# SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos

Source: [SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos](<https://www.sota2.com/research/paper/68fa65821e209131cea0aa33>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-14T17:03:05.823Z

Authors: Silvio Giancola, Mohieddine Amine, Tarek Dghaily, Bernard Ghanem

Published: 2018-04-12T14:19:50.000Z

## Abstract

In this paper, we introduce SoccerNet, a benchmark for action spotting in soccer videos. The dataset is composed of 500 complete soccer games from six main European leagues, covering three seasons from 2014 to 2017 and a total duration of 764 hours. A total of 6,637 temporal annotations are automatically parsed from online match reports at a one minute resolution for three main classes of events (Goal, Yellow/Red Card, and Substitution). As such, the dataset is easily scalable. These annotations are manually refined to a one second resolution by anchoring them at a single timestamp following well-defined soccer rules. With an average of one event every 6.9 minutes, this dataset focuses on the problem of localizing very sparse events within long videos. We define the task of spotting as finding the anchors of soccer events in a video. Making use of recent developments in the realm of generic action recognition and detection in video, we provide strong baselines for detecting soccer events. We show that our best model for classifying temporal segments of length one minute reaches a mean Average Precision (mAP) of 67.8%. For the spotting task, our baseline reaches an Average-mAP of 49.7% for tolerances $\\delta$ ranging from 5 to 60 seconds. Our dataset and models are available at https://silviogiancola.github.io/SoccerNet.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Soccer Action Spotting on SoccerNet v1 (test)](<https://www.sota2.com/research/sota/soccer-action-spotting-on-soccernet-v1-test.md>): Soccer Action Spotting; SoccerNet v1 (test); Cards: 52.1.

- [Action Classification on SoccerNet (test)](<https://www.sota2.com/research/sota/action-classification-on-soccernet-test.md>): Action Classification; SoccerNet (test); mAP: 67.5.

- [Action spotting on SoccerNet (test)](<https://www.sota2.com/research/sota/action-spotting-on-soccernet-test.md>): Action spotting; SoccerNet (test); Average mAP: 49.7.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1804.04527>)

[PDF](<https://arxiv.org/pdf/1804.04527.pdf>)