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

One of the key challenges in learning joint embeddings of multiplemodalities, e.g. of images and text, is to ensure coherent cross-modalsemantics that generalize across datasets. We propose to address this throughjoint Gaussian regularization of the latent representations. Building onWasserstein autoencoders (WAEs) to encode the input in each domain, we enforcethe latent embeddings to be similar to a Gaussian prior that is shared acrossthe two domains, ensuring compatible continuity of the encoded semanticrepresentations of images and texts. Semantic alignment is achieved throughsupervision from matching image-text pairs. To show the benefits of oursemi-supervised representation, we apply it to cross-modal retrieval and phraselocalization. We not only achieve state-of-the-art accuracy, but significantlybetter generalization across datasets, owing to the semantic continuity of thelatent space.

Joint Wasserstein Autoencoders for Aligning Multimodal Embeddings