In this paper, we study the problem of learning Graph Neural Networks (GNNs) with
Differential Privacy (DP). We propose a novel differentially private GNN based on …

A distance metric known as non‐Euclidean distance deviates from the laws of Euclidean
geometry, which is the geometry that governs most physical spaces. It is utilized when …

In computer vision tasks, features often come from diverse representations, domains, and
modalities, such as text, images, and videos. Effectively fusing these features is essential for …

In this paper a pure-attention bottom-up approach, called ViGAT, that utilizes an object
detector together with a Vision Transformer (ViT) backbone network to derive object and …

The apparent" black box" nature of neural networks is a barrier to adoption in applications
where explainability is essential. This paper presents TAME (Trainable Attention Mechanism …

This survey considers the vision of TV broadcasting where content is personalised and
personalisation is data-driven, looks at the AI and data technologies making this possible …

Unsupervised video hashing aims to learn a nonlinear hashing function to map videos into a
similarity-preserving hamming space without label supervision. Different from static images …

Proactivity in robot assistance refers to the robot's ability to anticipate user needs and
perform assistive actions without explicit requests. This requires understanding user …

In this paper, Gated-ViGAT, an efficient approach for video event recognition, utilizing bottom-
up (object) information, a new frame sampling policy and a gating mechanism is proposed …

Graph Neural Networks (GNNs) have become a popular tool for learning on graphs, but their
widespread use raises privacy concerns as graph data can contain personal or sensitive …