SoccerNet-FoulRet：检索语义相似的足球犯规视频
SoccerNet-FoulRet: Retrieving Semantically Similar Soccer Foul Videos
- University of Liège（列日大学）
- KAUST（阿卜杜拉国王科技大学）
- SpAItial
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对足球裁判判罚不一致问题，提出首个语义犯规检索基准SoccerNet-FoulRet，基于裁判解释定义相关性，评估零样本与微调模型，发现现有方法检索先例效果有限。
AI中文摘要：
职业足球中的裁判判罚仍然存在不一致性，因为裁判难以将争议犯规与相似的过往案例进行轻松比较。我们将此问题定义为检索问题，并引入SoccerNet-FoulRet，这是首个用于语义犯规检索的基准。给定一个查询犯规，任务是检索被判定为相关先例的过往犯规，无论摄像机角度、球队或外观如何。这不同于先前的视频到视频检索，后者通过视觉相似性或共享事件来匹配片段。在此，相关性由裁判解释来定义。我们从SoccerNet-MVFoul数据集构建该基准，并评估零样本视频和视觉-语言嵌入器的检索能力，以及一个任务特定的微调基线，在693个人工验证的查询和类别相关性标签上进行评估。语义犯规检索仍然具有挑战性。最强的零样本模型在人工验证的先例上实现了不到5%的HitRate@10，而类别监督的微调提高了类别相关性，但对先例检索的迁移效果有限。我们发布SoccerNet-FoulRet，将语义犯规检索确立为一个开放问题：此https URL。
英文摘要：
Refereeing decisions in professional soccer remain inconsistent because referees cannot easily compare a contentious foul against similar past cases. We cast this as a retrieval problem and introduce SoccerNet-FoulRet, the first benchmark for semantic foul retrieval. Given a query foul, the task is to retrieve past fouls judged to be relevant precedents, regardless of camera angle, teams, or appearance. This differs from prior video-to-video retrieval, which matches clips by visual similarity or a shared event. Here, relevance is defined by refereeing interpretation. We build the benchmark from the SoccerNet-MVFoul dataset and evaluate retrieval ability of zero-shot video and vision-language embedders together with a task-specific fine-tuned baseline on 693 human-verified queries and category-relevance labels. Semantic foul retrieval remains challenging. The strongest zero-shot model achieves under 5% HitRate@10 on human-verified precedents, while category-supervised fine-tuning improves category relevance but transfers only modestly to precedent retrieval. We release SoccerNet-FoulRet to establish semantic foul retrieval as an open problem: https://github.com/SoccerNet/sn-foulret.
