Reproduce “SoccerNet 2026 Challenges Results” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Anthony Cioppa, Silvio Giancola, Håkan Ardö, Mohamad Dalal, Jan Held, Jérémie Ochin, Jiayuan Rao, Karen Sanchez and 97 more

SoccerNet 2026 presents five football-video understanding tasks in shared benchmarks, baselines, and held-out evaluations: anticipating actions, identifying players, synthesizing views, locating athletes, and answering questions. Across 427 teams and 1,129 entries, reported submissions improved supplied baselines; Ball Action Anticipation reached 24.08 mAPavg versus 16.76. These comparisons do not establish causal component effects or general predictability.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.