论文标题
改善基于骨架的动作识别，并具有强大的空间和时间特征
Improving Skeleton-based Action Recognitionwith Robust Spatial and Temporal Features
论文作者
论文摘要
最近，基于骨架的动作识别已在计算机视觉社区中取得了显着的进步。大多数最先进的算法基于图形卷积网络（GCN），并且可以改善骨干GCN Lay-ers的网络结构。在本文中，我们提出了一种新的机制，可以在时空中学习更多鲁棒性的特征。更具体地说，我们将Adiscriminative特征学习（DFL）分支添加到最后一层，以提取歧视性的空间和时间特征，以帮助对学习进行规范。我们还正式主张使用方向不变特征（DIF）作为神经网络的输入。当这些可靠的功能学习和使用时，我们可以显示该识别精度可以提高。我们将我们的结果与四个数据集中的ST-GCNAND相关方法的结果进行了比较：NTU-RGBD60，NTU-RGBD120，SYSU 3DHOI和Skeleton-Keleton-Keleton-intetics。
Recently skeleton-based action recognition has made signif-icant progresses in the computer vision community. Most state-of-the-art algorithms are based on Graph Convolutional Networks (GCN), andtarget at improving the network structure of the backbone GCN lay-ers. In this paper, we propose a novel mechanism to learn more robustdiscriminative features in space and time. More specifically, we add aDiscriminative Feature Learning (DFL) branch to the last layers of thenetwork to extract discriminative spatial and temporal features to helpregularize the learning. We also formally advocate the use of Direction-Invariant Features (DIF) as input to the neural networks. We show thataction recognition accuracy can be improved when these robust featuresare learned and used. We compare our results with those of ST-GCNand related methods on four datasets: NTU-RGBD60, NTU-RGBD120,SYSU 3DHOI and Skeleton-Kinetics.
