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

Pairwise comparison data arise in many domains with subjective assessmentexperiments, for example in image and video quality assessment. In theseexperiments observers are asked to express a preference between two conditions.However, many pairwise comparison protocols require a large number ofcomparisons to infer accurate scores, which may be unfeasible when eachcomparison is time-consuming (e.g. videos) or expensive (e.g. medical imaging).This motivates the use of an active sampling algorithm that chooses only themost informative pairs for comparison. In this paper we propose ASAP, an activesampling algorithm based on approximate message passing and expectedinformation gain maximization. Unlike most existing methods, which rely onpartial updates of the posterior distribution, we are able to perform fullupdates and therefore much improve the accuracy of the inferred scores. Thealgorithm relies on three techniques for reducing computational cost: inferencebased on approximate message passing, selective evaluations of the informationgain, and selecting pairs in a batch that forms a minimum spanning tree of theinverse of information gain. We demonstrate, with real and synthetic data, thatASAP offers the highest accuracy of inferred scores compared to the existingmethods. We also provide an open-source GPU implementation of ASAP forlarge-scale experiments.

Active Sampling for Pairwise Comparisons via Approximate Message Passing and Information Gain Maximization