IEEE Trans Image Process. 2017 Jun;26(6):3028-3037. doi: 10.1109/TIP.2017.2696786. Epub 2017 Apr 24.
Classifying human actions from varied views is challenging due to huge data variations in different views. The key to this problem is to learn discriminative view-invariant features robust to view variations. In this paper, we address this problem by learning view-specific and view-shared features using novel deep models. View-specific features capture unique dynamics of each view while view-shared features encode common patterns across views. A novel sample-affinity matrix is introduced in learning shared features, which accurately balances information transfer within the samples from multiple views and limits the transfer across samples. This allows us to learn more discriminative shared features robust to view variations. In addition, the incoherence between the two types of features is encouraged to reduce information redundancy and exploit discriminative information in them separately. The discriminative power of the learned features is further improved by encouraging features in the same categories to be geometrically closer. Robust view-invariant features are finally learned by stacking several layers of features. Experimental results on three multi-view data sets show that our approaches outperform the state-of-the-art approaches.
由于不同视角下的数据变化巨大，因此从多种视角对人类行为进行分类具有挑战性。解决此问题的关键是学习对视图变化具有鲁棒性的判别视图不变特征。在本文中，我们通过使用新颖的深度模型来学习特定于视图和共享视图的特征来解决此问题。特定于视图的特征捕获每个视图的独特动态，而共享视图的特征则在视图之间编码通用模式。在学习共享特征时引入了新颖的样本亲和度矩阵，该矩阵可以准确地平衡来自多个视图的样本内的信息传递，并限制样本间的传递。这使我们能够学习更具判别力的共享特征，从而对视图变化具有鲁棒性。此外，鼓励两种类型的特征之间的不协调性，以减少信息冗余并分别利用其中的判别信息。通过鼓励同一类别中的特征在几何上更接近，进一步提高了学习到的特征的判别力。最后，通过堆叠多个特征层来学习鲁棒的视图不变特征。在三个多视图数据集上的实验结果表明，我们的方法优于最先进的方法。
