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

Recent visuolinguistic pre-trained models show promising progress on variousend tasks such as image retrieval and video captioning. Yet, they failmiserably on the recently proposed Winoground dataset, which challenges modelsto match paired images and English captions, with items constructed to overlaplexically but differ in meaning (e.g., "there is a mug in some grass" vs."there is some grass in a mug"). By annotating the dataset using newfine-grained tags, we show that solving the Winoground task requires not justcompositional language understanding, but a host of other abilities likecommonsense reasoning or locating small, out-of-focus objects in low-resolutionimages. In this paper, we identify the dataset's main challenges through asuite of experiments on related tasks (probing task, image retrieval task),data augmentation, and manual inspection of the dataset. Our analysis suggeststhat a main challenge in visuolinguistic models may lie in fusing visual andtextual representations, rather than in compositional language understanding.We release our annotation and code athttps://github.com/ajd12342/why-winoground-hard .

Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality