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

Understanding images and text together is an important aspect of cognitionand building advanced Artificial Intelligence (AI) systems. As a community, wehave achieved good benchmarks over language and vision domains separately,however joint reasoning is still a challenge for state-of-the-art computervision and natural language processing (NLP) systems. We propose a novel taskto derive joint inference about a given image-text modality and compile theVisuo-Linguistic Question Answering (VLQA) challenge corpus in a questionanswering setting. Each dataset item consists of an image and a readingpassage, where questions are designed to combine both visual and textualinformation i.e., ignoring either modality would make the questionunanswerable. We first explore the best existing vision-language architecturesto solve VLQA subsets and show that they are unable to reason well. We thendevelop a modular method with slightly better baseline performance, but it isstill far behind human performance. We believe that VLQA will be a goodbenchmark for reasoning over a visuo-linguistic context. The dataset, code andleaderboard is available at https://shailaja183.github.io/vlqa/.

Visuo-Linguistic Question Answering (VLQA) Challenge