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

We study the problem of recognizing visual entities from the textualdescriptions of their classes. Specifically, given birds' images with free-textdescriptions of their species, we learn to classify images of previously-unseenspecies based on specie descriptions. This setup has been studied in the visioncommunity under the name zero-shot learning from text, focusing on learning totransfer knowledge about visual aspects of birds from seen classes topreviously-unseen ones. Here, we suggest focusing on the textual descriptionand distilling from the description the most relevant information toeffectively match visual features to the parts of the text that discuss them.Specifically, (1) we propose to leverage the similarity between species,reflected in the similarity between text descriptions of the species. (2) wederive visual summaries of the texts, i.e., extractive summaries that focus onthe visual features that tend to be reflected in images. We propose a simpleattention-based model augmented with the similarity and visual summariescomponents. Our empirical results consistently and significantly outperform thestate-of-the-art on the largest benchmarks for text-based zero-shot learning,illustrating the critical importance of texts for zero-shot image-recognition.

ZEST: Zero-shot Learning from Text Descriptions using Textual Similarity and Visual Summarization