# SoccerNet 2026 Player-Centric Ball-Action Spotting:Retraining and Post-Processing Extensions to the FOOTPASS Baselines

arXiv: https://arxiv.org/abs/2606.09679 · HTML: https://mlsanity.com/paper/2606.09679/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 8 references that are in the map.
- First posted on arXiv 8 Jun 2026.

## Builds on (most cited first, 6 of 6)

- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [Spatio-Temporal Action Detection Under Large Motion](https://mlsanity.com/paper/2209.02250/) (2022)
- [Game State and Spatio-temporal Action Detection in Soccer using Graph Neural Networks and 3D Convolutional Networks](https://mlsanity.com/paper/2502.15462/) (2025)
- [Beyond Pixels: Leveraging the Language of Soccer to Improve Spatio-Temporal Action Detection in Broadcast Videos](https://mlsanity.com/paper/2505.09455/) (2025)
- [FOOTPASS: A Multi-Modal Multi-Agent Tactical Context Dataset for Play-by-Play Action Spotting in Soccer Broadcast Videos](https://mlsanity.com/paper/2511.16183/) (2025)

## Abstract (arXiv)

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 GNN logits into the DST encoder, combining graph-based tactical context with per-player visual features; (3) square-root frequency class weighting to address the 213:1 pass-to-tackle imbalance in the training data; and (4) a post processing pipeline comprising per-class logit gating, temporal frame refinement, jersey re-assignment, and a two-model ensemble. Our system achieves 0.548 Macro F1 on the test set and 0.446 on the challenge set (server evaluation).