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/

Zendy Plus

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

Zendy Tools

Zendy Open

Structured scene descriptions of images are useful for the automaticprocessing and querying of large image databases. We show how the combinationof a semantic and a visual statistical model can improve on the task of mappingimages to their associated scene description. In this paper we consider scenedescriptions which are represented as a set of triples (subject, predicate,object), where each triple consists of a pair of visual objects, which appearin the image, and the relationship between them (e.g. man-riding-elephant,man-wearing-hat). We combine a standard visual model for object detection,based on convolutional neural networks, with a latent variable model for linkprediction. We apply multiple state-of-the-art link prediction methods andcompare their capability for visual relationship detection. One of the mainadvantages of link prediction methods is that they can also generalize totriples, which have never been observed in the training data. Our experimentalresults on the recently published Stanford Visual Relationship dataset, achallenging real world dataset, show that the integration of a semantic modelusing link prediction methods can significantly improve the results for visualrelationship detection. Our combined approach achieves superior performancecompared to the state-of-the-art method from the Stanford computer visiongroup.

Improving Visual Relationship Detection using Semantic Modeling of Scene Descriptions