School of Electronic Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China.
IEEE Trans Image Process. 2015 Oct;24(10):3203-17. doi: 10.1109/TIP.2015.2441634.
This paper develops a human action recognition method for human silhouette sequences based on supervised temporal t-stochastic neighbor embedding (ST-tSNE) and incremental learning. Inspired by the SNE and its variants, ST-tSNE is proposed to learn the underlying relationship between action frames in a manifold, where the class label information and temporal information are introduced to well represent those frames from the same action class. As to the incremental learning, an important step for action recognition, we introduce three methods to perform the low-dimensional embedding of new data. Two of them are motivated by local methods, locally linear embedding and locality preserving projection. Those two techniques are proposed to learn explicit linear representations following the local neighbor relationship, and their effectiveness is investigated for preserving the intrinsic action structure. The rest one is based on manifold-oriented stochastic neighbor projection to find a linear projection from high-dimensional to low-dimensional space capturing the underlying pattern manifold. Extensive experimental results and comparisons with the state-of-the-art methods demonstrate the effectiveness and robustness of the proposed ST-tSNE and incremental learning methods in the human action silhouette analysis.
本文提出了一种基于监督时间 t 随机近邻嵌入（ST-tSNE）和增量学习的人体轮廓序列人体动作识别方法。受 SNE 及其变体的启发，ST-tSNE 被提出用于学习流形中动作帧之间的潜在关系，其中引入了类别标签信息和时间信息，以便很好地表示来自同一动作类别的那些帧。至于增量学习，这是动作识别的重要步骤，我们引入了三种方法来对新数据进行低维嵌入。其中两种方法是受局部方法启发的，即局部线性嵌入和局部保持投影。这两种技术旨在学习遵循局部邻居关系的显式线性表示，并研究其在保持内在动作结构方面的有效性。其余的方法基于面向流形的随机近邻投影，以找到从高维到低维空间的线性投影，从而捕获潜在的模式流形。广泛的实验结果和与最先进方法的比较表明，所提出的 ST-tSNE 和增量学习方法在人体轮廓分析中的有效性和鲁棒性。
