改进足球动作检测模型，提升球员与动作匹配精度。
SoccerNet 2026 Player-Centric Ball-Action Spotting:Retraining and Post-Processing Extensions to the FOOTPASS Baselines
- 用梯度检查点实现单卡全模型微调，节省显存
- 融合图网络与时空模型，结合战术与视觉特征
- 针对传球与抢断数据不平衡问题优化权重
我们为SoccerNet 2026球员中心球动作用检测挑战设计了系统，需在8类广播足球动作中预测谁在何时执行何种动作。基于三个FOOTPASS基线（TAAD、TAAD+GNN、TAAD+DST），提出四项改进：(1) 梯度检查点技术，支持单GPU全骨干网络微调；(2) 将GNN输出的逻辑值融合进DST编码器，结合图结构战术上下文与球员视觉特征；(3) 采用平方根频率加权策略，缓解训练数据中传球与抢断213:1的严重不平衡；(4) 后处理流水线包括每类逻辑门控、时序帧修正、球衣重分配及双模型集成。最终系统在测试集上达到0.548宏平均F1，挑战集上0.446（服务器评估）。
原文摘要 · Abstract (English)
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).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。