Zero-shot learning (ZSL) is an extreme case of transfer learning that aims to recognize
samples (eg, images) of unseen classes relying on a train-set covering only seen classes …

The excellent generalization capability of pre-trained Vision-Language Models (VLMs)
makes fine-tuning VLMs for downstream zero-shot tasks a popular choice. Despite …

Unsupervised domain adaptation (UDA) aims at transferring knowledge from one labeled
source domain to a related but unlabeled target domain. Recently, active domain adaptation …

Zero-Shot Learning (ZSL) aims to recognize unseen classes by generalizing the knowledge,
ie, visual and semantic relationships, obtained from seen classes, where image …

Deep Learning (DL) models have been widely deployed on IoT devices with the help of
advancements in DL algorithms and chips. However, the limited resources of edge devices …

Generalized Zero-Shot Learning (GZSL) aims to recognize images not only for seen classes
but also for unseen ones by transferring semantic-visual relationships from the seen to the …

A serious issue that harms the performance of zero-shot visual recognition is named
objective misalignment, ie, the learning objective prioritizes improving the recognition …

Visual grounding (VG) locates target objects in visual scenes by understanding given
natural language queries. Current methods for VG mainly focus on grounding referring …

Abstract Open-set Domain Adaptation (OSDA) aims to recognize classes in the target
domain that are seen in the source domain while rejecting other unseen target-exclusive …

Abstract Zero-Shot Learning (ZSL) involves transferring knowledge from seen classes to
unseen classes by establishing connections between visual and semantic spaces …