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

Textual scene graph parsing has become increasingly important in variousvision-language applications, including image caption evaluation and imageretrieval. However, existing scene graph parsers that convert image captionsinto scene graphs often suffer from two types of errors. First, the generatedscene graphs fail to capture the true semantics of the captions or thecorresponding images, resulting in a lack of faithfulness. Second, thegenerated scene graphs have high inconsistency, with the same semanticsrepresented by different annotations.  To address these challenges, we propose a novel dataset, which involvesre-annotating the captions in Visual Genome (VG) using a new intermediaterepresentation called FACTUAL-MR. FACTUAL-MR can be directly converted intofaithful and consistent scene graph annotations. Our experimental resultsclearly demonstrate that the parser trained on our dataset outperforms existingapproaches in terms of faithfulness and consistency. This improvement leads toa significant performance boost in both image caption evaluation and zero-shotimage retrieval tasks. Furthermore, we introduce a novel metric for measuringscene graph similarity, which, when combined with the improved scene graphparser, achieves state-of-the-art (SOTA) results on multiple benchmark datasetsfor the aforementioned tasks. The code and dataset are available athttps://github.com/zhuang-li/FACTUAL .

FACTUAL: A Benchmark for Faithful and Consistent Textual Scene Graph Parsing