Construct Dynamic Graphs for Hand Gesture Recognition via Spatial-Temporal Attention
Construct Dynamic Graphs for Hand Gesture Recognition via Spatial-Temporal Attention
复制标题
DOI：
--
复制
发表时间：
2019-07
期刊：
影响因子：
--
通讯作者：
Yuxiao Chen;Long Zhao;Xi Peng;Jianbo Yuan;Dimitris N. Metaxas
中科院分区：
文献类型：
--
作者：
Yuxiao Chen;Long Zhao;Xi Peng;Jianbo Yuan;Dimitris N. Metaxas
提出了一种基于动态图的时空注意力（DG-STA）手势识别方法。其关键思想是首先从手部骨架构建一个全连接图，然后通过在空间和时间域中执行的自注意机制自动学习节点特征和边缘。我们进一步建议利用联合位置的时空线索，以保证在具有挑战性的条件下的鲁棒识别。此外，一种新的时空掩模被应用到显着减少99%的计算成本。我们进行了大量的实验基准（DHG-14/28和SHREC'17），并证明了我们的方法相比，国家的最先进的方法的上级性能。源代码可以在这个https URL上找到。
We propose a Dynamic Graph-Based Spatial-Temporal Attention (DG-STA) method for hand gesture recognition. The key idea is to first construct a fully-connected graph from a hand skeleton, where the node features and edges are then automatically learned via a self-attention mechanism that performs in both spatial and temporal domains. We further propose to leverage the spatial-temporal cues of joint positions to guarantee robust recognition in challenging conditions. In addition, a novel spatial-temporal mask is applied to significantly cut down the computational cost by 99%. We carry out extensive experiments on benchmarks (DHG-14/28 and SHREC'17) and prove the superior performance of our method compared with the state-of-the-art methods. The source code can be found at this https URL.