A graph-based method for soccer action spotting using unsupervised player classification

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Cartas, Alejandro
• dc.contributor.author Ballester, Coloma
• dc.contributor.author Haro Ortega, Gloria
• dc.date.accessioned 2025-03-27T07:24:10Z
• dc.date.available 2025-03-27T07:24:10Z
• dc.date.issued 2022
• dc.description.abstract Action spotting in soccer videos is the task of identifying the specific time when a certain key action of the game occurs. Lately, it has received a large amount of attention and powerful methods have been introduced. Action spotting involves understanding the dynamics of the game, the complexity of events, and the variation of video sequences. Most approaches have focused on the latter, given that their models exploit the global visual features of the sequences. In this work, we focus on the former by (a) identifying and representing the players, referees, and goalkeepers as nodes in a graph, and by (b) modeling their temporal interactions as sequences of graphs. For the player identification, or player classification task, we obtain an accuracy of 97.72% in our annotated benchmark. For the action spotting task, our method obtains an overall performance of 57.83% average-mAP by combining it with other audiovisual modalities. This performance surpasses similar graph-based methods and has competitive results with heavy computing methods. Code and data are available at https://github.com/IPCV/soccer_action_spotting.
• dc.description.sponsorship The authors acknowledge support by MICINN/FEDER UE project, ref. PID2021-127643NB-I00, H2020-MSCA-RISE-2017 project, ref. 777826 NoMADS, and ReAViPeRo network, ref. RED2018-102511-T.
• dc.format.mimetype application/pdf
• dc.identifier.citation Cartas A, Ballester C, Haro G. A graph-based method for soccer action spotting using unsupervised player classification. In: MMSports '22: Proceedings of the 5th International Workshop on Multimedia Content Analysis in Sports; 2022 Oct 10; Lisboa, Portugal. New York: ACM; 2022. p. 93-102. DOI: 10.1145/3552437.3555691
• dc.identifier.doi 10.1145/3552437.3555691
• dc.identifier.isbn 9781450394888
• dc.identifier.uri http://hdl.handle.net/10230/70024
• dc.language.iso eng
• dc.publisher ACM Association for Computer Machinery
• dc.relation.ispartof MMSports '22: Proceedings of the 5th International Workshop on Multimedia Content Analysis in Sports; 2022 Oct 10; Lisboa, Portugal. New York: ACM; 2022
• dc.relation.projectID info:eu-repo/grantAgreement/ES/3PE/PID2021-127643
• dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/777826
• dc.rights © 2022Association for Computing Machinery
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.subject.keyword Action spotting
• dc.subject.keyword Sports summarization
• dc.subject.keyword Video summarization
• dc.subject.keyword Graph neural networks
• dc.subject.keyword Player classification
• dc.title A graph-based method for soccer action spotting using unsupervised player classification
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/acceptedVersion