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

This paper presents a novel application of Generative Adverserial Networks(GANs) to study visual aspects of social processes. I train a a StyleGAN2-modelon a custom dataset of 14,564 images of London, sourced from Google Streetviewtaken in London. After training, I invert the images in the training set,finding points in the model's latent space that correspond to them, and compareresults from three inversion techniques. I connect each data point withmetadata from the Indices of Multiple Deprivation, describing income, healthand environmental quality in the area where the photographs were taken. It isthen possible to map which parts of the model's latent space encode visualfeatures that are distinctive for health, income and environmental quality, andcondition the synthesis of new images based on these factors. The syntheticimages created reflect visual features of social processes that were previouslyunknown and difficult to study, describing recurring visual differences betweendeprived and privileged areas in London. GANs are known for their capability toproduce a continuous range of images that exhibit visual differences. The papertests how to exploit this ability through visual comparisons in still images aswell as through an interactive website where users can guide image synthesiswith sliders. Though conditioned synthesis has its limitations and the resultsare difficult to validate, the paper points to the potential for generativemodels to be repurposed to be parts of social scientific methods.

Generative models for visualising abstract social processes: Guiding streetview image synthesis of StyleGAN2 with indices of deprivation