This paper presents a new supervised representation learning framework, namely structured
probabilistic coding (SPC), to learn compact and informative representations from input …

As a fundamental problem in multimodal learning multimodal fusion aims to compensate for
the inherent limitations of a single modality. One challenge of multimodal fusion is that the …

Probabilistic embeddings have several advantages over deterministic embeddings as they
map each data point to a distribution, which better describes the uncertainty and complexity …

This paper proposes an information-theoretic representation learning framework, named
conditional information flow maximization, to extract noise-invariant sufficient …

An information bottleneck (IB) enables the acquisition of useful representations from data by
retaining necessary information while reducing unnecessary information. In its objective …

In most re-identification approaches, embedding vectors are compared to identify the best
match for a given query. However, this comparison does not take into account whether the …