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

Due to the strong correlation between visual attention and perceptualquality, many methods attempt to use human saliency information for imagequality assessment. Although this mechanism can get good performance, thenetworks require human saliency labels, which is not easily accessible foromnidirectional images (ODI). To alleviate this issue, we propose a spatialattention-based perceptual quality prediction network for non-reference qualityassessment on ODIs (SAP-net). To drive our SAP-net, we establish a large-scaleIQA dataset of ODIs (IQA-ODI), which is composed of subjective scores of 200subjects on 1,080 ODIs. In IQA-ODI, there are 120 high quality ODIs asreference, and 960 ODIs with impairments in both JPEG compression and mapprojection. Without any human saliency labels, our network can adaptivelyestimate human perceptual quality on impaired ODIs through a self-attentionmanner, which significantly promotes the prediction performance of qualityscores. Moreover, our method greatly reduces the computational complexity inquality assessment task on ODIs. Extensive experiments validate that ournetwork outperforms 9 state-of-the-art methods for quality assessment on ODIs.The dataset and code have been available on \url{https://github.com/yanglixiaoshen/SAP-Net}.

Spatial Attention-based Non-reference Perceptual Quality Prediction Network for Omnidirectional Images