论文标题
带有时间缓冲的流媒体视频中的在线操作检测
Online Action Detection in Streaming Videos with Time Buffers
论文作者
论文摘要
我们在实时流媒体视频中提出了在线时间动作检测的问题，承认实时流媒体视频的一个重要属性，即通常在最新捕获的框架和受众观看的实际框架之间存在广播延迟。在线操作检测任务的标准设置需要在捕获新框架后立即进行预测。我们说明，缺乏对延迟的考虑是对模型施加不必要的限制，因此不适合此问题。我们建议采用问题设置，该设置允许模型使用实时流媒体视频的延迟产生的小“缓冲时间”。我们设计了一个在线的动作启动和终端检测框架，并使用两个主要组件进行缓冲区设置：扁平的i3d和基于窗口的抑制作用。在拟议的设置下，对三个标准的时间动作检测基准进行了实验证明了拟议框架的有效性。我们表明，通过为此问题设置合适的问题，与现成的在线操作检测模型相比，我们可以获得更好的检测准确性。
We formulate the problem of online temporal action detection in live streaming videos, acknowledging one important property of live streaming videos that there is normally a broadcast delay between the latest captured frame and the actual frame viewed by the audience. The standard setting of the online action detection task requires immediate prediction after a new frame is captured. We illustrate that its lack of consideration of the delay is imposing unnecessary constraints on the models and thus not suitable for this problem. We propose to adopt the problem setting that allows models to make use of the small `buffer time' incurred by the delay in live streaming videos. We design an action start and end detection framework for this online with buffer setting with two major components: flattened I3D and window-based suppression. Experiments on three standard temporal action detection benchmarks under the proposed setting demonstrate the effectiveness of the proposed framework. We show that by having a suitable problem setting for this problem with wide-applications, we can achieve much better detection accuracy than off-the-shelf online action detection models.
