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

Thanks to the ability of providing an immersive and interactive experience,the uptake of 360 degree image content has been rapidly growing in consumer andindustrial applications. Compared to planar 2D images, saliency prediction for360 degree images is more challenging due to their high resolutions andspherical viewing ranges. Currently, most high-performance saliency predictionmodels for omnidirectional images (ODIs) rely on deeper or broaderconvolutional neural networks (CNNs), which benefit from CNNs' superior featurerepresentation capabilities while suffering from their high computationalcosts. In this paper, inspired by the human visual cognitive process, i.e.,human being's perception of a visual scene is always accomplished by multiplestages of analysis, we propose a novel multi-stage recurrent generativeadversarial networks for ODIs dubbed MRGAN360, to predict the saliency mapsstage by stage. At each stage, the prediction model takes as input the originalimage and the output of the previous stage and outputs a more accurate saliencymap. We employ a recurrent neural network among adjacent prediction stages tomodel their correlations, and exploit a discriminator at the end of each stageto supervise the output saliency map. In addition, we share the weights amongall the stages to obtain a lightweight architecture that is computationallycheap. Extensive experiments are conducted to demonstrate that our proposedmodel outperforms the state-of-the-art model in terms of both predictionaccuracy and model size.

MRGAN360: Multi-stage Recurrent Generative Adversarial Network for 360 Degree Image Saliency Prediction