LAP-Net：通过学习动作进展的自适应特征采样用于在线动作检测
LAP-Net: Adaptive Features Sampling via Learning Action Progression for Online Action Detection
摘要：
在线动作检测是一项任务，目的是从流视频中识别正在进行的动作，而无需任何辅助信息或访问未来的帧。最近提出的方法聚合固定的时间范围内不可见的，但预期的未来帧表示作为补充功能，并取得了良好的性能。它们基于这样的观察：人类经常通过同时考虑未来的愿景来检测正在进行的行动。然而，我们观察到，在不同的行动进展，最佳的补充功能，应获得不同的时间范围，而不是简单地固定未来的时间范围。为此，我们引入了自适应特征采样策略，以克服上述可变范围的最佳补充功能。具体来说，在本文中，我们提出了一种新的学习动作进展网络称为LAP网络，它集成了自适应特征采样策略。在每个时间步，该采样策略首先估计当前动作进展，然后决定应该使用什么时间范围来聚合最佳补充特征。我们在三个基准数据集（TVSeries、THUMOS-14和HDD）上评估了我们的LAP-Net。大量的实验表明，与我们的自适应特征采样策略，提出的LAP网络可以显着优于当前国家的最先进的方法有很大的利润。
英文摘要：
Online action detection is a task with the aim of identifying ongoing actions from streaming videos without any side information or access to future frames. Recent methods proposed to aggregate fixed temporal ranges of invisible but anticipated future frames representations as supplementary features and achieved promising performance. They are based on the observation that human beings often detect ongoing actions by contemplating the future vision simultaneously. However, we observed that at different action progressions, the optimal supplementary features should be obtained from distinct temporal ranges instead of simply fixed future temporal ranges. To this end, we introduce an adaptive features sampling strategy to overcome the mentioned variable-ranges of optimal supplementary features. Specifically, in this paper, we propose a novel Learning Action Progression Network termed LAP-Net, which integrates an adaptive features sampling strategy. At each time step, this sampling strategy first estimates current action progression and then decide what temporal ranges should be used to aggregate the optimal supplementary features. We evaluated our LAP-Net on three benchmark datasets, TVSeries, THUMOS-14 and HDD. The extensive experiments demonstrate that with our adaptive feature sampling strategy, the proposed LAP-Net can significantly outperform current state-of-the-art methods with a large margin.
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。
