AdaSpot：将分辨率用在关键处以实现精确事件定位
AdaSpot: Spend Resolution Where It Matters for Precise Event Spotting
提出一种无监督、任务感知的区域选择策略，在低分辨率全局特征引导下自适应选取每帧高分辨率区域，为视频时序动作定位中平衡精度与效率提供了可复用的思路。
原文依据 processes low-resolution videos to extract global task-relevant features while adaptively selecting the most informative region-of-interest in each frame for high-resolution processing
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论精确事件定位旨在以高时序精度定位视频中快速发生的动作或事件，是体育分析、机器人和自主系统应用中的关键任务。现有方法通常均匀处理所有帧，忽略了视频数据中固有的时空冗余。这导致在非信息区域进行冗余计算，同时限制了整体效率。为了保持可处理性，它们通常对输入进行空间下采样，丢失了对精确定位至关重要的细粒度细节。为了解决这些限制，我们提出了AdaSpot，一个简单而有效的框架，它处理低分辨率视频以提取全局任务相关特征，同时自适应地选择每帧中信息量最大的感兴趣区域进行高分辨率处理。选择通过一种无监督、任务感知的策略进行，该策略保持帧间的时空一致性，并避免了可学习替代方案的训练不稳定性。与仅低分辨率基线相比，这种设计以边际计算开销保留了必要的细粒度视觉线索，同时比均匀高分辨率处理高效得多。在标准PES基准上的实验表明，AdaSpot在严格评估指标下达到了最优性能（例如，在Tennis和FineDiving上mAP@0分别提升3.96和2.26），同时在较宽松指标下也保持了强劲结果。代码可在以下网址获取：https://github.com/arturxe2/AdaSpot
英文原文摘要 1528 字符
Precise Event Spotting aims to localize fast-paced actions or events in videos with high temporal precision, a key task for applications in sports analytics, robotics, and autonomous systems. Existing methods typically process all frames uniformly, overlooking the inherent spatio-temporal redundancy in video data. This leads to redundant computation on non-informative regions while limiting overall efficiency. To remain tractable, they often spatially downsample inputs, losing fine-grained details crucial for precise localization. To address these limitations, we propose AdaSpot, a simple yet effective framework that processes low-resolution videos to extract global task-relevant features while adaptively selecting the most informative region-of-interest in each frame for high-resolution processing. The selection is performed via an unsupervised, task-aware strategy that maintains spatio-temporal consistency across frames and avoids the training instability of learnable alternatives. This design preserves essential fine-grained visual cues with a marginal computational overhead compared to low-resolution-only baselines, while remaining far more efficient than uniform high-resolution processing. Experiments on standard PES benchmarks demonstrate that AdaSpot achieves state-of-the-art performance under strict evaluation metrics (e.g., +3.96 and +2.26 mAP@0 frames on Tennis and FineDiving), while also maintaining strong results under looser metrics. Code is available at: https://github.com/arturxe2/AdaSpot