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

Researchers have proposed to use data of human preference feedback tofine-tune text-to-image generative models. However, the scalability of humanfeedback collection has been limited by its reliance on manual annotation.Therefore, we develop and test a method to automatically annotate userpreferences from their spontaneous facial expression reaction to the generatedimages. We collect a dataset of Facial Expression Reaction to Generated Images(FERGI) and show that the activations of multiple facial action units (AUs) arehighly correlated with user evaluations of the generated images. Specifically,AU4 (brow lowerer) is most consistently reflective of negative evaluations ofthe generated image. This can be useful in two ways. Firstly, we canautomatically annotate user preferences between image pairs with substantialdifference in AU4 responses to them with an accuracy significantlyoutperforming state-of-the-art scoring models. Secondly, directly integratingthe AU4 responses with the scoring models improves their consistency with humanpreferences. Additionally, the AU4 response best reflects the user's evaluationof the image fidelity, making it complementary to the state-of-the-art scoringmodels, which are generally better at reflecting image-text alignment. Finally,this method of automatic annotation with facial expression analysis can bepotentially generalized to other generation tasks. The code is available athttps://github.com/ShuangquanFeng/FERGI, and the dataset is also available atthe same link for research purposes.

FERGI: Automatic Annotation of User Preferences for Text-to-Image Generation from Spontaneous Facial Expression Reaction