SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos

Handle URI:
http://hdl.handle.net/10754/627570
Title:
SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos
Authors:
Giancola, Silvio; Amine, Mohieddine; Dghaily, Tarek; Ghanem, Bernard ( 0000-0002-5534-587X )
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.
KAUST Department:
Visual Computing Center (VCC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Electrical Engineering Program
Publisher:
arXiv
Issue Date:
12-Apr-2018
ARXIV:
arXiv:1804.04527
Type:
Preprint
Additional Links:
http://arxiv.org/abs/1804.04527v1; http://arxiv.org/pdf/1804.04527v1
Appears in Collections:
Other/General Submission; Electrical Engineering Program; Visual Computing Center (VCC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorGiancola, Silvioen
dc.contributor.authorAmine, Mohieddineen
dc.contributor.authorDghaily, Tareken
dc.contributor.authorGhanem, Bernarden
dc.date.accessioned2018-04-19T10:45:32Z-
dc.date.available2018-04-19T10:45:32Z-
dc.date.issued2018-04-12en
dc.identifier.urihttp://hdl.handle.net/10754/627570-
dc.description.abstractIn 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.en
dc.publisherarXiven
dc.relation.urlhttp://arxiv.org/abs/1804.04527v1en
dc.relation.urlhttp://arxiv.org/pdf/1804.04527v1en
dc.rightsArchived with thanks to arXiven
dc.titleSoccerNet: A Scalable Dataset for Action Spotting in Soccer Videosen
dc.typePreprinten
dc.contributor.departmentVisual Computing Center (VCC)en
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentElectrical Engineering Programen
dc.eprint.versionPre-printen
dc.identifier.arxividarXiv:1804.04527en
kaust.authorGiancola, Silvioen
kaust.authorAmine, Mohieddineen
kaust.authorDghaily, Tareken
kaust.authorGhanem, Bernarden
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.