Order-Preserving Wasserstein Discriminant Analysis
Order-Preserving Wasserstein Discriminant Analysis
复制标题
DOI：
10.1109/iccv.2019.00998
复制
发表时间：
2019-10
期刊：
影响因子：
--
通讯作者：
Bing Su;Jiahuan Zhou;Ying Wu
中科院分区：
文献类型：
--
作者：
Bing Su;Jiahuan Zhou;Ying Wu
序列数据的监督降维将序列中的观测数据投影到低维子空间，以更好地分离不同的序列类别。对于静态数据，它通常比传统的降维更具挑战性，因为测量序列的可分性涉及处理时间结构的非线性过程。本文提出了一种线性方法，即保序Wasserstein判别分析(OWDA)，它通过最大化类间距离和最小化类内散度来学习投影。对于每一类，Owda提取保持有序的Wasserstein重心，并将训练序列在重心周围的离散度作为类内散布来构造。类间距离被测量为相应重心之间的保序Wasserstein距离。Owda通过解除带有时间约束的几何关系，能够专注于类之间的显著差异。实验表明，Owda在三个3D动作识别数据集上取得了与之相当的结果。
Supervised dimensionality reduction for sequence data projects the observations in sequences onto a low-dimensional subspace to better separate different sequence classes. It is typically more challenging than conventional dimensionality reduction for static data, because measuring the separability of sequences involves non-linear procedures to manipulate the temporal structures. This paper presents a linear method, namely Order-preserving Wasserstein Discriminant Analysis (OWDA), which learns the projection by maximizing the inter-class distance and minimizing the intra-class scatter. For each class, OWDA extracts the order-preserving Wasserstein barycenter and constructs the intra-class scatter as the dispersion of the training sequences around the barycenter. The inter-class distance is measured as the order-preserving Wasserstein distance between the corresponding barycenters. OWDA is able to concentrate on the distinctive differences among classes by lifting the geometric relations with temporal constraints. Experiments show that OWDA achieves competitive results on three 3D action recognition datasets.