This paper proposes a complex recurrent variational autoencoder (VAE) framework, for modeling time series data, particularly speech signals. First, to account for the temporal structure of speech ...

A prototype system that uses a CNN encoder and edge-based features to retrieve visually similar fashion items from the Fashion MNIST dataset using cosine similarity.

A Multimodal Variational Autoencoder (MVAVE) is constructed based on the multi-head self-attention mechanism, incorporating noise injection for denoising to mitigate the impact of data noise on ...

Geometric Dynamic Variational Autoencoders (GD-VAEs) for learning embedding maps for nonlinear dynamics into general latent spaces. This includes methods for standard latent spaces or manifold latent ...