TY - STD AU - Anthony Cioppa AU - Silvio Giancola AU - Vladimir Somers AU - Floriane Magera AU - Xin Zhou AU - Hassan Mkhallati AU - Adrien Deliège AU - Jan Held AU - Carlos Hinojosa AU - Amir M. Mansourian AU - Pierre Miralles AU - Olivier Barnich AU - Christophe De Vleeschouwer AU - Alexandre Alahi AU - Bernard Ghanem AU - Marc Van Droogenbroeck AU - Abdullah Kamal AU - Adrien Maglo AU - Albert Clapés AU - Amr Abdelaziz AU - Artur Xarles AU - Astrid Orcesi AU - Atom Scott AU - Bin Liu AU - Byoungkwon Lim AU - Chen Chen AU - Fabian Deuser AU - Feng Yan AU - Fufu Yu AU - Gal Shitrit AU - Guanshuo Wang AU - Gyusik Choi AU - Hankyul Kim AU - Hao Guo AU - Hasby Fahrudin AU - Hidenari Koguchi AU - Håkan Ardö AU - Ibrahim Salah AU - Ido Yerushalmy AU - Iftikar Muhammad AU - Ikuma Uchida AU - Ishay Be'ery AU - Jaonary Rabarisoa AU - Jeongae Lee AU - Jiajun Fu AU - Jianqin Yin AU - Jinghang Xu AU - Jongho Nang AU - Julien Denize AU - Junjie Li AU - Junpei Zhang AU - Juntae Kim AU - Kamil Synowiec AU - Kenji Kobayashi AU - Kexin Zhang AU - Konrad Habel AU - Kota Nakajima AU - Licheng Jiao AU - Lin Ma AU - Lizhi Wang AU - Luping Wang AU - Menglong Li AU - Mengying Zhou AU - Mohamed Nasr AU - Mohamed Abdelwahed AU - Mykola Liashuha AU - Nikolay Falaleev AU - Norbert Oswald AU - Qiong Jia AU - Quoc-Cuong Pham AU - Ran Song AU - Romain Hérault AU - Rui Peng AU - Ruilong Chen AU - Ruixuan Liu AU - Ruslan Baikulov AU - Ryuto Fukushima AU - Sergio Escalera AU - Seungcheon Lee AU - Shimin Chen AU - Shouhong Ding AU - Taiga Someya AU - Thomas B. Moeslund AU - Tianjiao Li AU - Wei Shen AU - Wei Zhang AU - Wei Li AU - Wei Dai AU - Weixin Luo AU - Wending Zhao AU - Wenjie Zhang AU - Xinquan Yang AU - Yanbiao Ma AU - Yeeun Joo AU - Yingsen Zeng AU - Yiyang Gan AU - Yongqiang Zhu AU - Yujie Zhong AU - Zheng Ruan AU - Zhiheng Li AU - Zhijian Huang AU - Ziyu Meng PY - 2023// TI - SoccerNet 2023 Challenges Results N2 - The SoccerNet 2023 challenges were the third annual video understanding challenges organized by the SoccerNet team. For this third edition, the challenges were composed of seven vision-based tasks split into three main themes. The first theme, broadcast video understanding, is composed of three high-level tasks related to describing events occurring in the video broadcasts: (1) action spotting, focusing on retrieving all timestamps related to global actions in soccer, (2) ball action spotting, focusing on retrieving all timestamps related to the soccer ball change of state, and (3) dense video captioning, focusing on describing the broadcast with natural language and anchored timestamps. The second theme, field understanding, relates to the single task of (4) camera calibration, focusing on retrieving the intrinsic and extrinsic camera parameters from images. The third and last theme, player understanding, is composed of three low-level tasks related to extracting information about the players: (5) re-identification, focusing on retrieving the same players across multiple views, (6) multiple object tracking, focusing on tracking players and the ball through unedited video streams, and (7) jersey number recognition, focusing on recognizing the jersey number of players from tracklets. Compared to the previous editions of the SoccerNet challenges, tasks (2-3-7) are novel, including new annotations and data, task (4) was enhanced with more data and annotations, and task (6) now focuses on end-to-end approaches. More information on the tasks, challenges, and leaderboards are available on this https URL. Baselines and development kits can be found on this https URL. UR - https://arxiv.org/abs/2309.06006 L1 - http://158.109.8.37/files/CGS2023.pdf N1 - HUPBA ID - Anthony Cioppa2023 ER -