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

Salient object detection has achieved great improvement by using the FullyConvolution Network (FCN). However, the FCN-based U-shape architecture maycause the dilution problem in the high-level semantic information during theup-sample operations in the top-down pathway. Thus, it can weaken the abilityof salient object localization and produce degraded boundaries. To this end, inorder to overcome this limitation, we propose a novel pyramid self-attentionmodule (PSAM) and the adoption of an independent feature-complementingstrategy. In PSAM, self-attention layers are equipped after multi-scale pyramidfeatures to capture richer high-level features and bring larger receptivefields to the model. In addition, a channel-wise attention module is alsoemployed to reduce the redundant features of the FPN and provide refinedresults. Experimental analysis shows that the proposed PSAM effectivelycontributes to the whole model so that it outperforms state-of-the-art resultsover five challenging datasets. Finally, quantitative results show that PSAMgenerates clear and integral salient maps which can provide further help toother computer vision tasks, such as object detection and semanticsegmentation.

Salient Object Detection Combining a Self-attention Module and a Feature Pyramid Network