Search Results for author:
Found 2 papers, 0 papers with code
A Generative Approach to Zero-Shot and Few-Shot Action Recognition
In particular, we assume that the distribution parameters for any action class in the visual space can be expressed as a linear combination of a set of basis vectors where the combination weights are given by the attributes of the action class.
A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoders
By extensive testing on four benchmark datasets, we show that our model outperforms the state of the art, particularly in the more realistic generalized setting, where the training classes can also appear at the test time along with the novel classes.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
