arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.22073cs.CV
收藏

AdaSpot: 在关键区域进行高精度事件定位以实现精确事件检测

AdaSpot: Spend Resolution Where It Matters for Precise Event Spotting

Universitat de Barcelona(巴塞罗那大学);Computer Vision Center(计算机视觉中心);Aalborg University(阿勒斯大学)

Artur Xarles, Sergio Escalera, Thomas B. Moeslund, Albert Clapés

AI总结:

AdaSpot通过自适应选择关键区域进行高分辨率处理,实现高精度事件检测,提升效率并取得最佳性能。

摘要:

精确事件检测旨在对视频中的快速动作或事件进行高时间精度的定位,是体育分析、机器人和自主系统应用中的关键任务。现有方法通常对所有帧进行统一处理,忽略了视频数据中固有的时空冗余性。这导致在非信息性区域进行冗余计算,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,从而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,该框架处理低分辨率视频以提取全局任务相关特征,同时在每个帧中自适应地选择最信息性的感兴趣区域进行高分辨率处理。选择过程通过一种无监督且任务感知的策略进行,该策略在帧之间保持时空一致性,并避免了可学习替代方案的训练不稳定性。这种设计在略微增加计算开销的情况下保留了必要的细粒度视觉线索,与仅使用低分辨率的基线相比,其计算开销更小,同时远比统一的高分辨率处理更高效。在标准PES基准测试中,实验表明AdaSpot在严格评估指标(例如,网球和FineDiving上分别提高3.96和2.26 mAP@0帧)下实现了最先进的性能,同时在较宽松的指标下也保持了强劲的结果。代码可在:https://github.com/arturxe2/AdaSpot上获得。

英文摘要:

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 \textbf{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 \textbf{AdaSpot} achieves state-of-the-art performance under strict evaluation metrics (\eg, $+3.96$ and $+2.26$ mAP$@0$ frames on Tennis and FineDiving), while also maintaining strong results under looser metrics. Code is available at: \href{https://github.com/arturxe2/AdaSpot}{https://github.com/arturxe2/AdaSpot}.

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。

↑