论文标题
流插图：用胶囊网络进行动作识别的光流估计
FlowCaps: Optical Flow Estimation with Capsule Networks For Action Recognition
论文作者
论文摘要
胶囊网络（CAPSNET）最近显示出在大多数计算机视觉任务中表现出色的希望，尤其是与场景理解有关的承诺。在本文中，我们探讨了CAPSNET在光流估计中的功能，该任务在该任务中，卷积神经网络（CNN）已经超过其他方法。我们提出了一个基于CAPSNET的体系结构，称为流程尺寸，该架构试图a）通过较细粒度，特定于运动的和更解释的编码至关重要的匹配，以适应光流估计，b）执行更好的原始光学流程估计，c）降低了地面真相数据，并降低了计算性的良好效率，d）降低了计算性的复杂性，d）降低了计算性的复杂性，分为成就成就成就成就成就的成就， CNN-CounterParts。
Capsule networks (CapsNets) have recently shown promise to excel in most computer vision tasks, especially pertaining to scene understanding. In this paper, we explore CapsNet's capabilities in optical flow estimation, a task at which convolutional neural networks (CNNs) have already outperformed other approaches. We propose a CapsNet-based architecture, termed FlowCaps, which attempts to a) achieve better correspondence matching via finer-grained, motion-specific, and more-interpretable encoding crucial for optical flow estimation, b) perform better-generalizable optical flow estimation, c) utilize lesser ground truth data, and d) significantly reduce the computational complexity in achieving good performance, in comparison to its CNN-counterparts.
