Generalized zero-shot learning aims to recognize images from seen and unseen domains.
Recent methods focus on learning a unified semantic-aligned visual representation to …

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 casts light on lacking unseen class data by transferring knowledge from
seen classes via a joint semantic space. However, the distributions of samples from seen …

Class-Incremental Learning (CIL) aims to train a reliable model with the streaming data,
which emerges unknown classes sequentially. Different from traditional closed set learning …

This paper proposes a novel model for recognizing images with composite attribute-object
concepts, notably for composite concepts that are unseen during model training. We aim to …

Generalized zero-shot Learning (GZSL) aims to recognize images from either seen or
unseen domain, mainly by learning a joint embedding space to associate image features …

Traditional 3D point cloud classification tasks focus on training a classifier in the closed-set
scenario, where training and test data have the same label set and the same data …

Zero-Shot Learning (ZSL) aims to recognize images from seen and unseen classes by
aligning visual and semantic knowledge (eg, attribute descriptions). However, the fine …

Zero-shot learning (ZSL) aims to recognize novel categories by merely utilizing disjoint seen
samples. It is a challenging task as the knowledge of unseen objects is forbidden in the …

Few-Shot transfer learning has become a major focus of research as it allows recognition of
new classes with limited labeled data. While it is assumed that train and test data have the …