Deep Learning has implemented a wide range of applications and has become increasingly
popular in recent years. The goal of multimodal deep learning is to create models that can …

Despite the remarkable success of deep multi-modal learning in practice, it has not been
well-explained in theory. Recently, it has been observed that the best uni-modal network …

Sketch-based image retrieval (SBIR) is challenging due to the inherent domain-gap
between sketch and photo. Compared with pixel-perfect depictions of photos, sketches are …

Sparse representation based methods have demonstrated their superior performance in
target detection tasks compared to more traditional approaches such as matched subspace …

In acoustic event recognition (AER), it is important to extract semantic features. As two
crucial aspects of semantic features, the essential content and the temporal structure can …

In this paper, we present a novel multimodal sparse dictionary learning algorithm based on
a hierarchical sparse Bayesian framework. The framework allows for enforcing joint sparsity …

This paper addresses the problem of learning dictionaries for multimodal datasets, ie
datasets collected from multiple data sources. We present an algorithm called multimodal …

Sparsity plays an essential role in a number of modern algorithms. This thesis examines
how we can incorporate additional structural information within the sparsity profile and …