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 (eg, social network …

Visual anomaly classification and segmentation are vital for automating industrial quality
inspection. The focus of prior research in the field has been on training custom models for …

Continual Learning aims to learn a single model on a sequence of tasks without having
access to data from previous tasks. The biggest challenge in the domain still remains …

Abstract Compositional Zero-Shot Learning (CZSL) aims to recognize novel concepts
formed by known states and objects during training. Existing methods either learn the …

Graph learning plays a pivotal role and has gained significant attention in various
application scenarios, from social network analysis to recommendation systems, for its …

Recent works have shown that unstructured text (documents) from online sources can serve
as useful auxiliary information for zero-shot image classification. However, these methods …

Compositional zero-shot learning (CZSL) aims at learning visual concepts (ie, attributes and
objects) from seen compositions and combining concept knowledge into unseen …

We study the problem of compositional zero-shot learning for object-attribute recognition.
Prior works use visual features extracted with a backbone network, pre-trained for object …

Abstract Compositional Zero-Shot Learning (CZSL) aims to recognize unseen attribute-
object pairs based on a limited set of observed examples. Current CZSL methodologies …

Despite the tremendous progress in zero-shot learning (ZSL), the majority of existing
methods still rely on human-annotated attributes, which are difficult to annotate and scale …