SoccerNet 2023 Challenges Results

• URL: http://arxiv.org/abs/2309.06006v1
• Date: Tue, 12 Sep 2023 07:03:30 GMT
• Title: SoccerNet 2023 Challenges Results
• Authors: Anthony Cioppa and Silvio Giancola and Vladimir Somers and Floriane Magera and Xin Zhou and Hassan Mkhallati and Adrien Deli\`ege and Jan Held and Carlos Hinojosa and Amir M. Mansourian and Pierre Miralles and Olivier Barnich and Christophe De Vleeschouwer and Alexandre Alahi and Bernard Ghanem and Marc Van Droogenbroeck and Abdullah Kamal and Adrien Maglo and Albert Clap\'es and Amr Abdelaziz and Artur Xarles and Astrid Orcesi and Atom Scott and Bin Liu and Byoungkwon Lim and Chen Chen and Fabian Deuser and Feng Yan and Fufu Yu and Gal Shitrit and Guanshuo Wang and Gyusik Choi and Hankyul Kim and Hao Guo and Hasby Fahrudin and Hidenari Koguchi and H{\aa}kan Ard\"o and Ibrahim Salah and Ido Yerushalmy and Iftikar Muhammad and Ikuma Uchida and Ishay Be'ery and Jaonary Rabarisoa and Jeongae Lee and Jiajun Fu and Jianqin Yin and Jinghang Xu and Jongho Nang and Julien Denize and Junjie Li and Junpei Zhang and Juntae Kim and Kamil Synowiec and Kenji Kobayashi and Kexin Zhang and Konrad Habel and Kota Nakajima and Licheng Jiao and Lin Ma and Lizhi Wang and Luping Wang and Menglong Li and Mengying Zhou and Mohamed Nasr and Mohamed Abdelwahed and Mykola Liashuha and Nikolay Falaleev and Norbert Oswald and Qiong Jia and Quoc-Cuong Pham and Ran Song and Romain H\'erault and Rui Peng and Ruilong Chen and Ruixuan Liu and Ruslan Baikulov and Ryuto Fukushima and Sergio Escalera and Seungcheon Lee and Shimin Chen and Shouhong Ding and Taiga Someya and Thomas B. Moeslund and Tianjiao Li and Wei Shen and Wei Zhang and Wei Li and Wei Dai and Weixin Luo and Wending Zhao and Wenjie Zhang and Xinquan Yang and Yanbiao Ma and Yeeun Joo and Yingsen Zeng and Yiyang Gan and Yongqiang Zhu and Yujie Zhong and Zheng Ruan and Zhiheng Li and Zhijian Huang and Ziyu Meng
• Abstract summary: 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.
• Score: 165.5977813812761
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 https://www.soccer-net.org. Baselines and development kits can be found on https://github.com/SoccerNet.

Related papers

• SoccerNet 2024 Challenges Results [152.8534707514927]
  SoccerNet 2024 challenges represent the fourth annual video understanding challenges organized by the SoccerNet team. The challenges aim to advance research across multiple themes in football, including broadcast video understanding, field understanding, and player understanding. This year, the challenges encompass four vision-based tasks.
  arXiv  Detail & Related papers  (2024-09-16T14:12:22Z)
• The 8th AI City Challenge [57.25825945041515]
  The 2024 edition featured five tracks, attracting unprecedented interest from 726 teams in 47 countries and regions. The challenge utilized two leaderboards to showcase methods, with participants setting new benchmarks.
  arXiv  Detail & Related papers  (2024-04-15T03:12:17Z)
• SoccerNet 2022 Challenges Results [167.6158475931228]
  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. 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.
  arXiv  Detail & Related papers  (2022-10-05T16:12:50Z)
• SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos [62.686484228479095]
  We propose a novel dataset for multiple object tracking composed of 200 sequences of 30s each. The dataset is fully annotated with bounding boxes and tracklet IDs. Our analysis shows that multiple player, referee and ball tracking in soccer videos is far from being solved.
  arXiv  Detail & Related papers  (2022-04-14T12:22:12Z)
• MMSys'22 Grand Challenge on AI-based Video Production for Soccer [2.14475390920102]
  This challenge aims to assist the automation of such a production pipeline using AI. In particular, we focus on the enhancement operations that take place after an event has been detected.
  arXiv  Detail & Related papers  (2022-02-02T13:53:42Z)
• Feature Combination Meets Attention: Baidu Soccer Embeddings and Transformer based Temporal Detection [3.7709686875144337]
  We present a two-stage paradigm to detect what and when events happen in soccer broadcast videos. Specifically, we fine-tune multiple action recognition models on soccer data to extract high-level semantic features. This approach achieved the state-of-the-art performance in both two tasks, i.e., action spotting and replay grounding, in the SoccerNet-v2 Challenge.
  arXiv  Detail & Related papers  (2021-06-28T08:00:21Z)
• SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos [71.72665910128975]
  SoccerNet-v2 is a novel large-scale corpus of manual annotations for the SoccerNet video dataset. We release around 300k annotations within SoccerNet's 500 untrimmed broadcast soccer videos. We extend current tasks in the realm of soccer to include action spotting, camera shot segmentation with boundary detection.
  arXiv  Detail & Related papers  (2020-11-26T16:10:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.