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

Salient object detection (SOD) in panoramic video is still in the initialexploration stage. The indirect application of 2D video SOD method to thedetection of salient objects in panoramic video has many unmet challenges, suchas low detection accuracy, high model complexity, and poor generalizationperformance. To overcome these hurdles, we design an Inter-Layer Attention(ILA) module, an Inter-Layer weight (ILW) module, and a Bi-Modal Attention(BMA) module. Based on these modules, we propose a Spatial-Temporal Dual-ModeMixed Flow Network (STDMMF-Net) that exploits the spatial flow of panoramicvideo and the corresponding optical flow for SOD. First, the ILA modulecalculates the attention between adjacent level features of consecutive framesof panoramic video to improve the accuracy of extracting salient objectfeatures from the spatial flow. Then, the ILW module quantifies the salientobject information contained in the features of each level to improve thefusion efficiency of the features of each level in the mixed flow. Finally, theBMA module improves the detection accuracy of STDMMF-Net. A large number ofsubjective and objective experimental results testify that the proposed methoddemonstrates better detection accuracy than the state-of-the-art (SOTA)methods. Moreover, the comprehensive performance of the proposed method isbetter in terms of memory required for model inference, testing time,complexity, and generalization performance.

A Spatial-Temporal Dual-Mode Mixed Flow Network for Panoramic Video Salient Object Detection