DART: 难度自适应路由用于零样本视频时间定位
DART: Difficulty-Adaptive Routing for Zero-Shot Video Temporal Grounding
AI总结：
提出DART方法，通过难度感知路由和结构化推理，利用DPP选择关键帧并评估难度，对简单查询快速预测，复杂查询使用时间标记提示分解定位，在零样本视频时间定位中取得SOTA性能。
摘要：
零样本视频时间定位（VTG）无需任务特定训练，即可从自然语言查询中定位未修剪视频中的事件。现有方法依赖于帧-查询特征匹配，这足以处理简单事件，但难以应对需要理解时间顺序和因果结构的复杂多阶段查询——我们将这种差异称为推理差距。我们提出DART（难度自适应时间定位路由），通过将难度感知路由与大型视觉-语言模型中的结构化推理相结合来弥合这一差距。查询条件行列式点过程（DPP）具有双重作用：选择多样且与查询相关的关键帧作为时间证据，并提供谱熵作为难度指标。简单查询路由到快速路径进行直接预测，而复杂查询则遵循慢速路径，使用时间标记提示，将定位分解为全局事件分析、每帧时间角色标注和边界提取。在Charades-STA和ActivityNet Captions上，DART在独立同分布和多种分布外设置中均实现了最先进的零样本性能，在比最强基线少使用7倍以上帧的情况下，mIoU提升了高达3.5个百分点。项目主页见该URL。
英文摘要：
Zero-shot video temporal grounding (VTG) localizes events in untrimmed videos from natural language queries without task-specific training. Existing methods rely on frame-query feature matching, which suffices for simple events but struggles with complex multi-stage queries that require understanding temporal ordering and causal structure -- a disparity we call the reasoning gap. We propose DART (Difficulty-Adaptive Routing for Temporal Grounding), which bridges this gap by coupling difficulty-aware routing with structured reasoning in large vision-language models. A query-conditioned Determinantal Point Process (DPP) serves a dual role: selecting diverse, query-relevant keyframes as temporal evidence, and providing spectral entropy as a difficulty indicator. Simple queries are routed to a Fast path for direct prediction, while complex queries follow a Slow path with Temporal Markup Prompting, which decomposes localization into global event analysis, per-frame temporal role annotation, and boundary extraction. On Charades-STA and ActivityNet Captions, DART achieves state-of-the-art zero-shot performance across both identically distributed and multiple out-of-distribution settings, improving mIoU by up to 3.5 points over the strongest baseline while using over 7 times fewer frames. The project homepage is available at https://dart-vtg.github.io/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
