English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

With the ever-increasing amount of data, the central challenge in multimodallearning involves limitations of labelled samples. For the task ofclassification, techniques such as meta-learning, zero-shot learning, andfew-shot learning showcase the ability to learn information about novel classesbased on prior knowledge. Recent techniques try to learn a cross-modal mappingbetween the semantic space and the image space. However, they tend to ignorethe local and global semantic knowledge. To overcome this problem, we propose aMultimodal Variational Auto-Encoder (M-VAE) which can learn the shared latentspace of image features and the semantic space. In our approach we concatenatemultimodal data to a single embedding before passing it to the VAE for learningthe latent space. We propose the use of a multi-modal loss during thereconstruction of the feature embedding through the decoder. Our approach iscapable to correlating modalities and exploit the local and global semanticknowledge for novel sample predictions. Our experimental results using a MLPclassifier on four benchmark datasets show that our proposed model outperformsthe current state-of-the-art approaches for generalized zero-shot learning.

Generalized Zero-Shot Learning using Multimodal Variational Auto-Encoder with Semantic Concepts