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

The growing interest in omnidirectional videos (ODVs) that capture the fullfield-of-view (FOV) has gained 360-degree saliency prediction importance incomputer vision. However, predicting where humans look in 360-degree scenespresents unique challenges, including spherical distortion, high resolution,and limited labelled data. We propose a novel vision-transformer-based modelfor omnidirectional videos named SalViT360 that leverages tangent imagerepresentations. We introduce a spherical geometry-aware spatiotemporalself-attention mechanism that is capable of effective omnidirectional videounderstanding. Furthermore, we present a consistency-based unsupervisedregularization term for projection-based 360-degree dense-prediction models toreduce artefacts in the predictions that occur after inverse projection. Ourapproach is the first to employ tangent images for omnidirectional saliencyprediction, and our experimental results on three ODV saliency datasetsdemonstrate its effectiveness compared to the state-of-the-art.

Spherical Vision Transformer for 360-degree Video Saliency Prediction