Graph Neural Networks (GNNs) have gained momentum in graph representation learning
and boosted the state of the art in a variety of areas, such as data mining (\emph {eg,} social …

Deep learning (DL) has proven to be a highly effective approach for developing models in
diverse contexts, including visual perception, speech recognition, and machine translation …

Referring image segmentation (RIS) aims to find a segmentation mask given a referring
expression grounded to a region of the input image. Collecting labelled datasets for this …

While deep learning strategies achieve outstanding results in computer vision tasks, one
issue remains: The current strategies rely heavily on a huge amount of labeled data. In many …

Network anomaly detection, also known as graph anomaly detection, aims to find network
elements (eg, nodes, edges, subgraphs) with significantly different behaviors from the vast …

Abstract Generalized Zero-Shot Learning (GZSL) aims to recognize new categories with
auxiliary semantic information, eg, category attributes. In this paper, we handle the critical …

Zero-shot learning (ZSL), an emerging topic in recent years, targets at distinguishing unseen
class images by taking images from seen classes for training the classifier. Existing works …

Convolution-based and Transformer-based vision backbone networks process images into
the grid or sequence structures, respectively, which are inflexible for capturing irregular …

Generalized zero-shot learning (GZSL) aims to recognize objects from both seen and
unseen classes when only the labeled examples from seen classes are provided. Recent …

Abstract Graph Convolutional Networks (GCNs), which can integrate both explicit
knowledge and implicit knowledge together, have shown effectively for zero-shot learning …