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 virtu al views are concatenated into an in?nite-dimensional feature to characterize continuous changes from the source to the target view. However, these in?nite-dimensional features cannot be used directly. Thus, we propose a virtual view kernel to compute the value of similarity between two in?nite-dimensional features, which can be readily used to construct any kernelized classi?ers. In addition, there are a lot of unlabeled samples from the target view, which can be utilized to improve the performance of classi?ers. 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 veri?ed on the IXMAS dataset, and the experimental results demonstrate that our method achieves better performance than the state-of-the-art methods.