Cross-View Action Recognition via a Continuous Virtual Path
Citations Over TimeTop 10% of 2013 papers
Abstract
In this paper, we propose a novel method for cross-view action recognition via a continuous virtual path which connects the source view and the target view. Each point on this virtual path is a virtual view which is obtained by a linear transformation of the action descriptor. All the virtual views are concatenated into an infinite-dimensional feature to characterize continuous changes from the source to the target view. However, these infinite-dimensional features cannot be used directly. Thus, we propose a virtual view kernel to compute the value of similarity between two infinite-dimensional features, which can be readily used to construct any kernelized classifiers. In addition, there are a lot of unlabeled samples from the target view, which can be utilized to improve the performance of classifiers. Thus, we present a constraint strategy to explore the information contained in the unlabeled samples. The rationality behind the constraint is that any action video belongs to only one class. Our method is verified on the IXMAS dataset, and the experimental results demonstrate that our method achieves better performance than the state-of-the-art methods.
Related Papers
- → Hyperspectral image classification using two-channel deep convolutional neural network(2016)137 cited
- → Gabor feature based face recognition using kernel methods(2004)51 cited
- → Face Alignment by Discriminative Feature Learning(2019)5 cited
- An Application of Wavelet Transform in Feature Level Image Fusion and Object Classification(2004)
- → Image-to-image Transformation with Auxiliary Condition(2021)