Attention operators have been applied on both 1-D data like texts and higher-order data
such as images and videos. Use of attention operators on high-order data requires flattening …

Variational autoencoders (VAEs) are a powerful class of deep generative latent variable
model for unsupervised representation learning on high-dimensional data. To ensure …

Spatial transcriptomics data is invaluable for understanding the spatial organization of gene
expression in tissues. There have been consistent efforts in studying how to effectively utilize …

Capsule networks get achievements in many computer vision tasks. However, in the field of
image generation, they have huge room for improvement compared with the mainstream …

Temporal anomaly detection looks for irregularities over space-time. Unsupervised temporal
models employed thus far typically work on sequences of feature vectors, and much less on …

Variational autoencoders (VAEs) are currently popular deep generative models that
demonstrate powerful performance in various applications. However, VAEs have a tendency …

Recently, deep generative models have made significant progress in handling missing data,
with the most notable being the use of variational autoencoders (VAEs). However, most of …

This thesis investigates temporal data relationships, discerning dependencies across time,
modalities, and data instances in a tempo-relational database. Through reproducible …

Tomato is one of the main vegetables worldwide due to its versatility of use and its economic
impact. However, climate change has caused the management of pests and diseases to be …

Even though asbestos has been banned for a long time, patients are still presenting with
asbestos-related diseases due to the long incubation time. To assist clinicians in quantifying …