论文标题
Argus ++：无约束视频流的强大实时活动检测，并带有重叠的立方体建议
Argus++: Robust Real-time Activity Detection for Unconstrained Video Streams with Overlapping Cube Proposals
论文作者
论文摘要
活动检测是利用广泛安装相机捕获的视频流的有吸引力的计算机视觉任务之一。尽管达到令人印象深刻的性能，但常规的活动检测算法通常是在某些约束下设计的，例如使用修剪和/或以对象为中心的视频剪辑作为输入。因此，他们未能在现实世界中未约束的视频流中处理多尺度的多构想案例，这些案例未经限制并且具有较大的视野。流式分析的实时要求也标志着它们不可行的蛮力扩展。 为了克服这些问题，我们提出了Argus ++，这是一个可靠的实时活动检测系统，用于分析不受约束的视频流。 Argus ++的设计引入了重叠的时空数据集，作为活动建议的中间概念，以确保通过过度采样的覆盖范围和完整性。整体系统已优化用于对独立消费级硬件进行实时处理。对不同监视和驾驶场景进行的广泛实验证明了其在一系列活动检测基准中的表现，包括CVPR ActivityNet Actev 2021，NIST Actev SDL UF/KF，Trecvid Actev 2020/2021和ICCV Road 2021。
Activity detection is one of the attractive computer vision tasks to exploit the video streams captured by widely installed cameras. Although achieving impressive performance, conventional activity detection algorithms are usually designed under certain constraints, such as using trimmed and/or object-centered video clips as inputs. Therefore, they failed to deal with the multi-scale multi-instance cases in real-world unconstrained video streams, which are untrimmed and have large field-of-views. Real-time requirements for streaming analysis also mark brute force expansion of them unfeasible. To overcome these issues, we propose Argus++, a robust real-time activity detection system for analyzing unconstrained video streams. The design of Argus++ introduces overlapping spatio-temporal cubes as an intermediate concept of activity proposals to ensure coverage and completeness of activity detection through over-sampling. The overall system is optimized for real-time processing on standalone consumer-level hardware. Extensive experiments on different surveillance and driving scenarios demonstrated its superior performance in a series of activity detection benchmarks, including CVPR ActivityNet ActEV 2021, NIST ActEV SDL UF/KF, TRECVID ActEV 2020/2021, and ICCV ROAD 2021.
