Human action recognition is an important branch of computer vision science. It is a challenging task based on skeletal data because of joints’ complex spatiotemporal information. In this work, we propose a method for action recognition, which consists of three parts: view-independent representation, frame interpolation, and combined model. First, the action sequence becomes view-independent representations independent of the view. Second, when judgment conditions are met, differentiated frame interpolations are used to expand the temporal dimensional information. Then, a combined model is adopted to extract these representation features and classify actions. Experimental results on two multi-view benchmark datasets Northwestern-UCLA and NTU RGB+D demonstrate the effectiveness of our complete method. Although using only one type of action feature and a simple architecture combined model, our complete method still outperforms most of the referential state-of-the-art methods and has strong robustness.

人体动作识别是计算机视觉科学的重要分支。由于关节复杂的时空信息，基于骨骼数据这是一项艰巨的任务。在这项工作中，我们提出了一种动作识别方法，该方法包括三个部分：独立于视图的表示，帧插值和组合模型。首先，动作序列成为独立于视图的视图无关表示。其次，当满足判断条件时，使用差分帧插值来扩展时间维信息。然后，采用组合模型提取这些表示特征并对动作进行分类。在两个多视图基准数据集Northwestern-UCLA和NTU RGB + D上的实验结果证明了我们完整方法的有效性。