Although supervised deep learning has revolutionized speech and audio processing, it has
necessitated the building of specialist models for individual tasks and application scenarios …

Multimodal learning is a framework for building models that make predictions based on
different types of modalities. Important challenges in multimodal learning are the inference of …

Existing multi-view classification algorithms focus on promoting accuracy by exploiting
different views, typically integrating them into common representations for follow-up tasks …

Multimodal representation learning, which aims to narrow the heterogeneity gap among
different modalities, plays an indispensable role in the utilization of ubiquitous multimodal …

Learning generative models that span multiple data modalities, such as vision and
language, is often motivated by the desire to learn more useful, generalisable …

Multiple modalities often co-occur when describing natural phenomena. Learning a joint
representation of these modalities should yield deeper and more useful representations …

Although multi-view learning has made significant progress over the past few decades, it is
still challenging due to the difficulty in modeling complex correlations among different views …

Crucial transitions in cancer—including tumor initiation, local expansion, metastasis, and
therapeutic resistance—involve complex interactions between cells within the dynamic …

Understanding human behaviors and intents from videos is a challenging task. Video flows
usually involve time-series data from different modalities, such as natural language, facial …

Variational autoencoders (VAE) are a powerful and widely-used class of models to learn
complex data distributions in an unsupervised fashion. One important limitation of VAEs is …