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

Automated image captioning has the potential to be a useful tool for peoplewith vision impairments. Images taken by this user group are often noisy, whichleads to incorrect and even unsafe model predictions. In this paper, we proposea quality-agnostic framework to improve the performance and robustness of imagecaptioning models for visually impaired people. We address this problem fromthree angles: data, model, and evaluation. First, we show how data augmentationtechniques for generating synthetic noise can address data sparsity in thisdomain. Second, we enhance the robustness of the model by expanding astate-of-the-art model to a dual network architecture, using the augmented dataand leveraging different consistency losses. Our results demonstrate increasedperformance, e.g. an absolute improvement of 2.15 on CIDEr, compared tostate-of-the-art image captioning networks, as well as increased robustness tonoise with up to 3 points improvement on CIDEr in more noisy settings. Finally,we evaluate the prediction reliability using confidence calibration on imageswith different difficulty/noise levels, showing that our models perform morereliably in safety-critical situations. The improved model is part of anassisted living application, which we develop in partnership with the RoyalNational Institute of Blind People.

Quality-agnostic Image Captioning to Safely Assist People with Vision Impairment