United States; [16] Inspur Electronic Information Industry Co. Ltd., State Key Laboratory of High-end Server Storage Technology, Jinan, China; [17] Purdue University, West Lafayette, United States; [18] Oppo Research Institute, Shenzhen, China; [19] Department of Augmented Reality Technology [ART], Baidu Inc, Beijing, China; [20] Sun Yat-sen University, Guangzhou, China; [21] Caritas Institute of Higher Education, Tseung Kwan O, Hong Kong; [22] Meituan Inc., Beijing, China; [23] Fujitsu Research, Kawasaki, Japan; [24] QCraft Inc., Beijing, China; [25] Tencent Youtu Lab, Shanghai, China; [26] Tsinghua University, Beijing, China; [27] Oppo Research Institute and Beijing, University of Posts and Telecommunications, Shenzhen, China; [28] Oppo Research Institute, Zhejiang University, Shenzhen, China; [29] Mgtv, Changsha, China; [30] L3S Research Center, Leibniz University Hannover, Hannover, Germany; [31] 2Ai School of Technology Ipca, S?o Martinho, Portugal; [32] Tencent Youtu Lab Shanghai Jiao, Tong University, Shanghai, China; [33] Arsenal Fc, London, United Kingdom; [34] Oppo Research Institute, East China University of Science and Technology, Shenzhen, China; [35] L3S Research Center Leibniz, University Hannover, Tib Leibniz Information Center for Science and Technology, Hannover, Germany; [36] School of Control Science and Engineering, Shandong University, Jinan, China; [37] Graduate School of Information Yonsei University, Modulabs, Seoul, Korea, Republic of; [38] Universitat de Barcelona, ComputerVision Center, Aalborg University, Barcelona, Spain; [39] Caritas Institute of Higher Education, Hong Kong Polytechnic University, Tseung Kwan O, Hong Kong; [40] Department of Computer Vision Technology [VIS], Baidu Inc, Beijing, China

年份：2022

起止页码：75

外文期刊名：MMSports 2022 - Proceedings of the 5th International ACM Workshop on Multimedia Content Analysis in Sports

收录：EI(收录号：20224513089844)

语种：英文

外文关键词：Cameras - Focusing - HTTP - Sports

摘要：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. ? 2022 Owner/Author.