Ball Action Spotting
SoccerNet Ball Action Spotting
In order to understand the salient actions of a broadcast soccer game, SoccerNet introduces the task of action spotting, which consists in finding all the actions occurring in the videos. Beyond soccer understanding, this task addresses the more general problem of retrieving moments with a specific semantic meaning in long untrimmed videos.
Our task.
Ball action spotting involves identifying both the timing and type of ball-related actions across 12 classes in our dataset. Each action is marked by a single timestamp. In contrast to the SoccerNet Action Spotting Challenge, our videos feature a higher density of actions.
All of our classes.
We provide annotation for all two types of soccer ball actions: {Pass, Drive}. In 2024, we extend it to 12 different classes of soccer ball actions: {Pass, Drive, Header, High Pass, Out, Cross, Throw In, Shot, Ball Player Block, Player Successful Tackle, Free Kick, Goal}
Our data.
The data consists of 7 videos of English Football League games, each broadcast in 720p quality. We don't provide extracted features to encourage the development of end-to-end methods. The challenge set is composed of 2 separate games. Additionally, participants are encouraged to leverage the 500 unannotated games from the Action Spotting challenge as a resource for this task.
Our Metric.
Unlike the SoccerNet Action Spotting Challenge, that uses the tight average-mAP ([1-5] seconds tolerance), this challenge focuses on accurately spotting the ball events with the mAP@1 (1 second tolerance).
2023 Challenge leaderboard
Our videos on Action Spotting
SoccerNet-v2: a new MASSIVE soccer dataset
In this video, we present our paper: “SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos” published at the CVPR 2021 workshop CVsports. We provide 300,000 temporal annotations within 500 soccer games. This allows a 17-class action spotting task, a 13-class camera boundary detection task, and a novel replay grounding task. We provide benchmarks for all these tasks to start an international challenge.
A Context-Aware Loss Function for Action Spotting in Soccer Videos
In this video, we present our paper: “A Context-Aware Loss Function for Action Spotting in Soccer Videos” published at CVPR 2020. This work introduces a novel loss to gather the temporal context surrounding the actions, further used to spot those actions in soccer videos. We achieve state-of-the-art performances on SoccerNet and improvements on ActivityNet!
SoccerNet-v2: Our new soccer dataset and AI challenge
SoccerNet-v2 challenge - Tutorial #2 (live session)
SoccerNet-v2 challenge - Tutorial #3 (live session)
SoccerNet-v2 challenge - Tutorial #4 part 1 (live session) ft. Matteo Tomei
SoccerNet-v2 challenge - Tutorial #4 part 2 (live session) ft. Bastien Vanderplaetse
SoccerNet-v2 challenge - Tutorial #5 part 1 (live session) ft. Kanav Vats
How to cite this work ?
@InProceedings{Deliège2020SoccerNetv2,
title={SoccerNet-v2 : A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos},
author={Adrien Deliège and Anthony Cioppa and Silvio Giancola and Meisam J. Seikavandi and Jacob V. Dueholm and Kamal Nasrollahi and Bernard Ghanem and Thomas B. Moeslund and Marc Van Droogenbroeck},
year={2021},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},