构建体育视频基准，测试大模型对物理风险的提前预警能力
From Sports to Safety: Benchmarking Proactive Risk Inference in MLLMs
- 用2888段真实体育视频构建风险预警评测集
- 顶尖模型能识险但超半数无法解释事故原因
- 提示词设计不当会引发大量误报，适合安全系统研究者
及时预判物理危险对现实安全至关重要，但现有多模态大模型（MLLM）评估集中于有害内容或一般风险，缺乏对主动物理风险预测的探索。体育场景具备多样性与可预测性：事故成因涵盖多种伤害维度，且事故前的空间时间线索依赖于与自动驾驶、跌倒检测等安全领域共享的推理能力。我们提出SPRINT（Sports Proactive Risk INference Testbed），包含2,888段真实体育视频（2,440段事故视频，448段安全对照视频），覆盖14项运动和3种环境。事故视频标注了早期危险线索、事故发生时间及分层原因；安全视频经人工验证无事故，用于诊断提示引发的误报。在不同提示和时间窗口下评估前沿MLLM发现，最佳模型在信号预警上超过95%，但在原因识别上低于50%。诊断实验显示，明确提问危险会引发严重误报，即使在无风险视频上。结果表明当前MLLM仅具表面化主动安全能力，缺乏基于成因的稳定早期预警，亟需提升动态物理环境中的可靠预警性能。数据与代码将在论文接收后开源。
原文摘要 · Abstract (English)
Timely anticipation of physical hazards is essential for real-world safety, yet existing MLLM evaluations focus on harmful content or general risks, leaving proactive physical hazard prediction underexplored. Sports provide a well-suited testbed: accident causes span diverse injury dimensions and pre-accident spatiotemporal cues draw on reasoning capabilities shared with broader safety domains such as autonomous driving and fall detection. We introduce SPRINT (Sports Proactive Risk INference Testbed), a benchmark of 2,888 real-world sports videos (2,440 accident, 448 safe controls) spanning 14 sports and 3 environmental settings. Accident videos feature fine-grained annotations of early hazard cues, accident timing, and hierarchical causes; safe videos are manually verified as accident-free and serve to diagnose prompt-induced false alarms. Evaluating state-of-the-art MLLMs under diverse prompts and temporal windows reveals a sharp gap between hazard sensitivity and understanding: the best model exceeds 95% in signaling hazards yet falls below 50% in identifying their causes. Diagnostic experiments further show that explicit danger queries trigger severe false alarms even on hazard-free videos. These findings indicate that current MLLMs exhibit only superficial proactive safety, lacking stable, cause-grounded early warning, and underscore the need for reliable proactive safety in dynamic physical environments. Data and code will be open-sourced upon acceptance.
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。