论文标题
单阶段时间动作本地化网络中的边界不确定性
Boundary Uncertainty in a Single-Stage Temporal Action Localization Network
论文作者
论文摘要
在本文中，我们通过单个阶段神经网络解决了时间动作定位的问题。在拟议的体系结构中，我们将边界预测建模为单差异高斯分布，以模拟其不确定性，这是我们最大程度地了解该领域的第一个。我们使用两个不确定性的边界回归损失：首先，边界的地面真相位置与高斯建模边界的预测和第二，同一高斯下$ \ ell_1 $损失的期望之间的kullback-leibler差异。我们表明，两种不确定性建模方法都将检测性能提高了$ 1.5 \％$ $@tim@tiou = 0.5，并且提出的简单单阶段网络的性能与更复杂的一个和两个阶段网络紧密相关。
In this paper, we address the problem of temporal action localization with a single stage neural network. In the proposed architecture we model the boundary predictions as uni-variate Gaussian distributions in order to model their uncertainties, which is the first in this area to the best of our knowledge. We use two uncertainty-aware boundary regression losses: first, the Kullback-Leibler divergence between the ground truth location of the boundary and the Gaussian modeling the prediction of the boundary and second, the expectation of the $\ell_1$ loss under the same Gaussian. We show that with both uncertainty modeling approaches improve the detection performance by more than $1.5\%$ in mAP@tIoU=0.5 and that the proposed simple one-stage network performs closely to more complex one and two stage networks.
