A Graph-Based Method for Soccer Action Spotting Using Unsupervised Player Classification
This work addresses the problem of accurately identifying key actions in soccer videos for sports analytics, offering a competitive graph-based approach that improves on similar methods.
The paper tackles action spotting in soccer videos by representing players, referees, and goalkeepers as nodes in a graph and modeling their temporal interactions, achieving 97.72% accuracy in player classification and 57.83% average-mAP for action spotting when combined with audiovisual modalities.
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.