识别节奏变化的视频事件
Recognizing Video Events with Varying Rhythms
摘要：
识别视频事件的长，复杂的视频与多个子活动最近一直受到关注。这项任务比传统的动作识别更具有挑战性，相对均匀的短视频剪辑。在本文中，我们探讨了识别长而复杂的事件与不同的动作节奏，这在文献中没有被考虑，但实际上是一个挑战的问题。我们的工作部分受到人类如何识别具有不同节奏的事件的启发：快速捕捉对特定事件贡献最大的帧。我们提出了一个两阶段的\emph{end-to-end}框架，其中第一阶段选择最重要的帧，而第二阶段使用所选择的帧识别事件。我们的模型在训练阶段只需要\emph{event-level labels}，因此当子活动标签丢失或难以获得时更实用。大量的实验结果表明，我们的模型可以实现显着提高事件识别从长视频，同时保持高精度，即使测试视频遭受严重的节奏变化。这证明了我们的方法在现实世界中基于视频的应用中的潜力，其中测试和训练视频在子活动的节奏上可能会有很大的不同。
英文摘要：
Recognizing Video events in long, complex videos with multiple sub-activities has received persistent attention recently. This task is more challenging than traditional action recognition with short, relatively homogeneous video clips. In this paper, we investigate the problem of recognizing long and complex events with varying action rhythms, which has not been considered in the literature but is a practical challenge. Our work is inspired in part by how humans identify events with varying rhythms: quickly catching frames contributing most to a specific event. We propose a two-stage \emph{end-to-end} framework, in which the first stage selects the most significant frames while the second stage recognizes the event using the selected frames. Our model needs only \emph{event-level labels} in the training stage, and thus is more practical when the sub-activity labels are missing or difficult to obtain. The results of extensive experiments show that our model can achieve significant improvement in event recognition from long videos while maintaining high accuracy even if the test videos suffer from severe rhythm changes. This demonstrates the potential of our method for real-world video-based applications, where test and training videos can differ drastically in rhythms of sub-activities.
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。
