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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Computational food analysis (CFA) naturally requires multi-modal evidence ofa particular food, e.g., images, recipe text, etc. A key to making CFA possibleis multi-modal shared representation learning, which aims to create a jointrepresentation of the multiple views (text and image) of the data. In this workwe propose a method for food domain cross-modal shared representation learningthat preserves the vast semantic richness present in the food data. Ourproposed method employs an effective transformer-based multilingual recipeencoder coupled with a traditional image embedding architecture. Here, wepropose the use of imperfect multilingual translations to effectivelyregularize the model while at the same time adding functionality acrossmultiple languages and alphabets. Experimental analysis on the public Recipe1Mdataset shows that the representation learned via the proposed methodsignificantly outperforms the current state-of-the-arts (SOTA) on retrievaltasks. Furthermore, the representational power of the learned representation isdemonstrated through a generative food image synthesis model conditioned onrecipe embeddings. Synthesized images can effectively reproduce the visualappearance of paired samples, indicating that the learned representationcaptures the joint semantics of both the textual recipe and its visual content,thus narrowing the modality gap.

Cross-Modal Retrieval and Synthesis (X-MRS): Closing the Modality Gap in Shared Representation Learning