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/

Zendy Plus

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

Zendy Tools

Zendy Open

Over the past decade, many computational saliency prediction models have beenproposed for 2D images and videos. Considering that the human visual system hasevolved in a natural 3D environment, it is only natural to want to designvisual attention models for 3D content. Existing monocular saliency models arenot able to accurately predict the attentive regions when applied to 3Dimage/video content, as they do not incorporate depth information. This paperexplores stereoscopic video saliency prediction by exploiting both low-levelattributes such as brightness, color, texture, orientation, motion, and depth,as well as high-level cues such as face, person, vehicle, animal, text, andhorizon. Our model starts with a rough segmentation and quantifies severalintuitive observations such as the effects of visual discomfort level, depthabruptness, motion acceleration, elements of surprise, size and compactness ofthe salient regions, and emphasizing only a few salient objects in a scene. Anew fovea-based model of spatial distance between the image regions is adoptedfor considering local and global feature calculations. To efficiently fuse theconspicuity maps generated by our method to one single saliency map that ishighly correlated with the eye-fixation data, a random forest based algorithmis utilized. The performance of the proposed saliency model is evaluatedagainst the results of an eye-tracking experiment, which involved 24 subjectsand an in-house database of 61 captured stereoscopic videos. Our stereo videodatabase as well as the eye-tracking data are publicly available along withthis paper. Experiment results show that the proposed saliency predictionmethod achieves competitive performance compared to the state-of-the-artapproaches.

A Learning-Based Visual Saliency Prediction Model for Stereoscopic 3D Video (LBVS-3D)