SoccerNet 2026 Player-Centric Ball Action Spotting: Per-Player Attention with Agreement-Based Ensembling

• URL: http://arxiv.org/abs/2606.28389v1
• Date: Tue, 23 Jun 2026 09:16:04 GMT
• Title: SoccerNet 2026 Player-Centric Ball Action Spotting: Per-Player Attention with Agreement-Based Ensembling
• Abstract summary: We present our submission to the SoccerNet 2026 Player-Centric Ball Action Spotting challenge.<n>A Track-Aware Action Detector (TAAD) produces per-player action logits from broadcast video, and a Denoising Sequence Transduction (DST) transformer converts game-state features and TAAD logits into structured event sequences.<n>For the DST stage, we introduce a two-stage per-player attention mechanism operating on game-state features, and show that a spatial-first attention ordering improves validation Macro-F1 by 1.87%.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present our submission to the SoccerNet 2026 Player-Centric Ball Action Spotting challenge, which uses a two-stage pipeline: a Track-Aware Action Detector (TAAD) produces per-player action logits from broadcast video, and a Denoising Sequence Transduction (DST) transformer converts game-state features and TAAD logits into structured event sequences. We improve the TAAD with a temporal transformer that adds cross-frame context, alongside several training fixes. For the DST stage, we introduce a two-stage per-player attention mechanism operating on game-state features, and show that a spatial-first attention ordering (cross-player attention before temporal attention) improves validation Macro-F1 by 1.87%. To exploit architectural diversity, we train four model variants and combine them with a Weighted Event Fusion ensemble that applies agreement filtering to suppress single-model false positives while preserving recall, plus a dedicated exception for the rare tackle class. Our final system improves the challenge Macro-F1 from a baseline of 48.6 to 58.94.

Related papers

• Entity-Aware Sequence Transduction for Player-Centric Ball Action Spotting [3.422845160588969]
  Player-centric ball action spotting requires temporally precise event detection together with actor attribution.<n>Existing Denoising Sequence Transduction (DST) baselines treat the player-role dimension as part of a flattened frame-level representation.<n>We propose Multi-Entity Denoising Sequence Transduction (ME-DST) to keep the role-slot dimension throughout encoding.
  arXiv  Detail & Related papers  (2026-08-03T04:48:54Z)
• SoccerNet 2026 Player-Centric Ball-Action Spotting:Retraining and Post-Processing Extensions to the FOOTPASS Baselines [0.0]
  SoccerNet 2026 Player-Centric Ball-Action Spotting Challenge requires predicting who performs which action and when across eight classes in broadcast soccer.<n>Our system achieves 0.548 Macro F1 on the test set and 0.446 on the challenge set (server evaluation)
  arXiv  Detail & Related papers  (2026-06-08T15:59:56Z)
• TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation [61.04423890085284]
  We present TunerDiT, a progressive steering method that requires no additional training for multi-event generation.<n>TunerDiT achieves state-of-the-art performance across 8 metrics and offers a tunable trade-off between video consistency and event separation.
  arXiv  Detail & Related papers  (2026-05-29T17:56:09Z)
• EgoAction: Egocentric Action Composition with Reliability-Aware Temporal Fusion for the EPIC-KITCHENS Action Detection Challenge at CVPR 2026 [69.56534058291463]
  We formulate our submission as EgoAction, a unified decoupled detection and fusion pipeline.<n>The pipeline uses EPIC-finetuned VideoMAE-L features, trains separate noun and verb temporal detectors with causal temporal modeling.<n>EgoAction provides a compact and reproducible system for egocentric temporal action detection.
  arXiv  Detail & Related papers  (2026-05-23T10:05:56Z)
• SCOPE: Simulating Cross-game Operations in Playable Environments for FPS World Models [49.15128236103093]
  Existing methods inject actions globally and train on single titles, failing under dense FPS inputs.<n>We propose SCOPE, which inserts a conditioning module into each transformer block of a pretrained video diffusion model.<n>We also introduce CrossFPS, the first multi-game FPS dataset with frame-aligned action telemetry.
  arXiv  Detail & Related papers  (2026-05-22T08:06:37Z)
• ActionParty: Multi-Subject Action Binding in Generative Video Games [117.52562594944679]
  ActionParty is a controllable multi-subject world model for generative video games.<n>We demonstrate the first video world model capable of controlling up to seven players simultaneously across 46 diverse environments.
  arXiv  Detail & Related papers  (2026-04-02T17:59:58Z)
• Beyond Pixels: Leveraging the Language of Soccer to Improve Spatio-Temporal Action Detection in Broadcast Videos [1.4249472316161877]
  State-of-the-art,temporal action detection methods show promising results for extracting events from broadcast videos.<n>Many false positives could be resolved by considering a broader sequence of actions and game-state information.<n>We address this by reasoning at the game level and improving STAD through the addition of a denoising sequence task.
  arXiv  Detail & Related papers  (2025-05-14T15:05:36Z)
• From Broadcast to Minimap: Achieving State-of-the-Art SoccerNet Game State Reconstruction [0.19748373512880277]
  Game State Reconstruction (GSR) involves precise tracking and localization of all individuals on the football field-players, goalkeepers, referees, and others.<n>This capability enables coaches and analysts to derive actionable insights into player movements, team formations, and game dynamics.<n>We present a robust end-to-end pipeline for tracking players across an entire match using a single-camera setup.
  arXiv  Detail & Related papers  (2025-04-08T18:10:44Z)
• TranSPORTmer: A Holistic Approach to Trajectory Understanding in Multi-Agent Sports [28.32714256545306]
  TranSPORTmer is a unified transformer-based framework capable of addressing all these tasks. It effectively captures temporal dynamics and social interactions in an equivariant manner. It outperforms state-of-the-art task-specific models in player forecasting, player forecasting-imputation, ball inference, and ball imputation.
  arXiv  Detail & Related papers  (2024-10-23T11:35:44Z)
• Harnessing Temporal Causality for Advanced Temporal Action Detection [53.654457142657236]
  We introduce CausalTAD, which combines causal attention and causal Mamba to achieve state-of-the-art performance on benchmarks. We ranked 1st in the Action Recognition, Action Detection, and Audio-Based Interaction Detection tracks at the EPIC-Kitchens Challenge 2024, and 1st in the Moment Queries track at the Ego4D Challenge 2024.
  arXiv  Detail & Related papers  (2024-07-25T06:03:02Z)
• ZJU ReLER Submission for EPIC-KITCHEN Challenge 2023: TREK-150 Single Object Tracking [62.98078087018469]
  We introduce MSDeAOT, a variant of the AOT framework that incorporates transformers at multiple feature scales. MSDeAOT efficiently propagates object masks from previous frames to the current frame using two feature scales of 16 and 8. As a testament to the effectiveness of our design, we achieved the 1st place in the EPIC-KITCHENS TREK-150 Object Tracking Challenge.
  arXiv  Detail & Related papers  (2023-07-05T03:50:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.