Topic modelling is the new revolution in text mining. It is a statistical technique for revealing
the underlying semantic structure in large collection of documents. After analysing …

Mainstream statistical methodology is generally applicable to data observed in Euclidean
space. There are, however, numerous contexts of considerable scientific interest in which …

Prevalent semantic segmentation solutions are, in essence, a dense discriminative classifier
of p (class| pixel feature). Though straightforward, this de facto paradigm neglects the …

Few-shot segmentation is challenging because objects within the support and query images
could significantly differ in appearance and pose. Using a single prototype acquired directly …

Detecting out-of-distribution (OOD) objects is indispensable for safely deploying object
detectors in the wild. Although distance-based OOD detection methods have demonstrated …

Despite the fact that Second Order Similarity (SOS) has been used with significant success
in tasks such as graph matching and clustering, it has not been exploited for learning local …

From sequences of speech sounds, or letters, humans can extract rich and nuanced
meaning through language. This capacity is essential for human communication. Yet …

The Variational Auto-Encoder (VAE) is one of the most used unsupervised machine learning
models. But although the default choice of a Gaussian distribution for both the prior and …

Resting-state functional magnetic resonance imaging (rs-fMRI) allows estimation of
individual-specific cortical parcellations. We have previously developed a multi-session …

Temperature is a major environmental cue affecting plant growth and development. Plants
often experience higher temperatures in the context of a 24 h day–night cycle, with …