Topic models have evolved from conventional Bayesian probabilistic model...
Few-shot video segmentation is the task of delineating a specific novel ...
Estimating the parameters of a probabilistic directed graphical model fr...
Deep learning models, even the-state-of-the-art ones, are highly vulnera...
Multiscale video transformers have been explored in a wide variety of vi...
Neural processes (NPs) have brought the representation power of parametr...
We study the problem of imputing missing values in a dataset, which has
...
Learning deep discrete latent presentations offers a promise of better
s...
Few-shot classification aims to learn a classifier to recognize unseen
c...
Uncertainty estimation is essential to make neural networks trustworthy ...
Interpretable machine learning seeks to understand the reasoning process...
This paper investigates the modeling of automated machine description on...
Imbalanced data pose challenges for deep learning based classification
m...
In this paper, we study the problem of procedure planning in instruction...
A topic model is often formulated as a generative model that explains ho...
It is well-known that deep neural networks (DNNs) are susceptible to
adv...
Neural topic models (NTMs) apply deep neural networks to topic modelling...
Video predictive understanding encompasses a wide range of efforts that ...
Early action recognition (action prediction) from limited preliminary
ob...
There has been recently a growing interest in studying adversarial examp...
Topic modelling has been a successful technique for text analysis for al...
Contrastive learning (CL) has recently emerged as an effective approach ...
Training robust deep learning models for down-stream tasks is a critical...
Deep neural network image classifiers are reported to be susceptible to
...
Ensemble-based adversarial training is a principled approach to achieve
...
In this paper, we present a new topic modelling approach via the theory ...
Deep neural network based image classification methods usually require a...
Obtaining training data for multi-document summarization (MDS) is time
c...
The fact that deep neural networks are susceptible to crafted perturbati...
Matrix factorization (MF) has been widely applied to collaborative filte...
Deep neural network image classifiers are reported to be susceptible to
...
It is always well believed that Binary Neural Networks (BNNs) could
dras...
Many applications, such as text modelling, high-throughput sequencing, a...
Re-identifying a person across multiple disjoint camera views is importa...
Recently, considerable research effort has been devoted to developing de...
Stochastic microstructure reconstruction has become an indispensable par...
Besides the text content, documents and their associated words usually c...
Relational data are usually highly incomplete in practice, which inspire...
This paper aims at synthesizing filamentary structured images such as re...